1
|
Wang D, Ma X, Schulz PE, Jiang X, Kim Y. Clinical outcome-guided deep temporal clustering for disease progression subtyping. J Biomed Inform 2024; 158:104732. [PMID: 39357664 DOI: 10.1016/j.jbi.2024.104732] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2024] [Revised: 09/24/2024] [Accepted: 09/28/2024] [Indexed: 10/04/2024]
Abstract
OBJECTIVE Complex diseases exhibit heterogeneous progression patterns, necessitating effective capture and clustering of longitudinal changes to identify disease subtypes for personalized treatments. However, existing studies often fail to design clustering-specific representations or neglect clinical outcomes, thereby limiting the interpretability and clinical utility. METHOD We design a unified framework for subtyping longitudinal progressive diseases. We focus on effectively integrating all data from disease progressions and improving patient representation for downstream clustering. Specifically, we propose a clinical Outcome-Guided Deep Temporal Clustering (OG-DTC) that generates representations informed by clustering and clinical outcomes. A GRU-based seq2seq architecture captures the temporal dynamics, and the model integrates k-means clustering and outcome regression to facilitate the formation of clustering structures and the integration of clinical outcomes. The learned representations are clustered using a Gaussian mixture model to identify distinct subtypes. The clustering results are extensively validated through reproducibility, stability, and significance tests. RESULTS We demonstrated the efficacy of our framework by applying it to three Alzheimer's Disease (AD) clinical trials. Through the AD case study, we identified three distinct subtypes with unique patterns associated with differentiated clinical declines across multiple measures. The ablation study revealed the contributions of each component in the model and showed that jointly optimizing the full model improved patient representations for clustering. Extensive validations showed that the derived clustering is reproducible, stable, and significant. CONCLUSION Our temporal clustering framework can derive robust clustering applicable for subtyping longitudinal progressive diseases and has the potential to account for subtype variability in clinical outcomes.
Collapse
Affiliation(s)
- Dulin Wang
- McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Xiaotian Ma
- McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Paul E Schulz
- Department of Neurology, McGovern Medical School, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Xiaoqian Jiang
- McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Yejin Kim
- McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA.
| |
Collapse
|
2
|
Rajan R, Holla VV, Kamble N, Yadav R, Pal PK. Genetic heterogeneity of early onset Parkinson disease: The dilemma of clinico-genetic correlation. Parkinsonism Relat Disord 2024:107146. [PMID: 39313403 DOI: 10.1016/j.parkreldis.2024.107146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/16/2024] [Revised: 09/05/2024] [Accepted: 09/08/2024] [Indexed: 09/25/2024]
Abstract
With advances in genetic testing increasing proportion of early onset Parkinson disease (EOPD) are being identified to have an underlying genetic aetiology. This is can be in the form of either highly penetrant genes associated with phenotypes with monogenic or mendelian inheritance patterns or those genes known as risk factor genes which confer an increased risk of PD in an individual. Both of them can modify the phenotypic manifestation in a patient with PD. This improved knowledge has helped in deciphering the intricate role of various cellular pathways in the pathophysiology of PD including both early and late and even sporadic PD. However, the phenotypic and genotypic heterogeneity is a major challenge. Different deleterious alterations in a same gene can result in a spectrum of presentation spanning from juvenile to late onset and typical to atypical parkinsonism manifestation. Similarly, a single phenotype can occur due to abnormality in two or more different genes. This conundrum poses a dilemma in the clinical approach and in understanding the clinico-genetic correlation. Understanding the clinico-genetic correlation carries even more importance especially when genetic testing is either not accessible or affordable or in many regions both. In this narrative review, we aim to discuss briefly the approach to various PARK gene related EOPD and describe in detail the clinico-genetic correlation of individual type of PARK gene related genetic EOPD with respect to their classical clinical presentation, pathophysiology, investigation findings and treatment response to medication and surgery.
Collapse
Affiliation(s)
- Roopa Rajan
- Department of Neurology, All India Institute of Medical Sciences, New Delhi, India
| | - Vikram V Holla
- Department of Neurology, National Institute of Mental Health and Neurosciences, Bengaluru, India
| | - Nitish Kamble
- Department of Neurology, National Institute of Mental Health and Neurosciences, Bengaluru, India
| | - Ravi Yadav
- Department of Neurology, National Institute of Mental Health and Neurosciences, Bengaluru, India
| | - Pramod Kumar Pal
- Department of Neurology, National Institute of Mental Health and Neurosciences, Bengaluru, India.
| |
Collapse
|
3
|
Culicetto L, Formica C, Lo Buono V, Latella D, Maresca G, Brigandì A, Sorbera C, Di Lorenzo G, Quartarone A, Marino S. Possible Implications of Managing Alexithymia on Quality of Life in Parkinson's Disease: A Systematic Review. PARKINSON'S DISEASE 2024; 2024:5551796. [PMID: 39228428 PMCID: PMC11371456 DOI: 10.1155/2024/5551796] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/02/2024] [Revised: 06/17/2024] [Accepted: 08/16/2024] [Indexed: 09/05/2024]
Abstract
Alexithymia, characterized by difficulty in recognizing and verbalizing emotions, is reported to be more prevalent in subjects with Parkinson's disease (PD) than in the general population. Although it is one of the nonmotor symptoms of PD, alexithymia is often overlooked in clinical practice. The aim of this systematic review is to investigate the prevalence of alexithymia in PD, assess its impact on quality of life, and explore the rehabilitation approaches for alexithymia. Research articles, selected from PubMed, Scopus, and Web of Science, were limited to those published in English from 2013 to 2023. The search terms combined were "Alexithymia," "Parkinson's disease,", and "Quality of life." Current literature review indicates that alexithymia is commonly assessed using the Toronto Alexithymia Scale (TAS-20), and it is associated with deficits in visuospatial and executive functions. Presently, rehabilitation interventions for alexithymia are scarce, and their effectiveness remains controversial. Future research should focus on developing comprehensive assessments and rehabilitation strategies for emotional processing, considering its significant impact on the quality of life of both patients and caregivers.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | | | | | - Silvia Marino
- IRCCS Centro Neurolesi “Bonino Pulejo”, Messina, Italy
| |
Collapse
|
4
|
Kim MS, Kim H, Lee G. Precision Medicine in Parkinson's Disease Using Induced Pluripotent Stem Cells. Adv Healthc Mater 2024; 13:e2303041. [PMID: 38269602 DOI: 10.1002/adhm.202303041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 01/17/2024] [Indexed: 01/26/2024]
Abstract
Parkinson's disease (PD) is one of the most devastating neurological diseases; however, there is no effective cure yet. The availability of human induced pluripotent stem cells (iPSCs) provides unprecedented opportunities to understand the pathogenic mechanism and identification of new therapy for PD. Here a new model system of PD, including 2D human iPSC-derived midbrain dopaminergic (mDA) neurons, 3D iPSC-derived midbrain organoids (MOs) with cellular complexity, and more advanced microphysiological systems (MPS) with 3D organoids, is introduced. It is believed that successful integrations and applications of iPSC, organoid, and MPS technologies can bring new insight on PD's pathogenesis that will lead to more effective treatments for this debilitating disease.
Collapse
Affiliation(s)
- Min Seong Kim
- Institute for Cell Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA
- Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA
| | - Hyesoo Kim
- Institute for Cell Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA
- Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA
| | - Gabsang Lee
- Institute for Cell Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA
- Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA
- The Solomon Snyder Department of Neuroscience, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA
| |
Collapse
|
5
|
Cash TV, Lessov-Schlaggar CN, Foster ER, Myers PS, Jackson JJ, Maiti B, Kotzbauer PT, Perlmutter JS, Campbell MC. Replication and reliability of Parkinson's disease clinical subtypes. Parkinsonism Relat Disord 2024; 124:107016. [PMID: 38838453 DOI: 10.1016/j.parkreldis.2024.107016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 04/24/2024] [Accepted: 05/19/2024] [Indexed: 06/07/2024]
Abstract
BACKGROUND We recently identified three distinct Parkinson's disease subtypes: "motor only" (predominant motor deficits with intact cognition and psychiatric function); "psychiatric & motor" (prominent psychiatric symptoms and moderate motor deficits); "cognitive & motor" (cognitive and motor deficits). OBJECTIVE We used an independent cohort to replicate and assess reliability of these Parkinson's disease subtypes. METHODS We tested our original subtype classification with an independent cohort (N = 100) of Parkinson's disease participants without dementia and the same comprehensive evaluations assessing motor, cognitive, and psychiatric function. Next, we combined the original (N = 162) and replication (N = 100) datasets to test the classification model with the full combined dataset (N = 262). We also generated 10 random split-half samples of the combined dataset to establish the reliability of the subtype classifications. Latent class analyses were applied to the replication, combined, and split-half samples to determine subtype classification. RESULTS First, LCA supported the three-class solution - Motor Only, Psychiatric & Motor, and Cognitive & Motor- in the replication sample. Next, using the larger, combined sample, LCA again supported the three subtype groups, with the emergence of a potential fourth group defined by more severe motor deficits. Finally, split-half analyses showed that the three-class model also had the best fit in 13/20 (65%) split-half samples; two-class and four-class solutions provided the best model fit in five (25%) and two (10%) split-half replications, respectively. CONCLUSIONS These results support the reproducibility and reliability of the Parkinson's disease behavioral subtypes of motor only, psychiatric & motor, and cognitive & motor groups.
Collapse
Affiliation(s)
- Therese V Cash
- Department of Neurology, Washington University School of Medicine, USA
| | | | - Erin R Foster
- Department of Neurology, Washington University School of Medicine, USA; Department of Psychiatry, Washington University School of Medicine, USA; Program in Occupational Therapy, Washington University School of Medicine, USA
| | - Peter S Myers
- Department of Neurology, Washington University School of Medicine, USA
| | - Joshua J Jackson
- Department of Psychological and Brain Sciences, Washington University in St. Louis, USA
| | - Baijayanta Maiti
- Department of Neurology, Washington University School of Medicine, USA; Department of Radiology, Washington University School of Medicine, USA
| | - Paul T Kotzbauer
- Department of Neurology, Washington University School of Medicine, USA
| | - Joel S Perlmutter
- Department of Neurology, Washington University School of Medicine, USA; Department of Radiology, Washington University School of Medicine, USA; Department of Neuroscience, Washington University School of Medicine, USA; Program in Occupational Therapy, Washington University School of Medicine, USA; Program in Physical Therapy, Washington University School of Medicine, USA
| | - Meghan C Campbell
- Department of Neurology, Washington University School of Medicine, USA; Department of Radiology, Washington University School of Medicine, USA.
| |
Collapse
|
6
|
Mulroy E, Erro R, Bhatia KP, Hallett M. Refining the clinical diagnosis of Parkinson's disease. Parkinsonism Relat Disord 2024; 122:106041. [PMID: 38360507 PMCID: PMC11069446 DOI: 10.1016/j.parkreldis.2024.106041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/06/2024] [Accepted: 02/09/2024] [Indexed: 02/17/2024]
Abstract
Our ability to define, understand, and classify Parkinson's disease (PD) has undergone significant changes since the disorder was first described in 1817. Clinical features and neuropathologic signatures can now be supplemented by in-vivo interrogation of genetic and biological substrates of disease, offering great opportunity for further refining the diagnosis of PD. In this mini-review, we discuss the historical perspectives which shaped our thinking surrounding the definition and diagnosis of PD. We highlight the clinical, genetic, pathologic and biologic diversity which underpins the condition, and proceed to discuss how recent developments in our ability to define biologic and pathologic substrates of disease might impact PD definition, diagnosis, individualised prognostication, and personalised clinical care. We argue that Parkinson's 'disease', as currently diagnosed in the clinic, is actually a syndrome. It is the outward manifestation of any array of potential dysfunctional biologic processes, neuropathological changes, and disease aetiologies, which culminate in common outward clinical features which we term PD; each person has their own unique disease, which we can now define with increasing precision. This is an exciting time in PD research and clinical care. Our ability to refine the clinical diagnosis of PD, incorporating in-vivo assessments of disease biology, neuropathology, and neurogenetics may well herald the era of biologically-based, precision medicine approaches PD management. With this however comes a number of challenges, including how to integrate these technologies into clinical practice in a way which is acceptable to patients, promotes meaningful changes to care, and minimises health economic impact.
Collapse
Affiliation(s)
- Eoin Mulroy
- Department of Clinical and Movement Neurosciences, UCL Queen Square Institute of Neurology, London, WC1N 3BG, UK
| | - Roberto Erro
- Department of Medicine, Surgery and Dentistry "Scuola Medica Salernitana", University of Salerno, Baronissi, (SA), Italy
| | - Kailash P Bhatia
- Department of Clinical and Movement Neurosciences, UCL Queen Square Institute of Neurology, London, WC1N 3BG, UK
| | - Mark Hallett
- Human Motor Control Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA.
| |
Collapse
|
7
|
Gokuladhas S, Fadason T, Farrow S, Cooper A, O'Sullivan JM. Discovering genetic mechanisms underlying the co-occurrence of Parkinson's disease and non-motor traits. NPJ Parkinsons Dis 2024; 10:27. [PMID: 38263313 PMCID: PMC10805842 DOI: 10.1038/s41531-024-00638-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Accepted: 01/09/2024] [Indexed: 01/25/2024] Open
Abstract
Understanding the biological mechanisms that underlie the non-motor symptoms of Parkinson's disease (PD) requires comprehensive frameworks that unravel the complex interplay of genetic risk factors. Here, we used a disease-agnostic brain cortex gene regulatory network integrated with Mendelian Randomization analyses that identified 19 genes whose changes in expression were causally linked to PD. We further used the network to identify genes that are regulated by PD-associated genome-wide association study (GWAS) SNPs. Extended protein interaction networks derived from PD-risk genes and PD-associated SNPs identified convergent impacts on biological pathways and phenotypes, connecting PD with established co-occurring traits, including non-motor symptoms. These findings hold promise for therapeutic development. In conclusion, while distinct sets of genes likely influence PD risk and outcomes, the existence of genes in common and intersecting pathways associated with other traits suggests that they may contribute to both increased PD risk and symptom heterogeneity observed in people with Parkinson's.
Collapse
Affiliation(s)
- Sreemol Gokuladhas
- The Liggins Institute, University of Auckland, Auckland, 1023, New Zealand
| | - Tayaza Fadason
- The Liggins Institute, University of Auckland, Auckland, 1023, New Zealand
- Maurice Wilkins Centre for Molecular Biodiscovery, Auckland, 1010, New Zealand
| | - Sophie Farrow
- The Liggins Institute, University of Auckland, Auckland, 1023, New Zealand
- Maurice Wilkins Centre for Molecular Biodiscovery, Auckland, 1010, New Zealand
| | - Antony Cooper
- St Vincent's Clinical School, UNSW Sydney, Sydney, NSW, Australia
- Australian Parkinson's Mission, Garvan Institute of Medical Research, Sydney, New South Wales, Australia
| | - Justin M O'Sullivan
- The Liggins Institute, University of Auckland, Auckland, 1023, New Zealand.
- Maurice Wilkins Centre for Molecular Biodiscovery, Auckland, 1010, New Zealand.
- Australian Parkinson's Mission, Garvan Institute of Medical Research, Sydney, New South Wales, Australia.
- MRC Lifecourse Epidemiology Unit, University of Southampton, Southampton, UK.
- Singapore Institute for Clinical Sciences, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
| |
Collapse
|
8
|
Arjmand B, Kokabi-Hamidpour S, Aghayan HR, Alavi-Moghadam S, Arjmand R, Rezaei-Tavirani M, Goodarzi P, Nasli-Esfahani E, Nikandish M. Stem Cell-Based Modeling Protocol for Parkinson's Disease. Methods Mol Biol 2024; 2736:105-114. [PMID: 36749483 DOI: 10.1007/7651_2022_473] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
Parkinson's disease is a progressive neurodegenerative disorder, which is mainly characterized by unintended or uncontrollable body movements. Pathophysiologically, disturbances in the neurotransmission system of the brain like dopaminergic system and synaptic dysfunction are classified as top-rated causes of the onset of Parkinson's disease, which symptoms can be different according to the involvement of neurotransmission system type and the effect of the disease on the motor and non-motor systems. Although some pharmacological and non-pharmacological approaches have been applied to control and slow down the progression of the disease, a definitive cure has not yet been discovered. One of the factors involved in this issue is the lack of appropriate laboratory models to investigate the pathological mechanisms involved in the disease as well as various aspects of candidate drugs, which ultimately leads to the failure of drug discovery and development pipelines. To deal with these challenges, the application of stem cells, especially cellular reprogramming of somatic cells to human pluripotent stem cells, also known as induced pluripotent stem cells, has been able to promise a new chapter in the modeling of Parkinson's disease. Induced pluripotent stem cells have the stemness capability; therefore, they can differentiate into any type of cell such as nerve cells. Also, since these cells are obtained from the reprogramming of somatic cells in the patient's body, they maintain the patient's genetic content, which can play an important role in increasing the quality of disease modeling and the validity of the results of laboratory studies. Therefore, the procedure for modeling induced pluripotent stem cells for Parkinson's disease is explained in this chapter.
Collapse
Affiliation(s)
- Babak Arjmand
- Cell Therapy and Regenerative Medicine Research Center, Endocrinology and Metabolism Molecular-Cellular Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran.
- Iranian Cancer Control Center (MACSA), Tehran, Iran.
| | - Shayesteh Kokabi-Hamidpour
- Cell Therapy and Regenerative Medicine Research Center, Endocrinology and Metabolism Molecular-Cellular Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Hamid Reza Aghayan
- Cell Therapy and Regenerative Medicine Research Center, Endocrinology and Metabolism Molecular-Cellular Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Sepideh Alavi-Moghadam
- Cell Therapy and Regenerative Medicine Research Center, Endocrinology and Metabolism Molecular-Cellular Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Rasta Arjmand
- Cell Therapy and Regenerative Medicine Research Center, Endocrinology and Metabolism Molecular-Cellular Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | | | - Parisa Goodarzi
- Cell Therapy and Regenerative Medicine Research Center, Endocrinology and Metabolism Molecular-Cellular Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Ensieh Nasli-Esfahani
- Diabetes Research Center, Endocrinology and Metabolism Clinical Sciences Institute, Tehran University of Medical Sciences, Tehran, Islamic Republic of Iran
| | - Mohsen Nikandish
- AJA Cancer Epidemiology Research and Treatment Center (AJA-CERTC), AJA University of Medical Sciences, Tehran, Iran
| |
Collapse
|
9
|
Boyton I, Valenzuela SM, Collins-Praino LE, Care A. Neuronanomedicine for Alzheimer's and Parkinson's disease: Current progress and a guide to improve clinical translation. Brain Behav Immun 2024; 115:631-651. [PMID: 37967664 DOI: 10.1016/j.bbi.2023.11.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/26/2023] [Revised: 09/19/2023] [Accepted: 11/08/2023] [Indexed: 11/17/2023] Open
Abstract
Neuronanomedicine is an emerging multidisciplinary field that aims to create innovative nanotechnologies to treat major neurodegenerative disorders, such as Alzheimer's (AD) and Parkinson's disease (PD). A key component of neuronanomedicine are nanoparticles, which can improve drug properties and demonstrate enhanced safety and delivery across the blood-brain barrier, a major improvement on existing therapeutic approaches. In this review, we critically analyze the latest nanoparticle-based strategies to modify underlying disease pathology to slow or halt AD/PD progression. We find that a major roadblock for neuronanomedicine translation to date is a poor understanding of how nanoparticles interact with biological systems (i.e., bio-nano interactions), which is partly due to inconsistent reporting in published works. Accordingly, this review makes a set of specific recommendations to help guide researchers to harness the unique properties of nanoparticles and thus realise breakthrough treatments for AD/PD.
Collapse
Affiliation(s)
- India Boyton
- School of Life Sciences, University of Technology Sydney, Gadigal Country, NSW 2007, Australia
| | - Stella M Valenzuela
- School of Life Sciences, University of Technology Sydney, Gadigal Country, NSW 2007, Australia
| | | | - Andrew Care
- School of Life Sciences, University of Technology Sydney, Gadigal Country, NSW 2007, Australia.
| |
Collapse
|
10
|
Thunold HH, Riegler MA, Yazidi A, Hammer HL. A Deep Diagnostic Framework Using Explainable Artificial Intelligence and Clustering. Diagnostics (Basel) 2023; 13:3413. [PMID: 37998548 PMCID: PMC10670034 DOI: 10.3390/diagnostics13223413] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 11/03/2023] [Accepted: 11/06/2023] [Indexed: 11/25/2023] Open
Abstract
An important part of diagnostics is to gain insight into properties that characterize a disease. Machine learning has been used for this purpose, for instance, to identify biomarkers in genomics. However, when patient data are presented as images, identifying properties that characterize a disease becomes far more challenging. A common strategy involves extracting features from the images and analyzing their occurrence in healthy versus pathological images. A limitation of this approach is that the ability to gain new insights into the disease from the data is constrained by the information in the extracted features. Typically, these features are manually extracted by humans, which further limits the potential for new insights. To overcome these limitations, in this paper, we propose a novel framework that provides insights into diseases without relying on handcrafted features or human intervention. Our framework is based on deep learning (DL), explainable artificial intelligence (XAI), and clustering. DL is employed to learn deep patterns, enabling efficient differentiation between healthy and pathological images. Explainable artificial intelligence (XAI) visualizes these patterns, and a novel "explanation-weighted" clustering technique is introduced to gain an overview of these patterns across multiple patients. We applied the method to images from the gastrointestinal tract. In addition to real healthy images and real images of polyps, some of the images had synthetic shapes added to represent other types of pathologies than polyps. The results show that our proposed method was capable of organizing the images based on the reasons they were diagnosed as pathological, achieving high cluster quality and a rand index close to or equal to one.
Collapse
Affiliation(s)
- Håvard Horgen Thunold
- Department of Compute Science, Faculty of Technology, Art and Design, Oslo Metropolitan University, 0176 Oslo, Norway; (H.H.T.); (M.A.R.); (A.Y.)
| | - Michael A. Riegler
- Department of Compute Science, Faculty of Technology, Art and Design, Oslo Metropolitan University, 0176 Oslo, Norway; (H.H.T.); (M.A.R.); (A.Y.)
- Department of Holistic Systems, SimulaMet, 0176 Oslo, Norway
| | - Anis Yazidi
- Department of Compute Science, Faculty of Technology, Art and Design, Oslo Metropolitan University, 0176 Oslo, Norway; (H.H.T.); (M.A.R.); (A.Y.)
| | - Hugo L. Hammer
- Department of Compute Science, Faculty of Technology, Art and Design, Oslo Metropolitan University, 0176 Oslo, Norway; (H.H.T.); (M.A.R.); (A.Y.)
- Department of Holistic Systems, SimulaMet, 0176 Oslo, Norway
| |
Collapse
|
11
|
Tall P, Qamar MA, Rosenzweig I, Raeder V, Sauerbier A, Heidemarie Z, Falup-Pecurariu C, Chaudhuri KR. The Park Sleep subtype in Parkinson's disease: from concept to clinic. Expert Opin Pharmacother 2023; 24:1725-1736. [PMID: 37561080 DOI: 10.1080/14656566.2023.2242786] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Accepted: 07/27/2023] [Indexed: 08/11/2023]
Abstract
INTRODUCTION The heterogeneity of Parkinson's disease (PD) is evident from descriptions of non-motor (NMS) subtypes and Park Sleep, originally identified by Sauerbier et al. 2016, is one such clinical subtype associated with the predominant clinical presentation of sleep dysfunctions including excessive daytime sleepiness (EDS), along with insomnia. AREAS COVERED A literature search was conducted using the PubMed, Medline, Embase, and Web of Science databases, accessed between 1 February 2023 and 28 March 2023. In this review, we describe the clinical subtype of Park Sleep and related 'tests' ranging from polysomnography to investigational neuromelanin MRI brain scans and some tissue-based biological markers. EXPERT OPINION Cholinergic, noradrenergic, and serotonergic systems are dominantly affected in PD. Park Sleep subtype is hypothesized to be associated primarily with serotonergic deficit, clinically manifesting as somnolence and narcoleptic events (sleep attacks), with or without rapid eye movement behavior disorder (RBD). In clinic, Park Sleep recognition may drive lifestyle changes (e.g. driving) along with therapy adjustments as Park Sleep patients may be sensitive to dopamine D3 active agonists, such as ropinirole and pramipexole. Specific dashboard scores based personalized management options need to be implemented and include pharmacological, non-pharmacological, and lifestyle linked advice.
Collapse
Affiliation(s)
- Phoebe Tall
- Department of Neuroscience, Institute of Psychiatry, Psychology, and Neuroscience (IoPpn), King's College London, London, UK
- Parkinson's Foundation Centre of Excellence, King's College Hospital NHS Foundation Trust, London, UK
| | - Mubasher A Qamar
- Department of Neuroscience, Institute of Psychiatry, Psychology, and Neuroscience (IoPpn), King's College London, London, UK
- Parkinson's Foundation Centre of Excellence, King's College Hospital NHS Foundation Trust, London, UK
| | - Ivana Rosenzweig
- Sleep and Brain Plasticity Centre, Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience (IoPpn), King's College London, London, UK
- Sleep Disorder Centre, Nuffield House, Guy's Hospital, London, UK
| | - Vanessa Raeder
- Parkinson's Foundation Centre of Excellence, King's College Hospital NHS Foundation Trust, London, UK
- Department of Neurology and Experimental Neurology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität, Berlin, Germany
| | - Anna Sauerbier
- Department of Neuroscience, Institute of Psychiatry, Psychology, and Neuroscience (IoPpn), King's College London, London, UK
- Department of Neurology, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany
| | - Zach Heidemarie
- Department of Neurology, Medical University of Vienna, Vienna, Austria
| | - Cristian Falup-Pecurariu
- Faculty of Medicine, Transilvania University of Braşov, Brașov, Romania
- Department of Neurology, County Clinic Hospital, Braşov, Romania
| | - Kallol Ray Chaudhuri
- Department of Neuroscience, Institute of Psychiatry, Psychology, and Neuroscience (IoPpn), King's College London, London, UK
- Parkinson's Foundation Centre of Excellence, King's College Hospital NHS Foundation Trust, London, UK
| |
Collapse
|
12
|
Ray Chaudhuri K, Leta V, Bannister K, Brooks DJ, Svenningsson P. The noradrenergic subtype of Parkinson disease: from animal models to clinical practice. Nat Rev Neurol 2023:10.1038/s41582-023-00802-5. [PMID: 37142796 DOI: 10.1038/s41582-023-00802-5] [Citation(s) in RCA: 12] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/16/2023] [Indexed: 05/06/2023]
Abstract
Many advances in understanding the pathophysiology of Parkinson disease (PD) have been based on research addressing its motor symptoms and phenotypes. Various data-driven clinical phenotyping studies supported by neuropathological and in vivo neuroimaging data suggest the existence of distinct non-motor endophenotypes of PD even at diagnosis, a concept further strengthened by the predominantly non-motor spectrum of symptoms in prodromal PD. Preclinical and clinical studies support early dysfunction of noradrenergic transmission in both the CNS and peripheral nervous system circuits in patients with PD that results in a specific cluster of non-motor symptoms, including rapid eye movement sleep behaviour disorder, pain, anxiety and dysautonomia (particularly orthostatic hypotension and urinary dysfunction). Cluster analyses of large independent cohorts of patients with PD and phenotype-focused studies have confirmed the existence of a noradrenergic subtype of PD, which had been previously postulated but not fully characterized. This Review discusses the translational work that unravelled the clinical and neuropathological processes underpinning the noradrenergic PD subtype. Although some overlap with other PD subtypes is inevitable as the disease progresses, recognition of noradrenergic PD as a distinct early disease subtype represents an important advance towards the delivery of personalized medicine for patients with PD.
Collapse
Affiliation(s)
- K Ray Chaudhuri
- Department of Basic and Clinical Neurosciences, The Maurice Wohl Clinical Neuroscience Institute, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK.
- Parkinson's Foundation Centre of Excellence, King's College Hospital, London, UK.
| | - Valentina Leta
- Department of Basic and Clinical Neurosciences, The Maurice Wohl Clinical Neuroscience Institute, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
- Parkinson's Foundation Centre of Excellence, King's College Hospital, London, UK
| | - Kirsty Bannister
- Central Modulation of Pain Lab, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
| | - David J Brooks
- Institute of Translational and Clinical Research, University of Newcastle upon Tyne, Newcastle, UK
- Department of Nuclear Medicine, Aarhus University, Aarhus, Denmark
| | - Per Svenningsson
- Department of Basic and Clinical Neurosciences, The Maurice Wohl Clinical Neuroscience Institute, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
- Department of Clinical Neuroscience, Karolinska Institute, Stockholm, Sweden
| |
Collapse
|
13
|
Sukumaran L, Kunisaki KM, Bakewell N, Winston A, Mallon PW, Doyle N, Anderson J, Boffito M, Haddow L, Post FA, Vera JH, Sachikonye M, Sabin CA. Association between inflammatory biomarker profiles and cardiovascular risk in individuals with and without HIV. AIDS 2023; 37:595-603. [PMID: 36541572 PMCID: PMC9994838 DOI: 10.1097/qad.0000000000003462] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Revised: 11/24/2022] [Accepted: 11/26/2022] [Indexed: 12/24/2022]
Abstract
BACKGROUND People with HIV have an increased risk for cardiovascular morbidity and mortality. Inflammation and immune activation may contribute to this excess risk. METHODS We assessed thirty-one biomarkers in a subset of POPPY participants and identified three distinct inflammatory profiles: 'gut/immune activation', 'neurovascular', and 'reference' (relatively low levels of inflammation). Ten-year cardiovascular disease (CVD) risk predictions were calculated using the QRISK, Framingham Risk Score (FRS) and the Data Collection on Adverse effects of anti-HIV Drugs (D:A:D) algorithms. The distributions of CVD risk scores across the different inflammatory profiles, stratified by HIV status, were compared using median quantile regression. RESULTS Of the 312 participants included [70% living with HIV, median (interquartile range; IQR) age 55 (51-60) years; 82% male; 91% white], 36, 130, and 146 were in the 'gut/immune activation', 'neurovascular', and 'reference' cluster, respectively. The median (IQR) QRISK scores were 9.3% (4.5-14.5) and 10.2% (5.5-16.9) for people with and without HV, respectively, with similar scores obtained with the FRS and D:A:D. We observed statistically significant differences between the distributions of scores in the three clusters among people with HV. In particular, median QRISK [5.8% (1.0-10.7) and 3.1% (0.3-5.8)] scores were higher, respectively, for those in the 'gut/immune activation' and 'neurovascular' clusters compared to those in the reference cluster. CONCLUSIONS People with HIV with increased gut/immune activation have a higher CVD risk compared to those with relatively low inflammation. Our findings highlight that clinically important inflammatory subgroups could be useful to differentiate risk and maximise prediction of CVD among people with HIV.
Collapse
Affiliation(s)
- Luxsena Sukumaran
- Institute for Global Health, University College London
- National Institute for Health Research (NIHR) Health Protection Research Unit (HPRU) in Blood-borne and Sexually Transmitted Infections at University College London, UK
| | - Ken M. Kunisaki
- Minneapolis Veterans Affairs Healthcare System, University of Minnesota, Minneapolis, Minnesota, USA
| | | | - Alan Winston
- Department of Infectious Disease, Imperial College London, London, UK
| | | | - Nicki Doyle
- Department of Infectious Disease, Imperial College London, London, UK
| | | | - Marta Boffito
- Chelsea and Westminster Healthcare NHS Foundation Trust
| | - Lewis Haddow
- Institute for Global Health, University College London
- Kingston Hospital NHS Foundation Trust
| | - Frank A. Post
- King's College Hospital NHS Foundation Trust, London
| | | | | | - Caroline A. Sabin
- Institute for Global Health, University College London
- National Institute for Health Research (NIHR) Health Protection Research Unit (HPRU) in Blood-borne and Sexually Transmitted Infections at University College London, UK
| |
Collapse
|
14
|
Beyond shallow feelings of complex affect: Non-motor correlates of subjective emotional experience in Parkinson's disease. PLoS One 2023; 18:e0281959. [PMID: 36827296 PMCID: PMC9955984 DOI: 10.1371/journal.pone.0281959] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Accepted: 02/04/2023] [Indexed: 02/25/2023] Open
Abstract
Affective disorders in Parkinson's disease (PD) concern several components of emotion. However, research on subjective feeling in PD is scarce and has produced overall varying results. Therefore, in this study, we aimed to evaluate the subjective emotional experience and its relationship with autonomic symptoms and other non-motor features in PD patients. We used a battery of film excerpts to elicit Amusement, Anger, Disgust, Fear, Sadness, Tenderness, and Neutral State, in 28 PD patients and 17 healthy controls. Self-report scores of emotion category, intensity, and valence were analyzed. In the PD group, we explored the association between emotional self-reported scores and clinical scales assessing autonomic dysregulation, depression, REM sleep behavior disorder, and cognitive impairment. Patient clustering was assessed by considering relevant associations. Tenderness occurrence and intensity of Tenderness and Amusement were reduced in the PD patients. Tenderness occurrence was mainly associated with the overall cognitive status and the prevalence of gastrointestinal symptoms. In contrast, the intensity and valence reported for the experience of Amusement correlated with the prevalence of urinary symptoms. We identified five patient clusters, which differed significantly in their profile of non-motor symptoms and subjective feeling. Our findings further suggest the possible existence of a PD phenotype with more significant changes in subjective emotional experience. We concluded that the subjective experience of complex emotions is impaired in PD. Non-motor feature grouping suggests the existence of disease phenotypes profiled according to specific deficits in subjective emotional experience, with potential clinical implications for the adoption of precision medicine in PD. Further research on larger sample sizes, combining subjective and physiological measures of emotion with additional clinical features, is needed to extend our findings.
Collapse
|
15
|
Olszewska DA, Lang AE. The definition of precision medicine in neurodegenerative disorders and the one disease-many diseases tension. HANDBOOK OF CLINICAL NEUROLOGY 2023; 192:3-20. [PMID: 36796946 DOI: 10.1016/b978-0-323-85538-9.00005-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/16/2023]
Abstract
Precision medicine is a patient-centered approach that aims to translate new knowledge to optimize the type and timing of interventions for the greatest benefit to individual patients. There is considerable interest in applying this approach to treatments designed to slow or halt the progression of neurodegenerative diseases. Indeed, effective disease-modifying treatment (DMT) remains the greatest unmet therapeutic need in this field. In contrast to the enormous progress in oncology, precision medicine in the field of neurodegeneration faces multiple challenges. These are related to major limitations in our understanding of many aspects of the diseases. A critical barrier to advances in this field is the question of whether the common sporadic neurodegenerative diseases (of the elderly) are single uniform disorders (particularly related to their pathogenesis) or whether they represent a collection of related but still very distinct disease states. In this chapter, we briefly touch on lessons from other fields of medicine that might be applied to the development of precision medicine for DMT in neurodegenerative diseases. We discuss why DMT trials may have failed to date, and particularly the importance of appreciating the multifaceted nature of disease heterogeneity and how this has and will impact on these efforts. We conclude with comments on how we can move from this complex disease heterogeneity to the successful application of precision medicine principles in DMT for neurodegenerative diseases.
Collapse
Affiliation(s)
- Diana A Olszewska
- Department of Neurology, Division of Movement Disorders, Edmond J. Safra Program in Parkinson's Disease and the Morton and Gloria Shulman Movement Disorders Clinic, Toronto Western Hospital, Toronto, ON, Canada
| | - Anthony E Lang
- Department of Neurology, Division of Movement Disorders, Edmond J. Safra Program in Parkinson's Disease and the Morton and Gloria Shulman Movement Disorders Clinic, Toronto Western Hospital, Toronto, ON, Canada.
| |
Collapse
|
16
|
Two-year clinical progression in focal and diffuse subtypes of Parkinson's disease. NPJ Parkinsons Dis 2023; 9:29. [PMID: 36806285 PMCID: PMC9937525 DOI: 10.1038/s41531-023-00466-4] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2022] [Accepted: 01/06/2023] [Indexed: 02/19/2023] Open
Abstract
Heterogeneity in Parkinson's disease (PD) presents a barrier to understanding disease mechanisms and developing new treatments. This challenge may be partially overcome by stratifying patients into clinically meaningful subtypes. A recent subtyping scheme classifies de novo PD patients into three subtypes: mild-motor predominant, intermediate, or diffuse-malignant, based on motor impairment, cognitive function, rapid eye movement sleep behavior disorder (RBD) symptoms, and autonomic symptoms. We aimed to validate this approach in a large longitudinal cohort of early-to-moderate PD (n = 499) by assessing the influence of subtyping on clinical characteristics at baseline and on two-year progression. Compared to mild-motor predominant patients (42%), diffuse-malignant patients (12%) showed involvement of more clinical domains, more diffuse hypokinetic-rigid motor symptoms (decreased lateralization and hand/foot focality), and faster two-year progression. These findings extend the classification of diffuse-malignant and mild-motor predominant subtypes to early-to-moderate PD and suggest that different pathophysiological mechanisms (focal versus diffuse cerebral propagation) may underlie distinct subtype classifications.
Collapse
|
17
|
Metabotyping: a tool for identifying subgroups for tailored nutrition advice. Proc Nutr Soc 2023:1-12. [PMID: 36727494 DOI: 10.1017/s0029665123000058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
Abstract
Diet-related diseases are the leading cause of death globally and strategies to tailor effective nutrition advice are required. Personalised nutrition advice is increasingly recognised as more effective than population-level advice to improve dietary intake and health outcomes. A potential tool to deliver personalised nutrition advice is metabotyping which groups individuals into homogeneous subgroups (metabotypes) using metabolic profiles. In summary, metabotyping has been successfully employed in human nutrition research to identify subgroups of individuals with differential responses to dietary challenges and interventions and diet–disease associations. The suitability of metabotyping to identify clinically relevant subgroups is corroborated by other fields such as diabetes research where metabolic profiling has been intensely used to identify subgroups of patients that display patterns of disease progression and complications. However, there is a paucity of studies examining the efficacy of the approach to improve dietary intake and health parameters. While the application of metabotypes to tailor and deliver nutrition advice is very promising, further evidence from randomised controlled trials is necessary for further development and acceptance of the approach.
Collapse
|
18
|
Chung SJ, Kim YJ, Kim YJ, Lee HS, Jeong SH, Hong JM, Sohn YH, Yun M, Jeong Y, Lee PH. Association Between White Matter Networks and the Pattern of Striatal Dopamine Depletion in Patients With Parkinson Disease. Neurology 2022; 99:e2672-e2682. [PMID: 36195451 DOI: 10.1212/wnl.0000000000201269] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2022] [Accepted: 08/03/2022] [Indexed: 11/15/2022] Open
Abstract
OBJECTIVES Individual variability in nigrostriatal dopaminergic denervation is an important factor underlying clinical heterogeneity in Parkinson disease (PD). This study aimed to explore whether the pattern of striatal dopamine depletion was associated with white matter (WM) networks in PD. METHODS A total of 240 newly diagnosed patients with PD who underwent 18F-FP-CIT PET scans and brain diffusion tensor imaging at initial assessment were enrolled in this study. We measured 18F-FP-CIT tracer uptake as an indirect marker for striatal dopamine depletion. Factor analysis-derived striatal dopamine loss patterns were estimated in each patient to calculate the composite scores of 4 striatal subregion factors (caudate, more-affected and less-affected sensorimotor striata, and anterior putamen) based on the availability of striatal dopamine transporter. The WM structural networks that were correlated with the composite scores of each striatal subregion factor were identified using a network-based statistical analysis. RESULTS A higher composite score of caudate (i.e., relatively preserved dopaminergic innervation in the caudate) was associated with a strong structural connectivity in a single subnetwork comprising the left caudate and left frontal gyri. Selective dopamine loss in the caudate was associated with strong connectivity in the structural subnetwork whose hub nodes were bilateral thalami and left insula, which were connected to the anterior cingulum. However, no subnetworks were correlated with the composite scores of other striatal subregion factors. The connectivity strength of the network with a positive correlation with the composite score of caudate affected the frontal/executive function either directly or indirectly through the mediation of dopamine depletion in the caudate. CONCLUSIONS Our findings indicate that different patterns of striatal dopamine depletion are closely associated with WM structural alterations, which may contribute to heterogeneous cognitive profiles in individuals with PD.
Collapse
Affiliation(s)
- Seok Jong Chung
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Yae Ji Kim
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Yun Joong Kim
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Hye Sun Lee
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea.
| | - Seong Ho Jeong
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Ji-Man Hong
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Young H Sohn
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Mijin Yun
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Yong Jeong
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea
| | - Phil Hyu Lee
- From the Department of Neurology (S.J.C., Yun Joong Kim, Y.H.S., P.H.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.J.C., Yun Joong Kim), Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea; Program of Brain and Cognitive Engineering (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; KI for Health Science and Technology (Yae Ji Kim, Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; Biostatistics Collaboration Unit (H.S.L.), Yonsei University College of Medicine, Seoul, South Korea; Department of Neurology (S.H.J.), Sanggye Paik Hospital, Inje University College of Medicine, Seoul, South Korea; Department of Nuclear Medicine (M.Y.), Yonsei University College of Medicine, Seoul, South Korea; Department of Bio and Brain Engineering (Y.J.), Korea Advanced Institute of Science and Technology, Daejeon, South Korea; and Severance Biomedical Science Institute (P.H.L.), Yonsei University College of Medicine, Seoul, South Korea.
| |
Collapse
|
19
|
Mostile G, Geroin C, Erro R, Luca A, Marcuzzo E, Barone P, Ceravolo R, Mazzucchi S, Pilotto A, Padovani A, Romito LM, Eleopra R, Dallocchio C, Arbasino C, Bono F, Bruno PA, Demartini B, Gambini O, Modugno N, Olivola E, Bonanni L, Albanese A, Ferrazzano G, De Micco R, Zibetti M, Calandra-Buonaura G, Petracca M, Morgante F, Esposito M, Pisani A, Manganotti P, Stocchi F, Coletti Moja M, Di Vico IA, Tesolin L, De Bertoldi F, Ercoli T, Defazio G, Zappia M, Nicoletti A, Tinazzi M. Data-driven clustering of combined Functional Motor Disorders based on the Italian registry. Front Neurol 2022; 13:987593. [PMID: 36518193 PMCID: PMC9742245 DOI: 10.3389/fneur.2022.987593] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2022] [Accepted: 10/17/2022] [Indexed: 11/29/2022] Open
Abstract
IntroductionFunctional Motor Disorders (FMDs) represent nosological entities with no clear phenotypic characterization, especially in patients with multiple (combined FMDs) motor manifestations. A data-driven approach using cluster analysis of clinical data has been proposed as an analytic method to obtain non-hierarchical unbiased classifications. The study aimed to identify clinical subtypes of combined FMDs using a data-driven approach to overcome possible limits related to “a priori” classifications and clinical overlapping.MethodsData were obtained by the Italian Registry of Functional Motor Disorders. Patients identified with multiple or “combined” FMDs by standardized clinical assessments were selected to be analyzed. Non-hierarchical cluster analysis was performed based on FMDs phenomenology. Multivariate analysis was then performed after adjustment for principal confounding variables.ResultsFrom a study population of n = 410 subjects with FMDs, we selected n = 188 subjects [women: 133 (70.7%); age: 47.9 ± 14.4 years; disease duration: 6.4 ± 7.7 years] presenting combined FMDs to be analyzed. Based on motor phenotype, two independent clusters were identified: Cluster C1 (n = 82; 43.6%) and Cluster C2 (n = 106; 56.4%). Cluster C1 was characterized by functional tremor plus parkinsonism as the main clinical phenotype. Cluster C2 mainly included subjects with functional weakness. Cluster C1 included older subjects suffering from anxiety who were more treated with botulinum toxin and antiepileptics. Cluster C2 included younger subjects referring to different associated symptoms, such as pain, headache, and visual disturbances, who were more treated with antidepressants.ConclusionUsing a data-driven approach of clinical data from the Italian registry, we differentiated clinical subtypes among combined FMDs to be validated by prospective studies.
Collapse
Affiliation(s)
- Giovanni Mostile
- Section of Neurosciences, Department “G.F. Ingrassia”, University of Catania, Catania, Italy
- Oasi Research Institute—IRCCS, Troina, Italy
| | - Christian Geroin
- Neurology Unit, Movement Disorders Division, Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy
- Christian Geroin
| | - Roberto Erro
- Center for Neurodegenerative Diseases (CEMAND), Department of Medicine, Surgery and Dentistry—Scuola Medica Salernitana, University of Salerno, Baronissi, Italy
| | - Antonina Luca
- Section of Neurosciences, Department “G.F. Ingrassia”, University of Catania, Catania, Italy
| | - Enrico Marcuzzo
- Neurology Unit, Movement Disorders Division, Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy
| | - Paolo Barone
- Center for Neurodegenerative Diseases (CEMAND), Department of Medicine, Surgery and Dentistry—Scuola Medica Salernitana, University of Salerno, Baronissi, Italy
| | - Roberto Ceravolo
- Neurology Unit, Department of Clinical and Experimental Medicine, University of Pisa, Pisa, Italy
| | - Sonia Mazzucchi
- Neurology Unit, Department of Clinical and Experimental Medicine, University of Pisa, Pisa, Italy
| | - Andrea Pilotto
- Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy
- FERB Onlus, Ospedale S. Isidoro, Bergamo, Italy
| | - Alessandro Padovani
- Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy
| | - Luigi Michele Romito
- Parkinson and Movement Disorders Unit, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy
| | - Roberto Eleopra
- Parkinson and Movement Disorders Unit, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy
| | - Carlo Dallocchio
- Department of Medical Area, Neurology Unit, ASST Pavia, Pavia, Italy
| | - Carla Arbasino
- Department of Medical Area, Neurology Unit, ASST Pavia, Pavia, Italy
| | - Francesco Bono
- Botulinum Toxin Center, Neurology Unit A.O.U. Mater Domini, Catanzaro, Italy
| | | | - Benedetta Demartini
- Aldo Ravelli Research Center for Neurotechnology and Experimental Brain Therapeutics, Department of Health Sciences, University of Milan, Milan, Italy
| | - Orsola Gambini
- Aldo Ravelli Research Center for Neurotechnology and Experimental Brain Therapeutics, Department of Health Sciences, University of Milan, Milan, Italy
| | | | | | - Laura Bonanni
- Department of Medicine and Aging Sciences, University G. d'Annunzio, Chieti, Italy
- Department of Medicine and Aging Sciences, University G. d'Annunzio, Pescara, Italy
| | | | - Gina Ferrazzano
- Department of Human Neurosciences, Università La Sapienza, Rome, Italy
| | - Rosa De Micco
- Department of Advanced Medical and Surgery Sciences, University of Campania—Luigi Vanvitelli, Naples, Italy
| | - Maurizio Zibetti
- Department of Neuroscience—Rita Levi Montalcini, University of Turin, Turin, Italy
| | - Giovanna Calandra-Buonaura
- Department of Biomedical and Neuromotor Sciences, University of Bologna, Bologna, Italy
- IRCCS, Institute of Neurological Sciences of Bologna, Bologna, Italy
| | - Martina Petracca
- Movement Disorder Unit, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy
| | - Francesca Morgante
- Neurosciences Research Centre, Molecular and Clinical Sciences Neurosciences Research Centre, Molecular and Clinical Sciences Research Institute, St George's University of London, London, United Kingdom
- Department of Experimental and Clinical Medicine, University of Messina, Messina, Italy
| | - Marcello Esposito
- Clinical Neurophysiology Unit, Cardarelli Hospital, Naples, Italy
- Department of Neurosciences, Reproductive and Odontostomatological Sciences, University of Naples—Federico II, Naples, Italy
| | - Antonio Pisani
- IRCCS Mondino Foundation, Pavia, Italy
- Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy
| | - Paolo Manganotti
- Clinical Neurology Unit, Department of Medical, Surgical and Health Services, University of Trieste, Trieste, Italy
| | - Fabrizio Stocchi
- University and Institute of Research and Medical Care San Raffaele, Rome, Italy
| | | | - Ilaria Antonella Di Vico
- Neurology Unit, Movement Disorders Division, Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy
| | | | | | - Tommaso Ercoli
- Department of Medical Sciences and Public Health, University of Cagliari, Cagliari, Italy
| | - Giovanni Defazio
- Department of Medical Sciences and Public Health, University of Cagliari, Cagliari, Italy
| | - Mario Zappia
- Section of Neurosciences, Department “G.F. Ingrassia”, University of Catania, Catania, Italy
| | - Alessandra Nicoletti
- Section of Neurosciences, Department “G.F. Ingrassia”, University of Catania, Catania, Italy
| | - Michele Tinazzi
- Neurology Unit, Movement Disorders Division, Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy
- *Correspondence: Michele Tinazzi
| |
Collapse
|
20
|
Biomarker characterization of clinical subtypes of Parkinson Disease. NPJ Parkinsons Dis 2022; 8:109. [PMID: 36038597 PMCID: PMC9424224 DOI: 10.1038/s41531-022-00375-y] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2022] [Accepted: 08/05/2022] [Indexed: 11/08/2022] Open
Abstract
AbstractThe biological underpinnings of the PD clusters remain unknown as the existing PD clusters lacks biomarker characterization. We try to identify clinical subtypes of Parkinson Disease (PD) in an Asian cohort and characterize them by comparing clinical assessments, genetic status and blood biochemical markers. A total of 206 PD patients were included from a multi-centre Asian cohort. Hierarchical clustering was performed to generate PD subtypes. Clinical and biological characterization of the subtypes were performed by comparing clinical assessments, allelic distributions of Asian related PD gene (SNCA, LRRK2, Park16, ITPKB, SV2C) and blood biochemical markers. Hierarchical clustering method identified three clusters: cluster A (severe subtype in motor, non-motor and cognitive domains), cluster B (intermediate subtype with cognitive impairment and mild non-motor symptoms) and cluster C (mild subtype and young age of onset). The three clusters had significantly different allele frequencies in two SNPs (Park16 rs6679073 A allele carriers in cluster A B C: 67%, 74%, 89%, p = 0.015; SV2C rs246814 T allele distribution: 7%, 12%, 25%, p = 0.026). Serum homocysteine (Hcy) and C-reactive protein (CRP) levels were also significantly different among three clusters (Mean levels of Hcy and CRP among cluster A B C were: 19.4 ± 4.2, 18.4 ± 5.7, 15.6 ± 5.6, adjusted p = 0.005; 2.5 ± 5.0, 1.5 ± 2.4, 0.9 ± 2.1, adjusted p < 0.0001, respectively). Of the 3 subtypes identified amongst early PD patients, the severe subtype was associated with significantly lower frequency of Park16 and SV2C alleles and higher levels of Hcy and CRP. These biomarkers may be useful to stratify PD subtypes and identify more severe subtypes.
Collapse
|
21
|
Meira B, Lhommée E, Schmitt E, Klinger H, Bichon A, Pélissier P, Anheim M, Tranchant C, Fraix V, Meoni S, Durif F, Houeto JL, Azulay JP, Moro E, Thobois S, Krack P, Castrioto A. Early Parkinson's Disease Phenotypes Tailored by Personality, Behavior, and Motor Symptoms. JOURNAL OF PARKINSON'S DISEASE 2022; 12:1665-1676. [PMID: 35527563 DOI: 10.3233/jpd-213070] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
BACKGROUND Previous studies described a parkinsonian personality characterized as rigid, introverted, and cautious; however, little is known about personality traits in de novo Parkinson's disease (PD) patients and their relationships with motor and neuropsychiatric symptoms. OBJECTIVE To investigate personality in de novo PD and explore its relationship with PD symptoms. METHODS Using Cloninger's biosocial model, we assessed personality in 193 de novo PD patients. Motor and non-motor symptoms were measured using several validated scales. Cluster analysis was conducted to investigate the interrelationship of personality traits, motor, and non-motor symptoms. RESULTS PD patients showed low novelty seeking, high harm avoidance, and normal reward dependence and persistence scores. Harm avoidance was positively correlated with the severity of depression, anxiety, and apathy (rs = [0.435, 0.676], p < 0.001) and negatively correlated with quality of life (rs = -0.492, p < 0.001). Novelty seeking, reward dependence, and persistence were negatively correlated with apathy (rs = [-0.274, -0.375], p < 0.001). Classification of patients according to personality and PD symptoms revealed 3 distinct clusters: i) neuropsychiatric phenotype (with high harm avoidance and low novelty seeking, hypodopaminergic neuropsychiatric symptoms and higher impulsivity), ii) motor phenotype (with low novelty seeking and higher motor severity), iii) benign phenotype (with low harm avoidance and high novelty seeking, reward dependence, and persistence traits clustered with lower symptoms severity and low impulsivity). CONCLUSION Personality in early PD patients allows us to recognize 3 patients' phenotypes. Identification of such subgroups may help to better understand their natural history. Their longitudinal follow-up will allow confirming whether some personality features might influence disease evolution and treatment.
Collapse
Affiliation(s)
- Bruna Meira
- Neurology Department, Centro Hospitalar Lisboa Ocidental, Lisbon, Portugal.,Movement Disorders Center, Neurology, CHU Grenoble Alpes, Grenoble, France
| | - Eugénie Lhommée
- Movement Disorders Center, Neurology, CHU Grenoble Alpes, Grenoble, France
| | - Emmanuelle Schmitt
- Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, Grenoble Institut Neurosciences, Grenoble, France
| | - Hélène Klinger
- Hospices Civils de Lyon, Hôpital Neurologique Pierre Wertheimer, Neurologie C, Centre Expert Parkinson, Lyon, France.,Univ Lyon, Université Claude Bernard Lyon 1, CNRS, Institut des Sciences Cognitives Marc Jeannerod, Bron, France
| | - Amélie Bichon
- Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, Grenoble Institut Neurosciences, Grenoble, France
| | - Pierre Pélissier
- Movement Disorders Center, Neurology, CHU Grenoble Alpes, Grenoble, France
| | - Mathieu Anheim
- Département de Neurologie, Hôpital de Hautepierre, Hôpitaux Universitaires de Strasbourg, Strasbourg, France.,Institut de Génétique et de Biologie Moléculaire et Cellulaire, (IGBMC), INSERM-U964/CNRS-UMR7104/, Université de Strasbourg, Illkirch, France.,Fédération de Médecine Translationnelle de Strasbourg (FMTS), Université de Strasbourg, Strasbourg, France
| | - Christine Tranchant
- Département de Neurologie, Hôpital de Hautepierre, Hôpitaux Universitaires de Strasbourg, Strasbourg, France.,Institut de Génétique et de Biologie Moléculaire et Cellulaire, (IGBMC), INSERM-U964/CNRS-UMR7104/, Université de Strasbourg, Illkirch, France.,Fédération de Médecine Translationnelle de Strasbourg (FMTS), Université de Strasbourg, Strasbourg, France
| | - Valérie Fraix
- Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, Grenoble Institut Neurosciences, Grenoble, France
| | - Sara Meoni
- Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, Grenoble Institut Neurosciences, Grenoble, France
| | - Franck Durif
- Université Clermont Auvergne, NPsy-Sydo, Clermont-Ferrand University Hospital, Neurology Department, Clermont-Ferrand, France
| | - Jean-Luc Houeto
- Service de Neurologie, Centre Expert Parkinson, CHU de Limoges, UMR1094 INSERM, Université de Limoges, Limoges, France
| | - Jean Philippe Azulay
- Neurology and Pathology Department of the Movement, University Hospital of Marseille, Timone Hospital, Marseille, France
| | - Elena Moro
- Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, Grenoble Institut Neurosciences, Grenoble, France
| | - Stéphane Thobois
- Hospices Civils de Lyon, Hôpital Neurologique Pierre Wertheimer, Neurologie C, Centre Expert Parkinson, Lyon, France.,Univ Lyon, Université Claude Bernard Lyon 1, CNRS, Institut des Sciences Cognitives Marc Jeannerod, Bron, France
| | - Paul Krack
- Department of Neurology, Inselspital, University Hospital Bern, Bern, Switzerland
| | - Anna Castrioto
- Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, Grenoble Institut Neurosciences, Grenoble, France
| | | |
Collapse
|
22
|
Shakya S, Prevett J, Hu X, Xiao R. Characterization of Parkinson's Disease Subtypes and Related Attributes. Front Neurol 2022; 13:810038. [PMID: 35677337 PMCID: PMC9167933 DOI: 10.3389/fneur.2022.810038] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2021] [Accepted: 05/04/2022] [Indexed: 11/13/2022] Open
Abstract
Parkinson's disease is a progressive neurodegenerative disease with complex, heterogeneous motor and non-motor symptoms. The current evidence shows that there is still a marked heterogeneity in the subtyping of Parkinson's disease using both clinical and data-driven approaches. Another challenge posed in PD subtyping is the reproducibility of previously identified PD subtypes. These issues require additional results to confirm previous findings and help reconcile discrepancies, as well as establish a standardized application of cluster analysis to facilitate comparison and reproducibility of identified PD subtypes. Our study aimed to address this gap by investigating subtypes of Parkinson's disease using comprehensive clinical (motor and non-motor features) data retrieved from 408 de novo Parkinson's disease patients with the complete clinical data in the Parkinson's Progressive Marker Initiative database. A standardized k-means cluster analysis approach was developed by taking into consideration of common practice and recommendations from previous studies. All data analysis codes were made available online to promote data comparison and validation of reproducibility across research groups. We identified two distinct PD subtypes, termed the severe motor-non-motor subtype (SMNS) and the mild motor- non-motor subtype (MMNS). SMNS experienced symptom onset at an older age and manifested more intense motor and non-motor symptoms than MMNS, who experienced symptom onset at a younger age and manifested milder forms of Parkinson's symptoms. The SPECT imaging makers supported clinical findings such that the severe motor-non-motor subtype showed lower binding values than the mild motor- non-motor subtype, indicating more significant neural damage at the nigral pathway. In addition, SMNS and MMNS show distinct motor (ANCOVA test: F = 47.35, p< 0.001) and cognitive functioning (F = 33.93, p< 0.001) progression trends. Such contrast between SMNS and MMNS in both motor and cognitive functioning can be consistently observed up to 3 years following the baseline visit, demonstrating the potential prognostic value of identified PD subtypes.
Collapse
Affiliation(s)
| | - Julia Prevett
- School of Nursing, Duke University, Durham, NC, United States
| | - Xiao Hu
- School of Nursing, Emory University, Atlanta, GA, United States
- Department of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA, United States
- Department of Computer Science, College of Arts and Sciences, Emory University, Atlanta, GA, United States
| | - Ran Xiao
- School of Nursing, Duke University, Durham, NC, United States
- *Correspondence: Ran Xiao
| |
Collapse
|
23
|
Pelzer EA, Stürmer S, Feis DL, Melzer C, Schwartz F, Scharge M, Eggers C, Tittgemeyer M, Timmermann L. Clustering of Parkinson subtypes reveals strong influence of DRD2 polymorphism and gender. Sci Rep 2022; 12:6038. [PMID: 35411010 PMCID: PMC9001640 DOI: 10.1038/s41598-022-09657-0] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2021] [Accepted: 03/07/2022] [Indexed: 12/11/2022] Open
Abstract
AbstractMost classification approaches for idiopathic Parkinson’s disease subtypes primarily focus on motor and non-motor symptoms. Besides these characteristics, other features, including gender or genetic polymorphism of dopamine receptors are potential factors influencing the disease’s phenotype. By utilizing a kmeans-clustering algorithm we were able to identify three subgroups mainly characterized by gender, DRD2 Taq1A (rs1800497) polymorphism—associated with changes in dopamine signaling in the brain—and disease progression. A subsequent regression analysis of these subgroups further suggests an influence of their characteristics on the daily levodopa dosage, an indicator for medication response. These findings could promote further enhancements in individualized therapies for idiopathic Parkinson’s disease.
Collapse
|
24
|
The emerging postural instability phenotype in idiopathic Parkinson disease. NPJ Parkinsons Dis 2022; 8:28. [PMID: 35304493 PMCID: PMC8933561 DOI: 10.1038/s41531-022-00287-x] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2020] [Accepted: 02/01/2022] [Indexed: 01/15/2023] Open
Abstract
Identification of individuals at high risk for rapid progression of motor and cognitive signs in Parkinson disease (PD) is clinically significant. Postural instability and gait dysfunction (PIGD) are associated with greater motor and cognitive deterioration. We examined the relationship between baseline clinical factors and the development of postural instability using 5-year longitudinal de-novo idiopathic data (n = 301) from the Parkinson’s Progressive Markers Initiative (PPMI). Logistic regression analysis revealed baseline features associated with future postural instability, and we designated this cohort the emerging postural instability (ePI) phenotype. We evaluated the resulting ePI phenotype rating scale validity in two held-out populations which showed a significantly higher risk of postural instability. Emerging PI phenotype was identified before onset of postural instability in 289 of 301 paired comparisons, with a median progression time of 972 days. Baseline cognitive performance was similar but declined more rapidly in ePI phenotype. We provide an ePI phenotype rating scale (ePIRS) for evaluation of individual risk at baseline for progression to postural instability.
Collapse
|
25
|
Salmanpour MR, Shamsaei M, Hajianfar G, Soltanian-Zadeh H, Rahmim A. Longitudinal clustering analysis and prediction of Parkinson's disease progression using radiomics and hybrid machine learning. Quant Imaging Med Surg 2022; 12:906-919. [PMID: 35111593 DOI: 10.21037/qims-21-425] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2021] [Accepted: 08/13/2021] [Indexed: 11/06/2022]
Abstract
BACKGROUND We employed machine learning approaches to (I) determine distinct progression trajectories in Parkinson's disease (PD) (unsupervised clustering task), and (II) predict progression trajectories (supervised prediction task), from early (years 0 and 1) data, making use of clinical and imaging features. METHODS We studied PD-subjects derived from longitudinal datasets (years 0, 1, 2 & 4; Parkinson's Progressive Marker Initiative). We extracted and analyzed 981 features, including motor, non-motor, and radiomics features extracted for each region-of-interest (ROIs: left/right caudate and putamen) using our standardized standardized environment for radiomics analysis (SERA) radiomics software. Segmentation of ROIs on dopamine transposer - single photon emission computed tomography (DAT SPECT) images were performed via magnetic resonance images (MRI). After performing cross-sectional clustering on 885 subjects (original dataset) to identify disease subtypes, we identified optimal longitudinal trajectories using hybrid machine learning systems (HMLS), including principal component analysis (PCA) + K-Means algorithms (KMA) followed by Bayesian information criterion (BIC), Calinski-Harabatz criterion (CHC), and elbow criterion (EC). Subsequently, prediction of the identified trajectories from early year data was performed using multiple HMLSs including 16 Dimension Reduction Algorithms (DRA) and 10 classification algorithms. RESULTS We identified 3 distinct progression trajectories. Hotelling's t squared test (HTST) showed that the identified trajectories were distinct. The trajectories included those with (I, II) disease escalation (2 trajectories, 27% and 38% of patients) and (III) stable disease (1 trajectory, 35% of patients). For trajectory prediction from early year data, HMLSs including the stochastic neighbor embedding algorithm (SNEA, as a DRA) as well as locally linear embedding algorithm (LLEA, as a DRA), linked with the new probabilistic neural network classifier (NPNNC, as a classifier), resulted in accuracies of 78.4% and 79.2% respectively, while other HMLSs such as SNEA + Lib_SVM (library for support vector machines) and t_SNE (t-distributed stochastic neighbor embedding) + NPNNC resulted in 76.5% and 76.1% respectively. CONCLUSIONS This study moves beyond cross-sectional PD subtyping to clustering of longitudinal disease trajectories. We conclude that combining medical information with SPECT-based radiomics features, and optimal utilization of HMLSs, can identify distinct disease trajectories in PD patients, and enable effective prediction of disease trajectories from early year data.
Collapse
Affiliation(s)
- Mohammad R Salmanpour
- Department of Energy Engineering and Physics, Amirkabir University of Technology, Tehran, Iran.,Department of Physics & Astronomy, University of British Columbia, Vancouver BC, Canada
| | - Mojtaba Shamsaei
- Department of Energy Engineering and Physics, Amirkabir University of Technology, Tehran, Iran
| | - Ghasem Hajianfar
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Science, Tehran, Iran
| | - Hamid Soltanian-Zadeh
- CIPCE, School of Electrical & Computer Engineering, University of Tehran, Tehran, Iran.,Departments of Radiology and Research Administration, Henry Ford Health System, Detroit, USA
| | - Arman Rahmim
- Department of Physics & Astronomy, University of British Columbia, Vancouver BC, Canada.,Department of Radiology, University of British Columbia, Vancouver BC, Canada
| |
Collapse
|
26
|
Parkinson's Disease Subtyping Using Clinical Features and Biomarkers: Literature Review and Preliminary Study of Subtype Clustering. Diagnostics (Basel) 2022; 12:diagnostics12010112. [PMID: 35054279 PMCID: PMC8774435 DOI: 10.3390/diagnostics12010112] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2021] [Revised: 12/31/2021] [Accepted: 01/03/2022] [Indexed: 12/29/2022] Open
Abstract
The second most common progressive neurodegenerative disorder, Parkinson’s disease (PD), is characterized by a broad spectrum of symptoms that are associated with its progression. Several studies have attempted to classify PD according to its clinical manifestations and establish objective biomarkers for early diagnosis and for predicting the prognosis of the disease. Recent comprehensive research on the classification of PD using clinical phenotypes has included factors such as dominance, severity, and prognosis of motor and non-motor symptoms and biomarkers. Additionally, neuroimaging studies have attempted to reveal the pathological substrate for motor symptoms. Genetic and transcriptomic studies have contributed to our understanding of the underlying molecular pathogenic mechanisms and provided a basis for classifying PD. Moreover, an understanding of the heterogeneity of clinical manifestations in PD is required for a personalized medicine approach. Herein, we discuss the possible subtypes of PD based on clinical features, neuroimaging, and biomarkers for developing personalized medicine for PD. In addition, we conduct a preliminary clustering using gait features for subtyping PD. We believe that subtyping may facilitate the development of therapeutic strategies for PD.
Collapse
|
27
|
Uszko-Lencer NHMK, Janssen DJA, Gaffron S, Vanfleteren LEGW, Janssen E, Werter C, Franssen FME, Wouters EFM, Rechberger S, Brunner La Rocca HP, Spruit MA. Clustering based on comorbidities in patients with chronic heart failure: an illustration of clinical diversity. ESC Heart Fail 2021; 9:614-626. [PMID: 34796690 PMCID: PMC8787997 DOI: 10.1002/ehf2.13704] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2021] [Revised: 10/01/2021] [Accepted: 10/29/2021] [Indexed: 11/30/2022] Open
Abstract
Aims It is increasingly recognized that the presence of comorbidities substantially contributes to the disease burden in patients with heart failure (HF). Several reports have suggested that clustering of comorbidities can lead to improved characterization of the disease phenotypes, which may influence management of the individual patient. Therefore, we aimed to cluster patients with HF based on medical comorbidities and their treatment and, subsequently, compare the clinical characteristics between these clusters. Methods and results A total of 603 patients with HF entering an outpatient HF rehabilitation programme were included [median age 65 years (interquartile range 56–71), 57% ischaemic origin of cardiomyopathy, and left ventricular ejection fraction 35% (26–45)]. Exercise performance, daily life activities, disease‐specific health status, coping styles, and personality traits were assessed. In addition, the presence of 12 clinically relevant comorbidities was recorded, based on targeted diagnostics combined with applicable pharmacotherapies. Self‐organizing maps (SOMs; www.viscovery.net) were used to visualize clusters, generated by using a hybrid algorithm that applies the classical hierarchical cluster method of Ward on top of the SOM topology. Five clusters were identified: (1) a least comorbidities cluster; (2) a cachectic/implosive cluster; (3) a metabolic diabetes cluster; (4) a metabolic renal cluster; and (5) a psychologic cluster. Exercise performance, daily life activities, disease‐specific health status, coping styles, personality traits, and number of comorbidities were significantly different between these clusters. Conclusions Distinct combinations of comorbidities could be identified in patients with HF. Therapy may be tailored based on these clusters as next step towards precision medicine. The effect of such an approach needs to be prospectively tested.
Collapse
Affiliation(s)
- Nicole H M K Uszko-Lencer
- Department of Cardiology, Maastricht University Medical Center+ (MUMC+), Maastricht, The Netherlands.,Department of Research & Development, CIRO, Horn, The Netherlands
| | - Daisy J A Janssen
- Department of Research & Development, CIRO, Horn, The Netherlands.,Department of Health Services Research, Care and Public Health Research Institute, Faculty of Health, Medicine and Life Sciences, Maastricht University, Maastricht, The Netherlands
| | | | - Lowie E G W Vanfleteren
- Department of Internal Medicine and Clinical Nutrition, Institute of Medicine, Sahlgrenska Academy, Gothenburg University, Gothenburg, Sweden.,COPD Center, Department of Respiratory Medicine and Allergology, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Eefje Janssen
- Department of Research & Development, CIRO, Horn, The Netherlands
| | - Christ Werter
- Department of Cardiology, Laurentius Hospital, Roermond, The Netherlands
| | - Frits M E Franssen
- Department of Research & Development, CIRO, Horn, The Netherlands.,Department of Respiratory Medicine, Maastricht University Medical Center+ (MUMC+), Maastricht, The Netherlands
| | - Emiel F M Wouters
- Department of Research & Development, CIRO, Horn, The Netherlands.,Department of Respiratory Medicine, Maastricht University Medical Center+ (MUMC+), Maastricht, The Netherlands
| | | | | | - Martijn A Spruit
- Department of Research & Development, CIRO, Horn, The Netherlands.,Department of Respiratory Medicine, Maastricht University Medical Center+ (MUMC+), Maastricht, The Netherlands.,Faculty of Health, Medicine and Life Sciences, NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht, The Netherlands
| |
Collapse
|
28
|
Hendricks RM, Khasawneh MT. A Systematic Review of Parkinson's Disease Cluster Analysis Research. Aging Dis 2021; 12:1567-1586. [PMID: 34631208 PMCID: PMC8460306 DOI: 10.14336/ad.2021.0519] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2021] [Accepted: 05/18/2021] [Indexed: 12/17/2022] Open
Abstract
One way to understand the Parkinson’s disease (PD) population is to investigate the similarities and differences among patients through cluster analysis, which may lead to defined, patient subgroups for diagnosis, progression tracking and treatment planning. This paper provides a systematic review of PD patient clustering research, evaluating the variables included in clustering, the cluster methods applied, the resulting patient subgroups, and evaluation metrics. A search was conducted from 1999 to 2021 on the PubMed database, using various search terms including: Parkinson’s disease, cluster, and analysis. The majority of studies included a variety of clinical scale scores for clustering, of which many provide a numerical, but ordinal, categorical value. Even though the scale scores are ordinal, these were treated as numerical values with numerical and continuous values being the focus of the clustering, with limited attention to categorical variables, such as gender and family history, which may also provide useful insights into disease diagnosis, progression, and treatment. The results pointed to two to five patient clusters, with similarities among the age of onset and disease duration. The studies lacked the use of existing clustering evaluation metrics which points to a need for a thorough, analysis framework, and consensus on the appropriate variables to include in cluster analysis. Accurate cluster analysis may assist with determining if PD patients’ symptoms can be treated based on a subgroup of features, if personalized care is required, or if a mix of individualized and group-based care is the best approach.
Collapse
Affiliation(s)
- Renee M Hendricks
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Mohammad T Khasawneh
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| |
Collapse
|
29
|
Myers PS, Jackson JJ, Clover AK, Lessov‐Schlaggar CN, Foster ER, Maiti B, Perlmutter JS, Campbell MC. Distinct progression patterns across Parkinson disease clinical subtypes. Ann Clin Transl Neurol 2021; 8:1695-1708. [PMID: 34310084 PMCID: PMC8351397 DOI: 10.1002/acn3.51436] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2021] [Revised: 06/18/2021] [Accepted: 07/12/2021] [Indexed: 11/23/2022] Open
Abstract
OBJECTIVE To examine specific symptom progression patterns and possible disease staging in Parkinson disease clinical subtypes. METHODS We recently identified Parkinson disease clinical subtypes based on comprehensive behavioral evaluations, "Motor Only," "Psychiatric & Motor," and "Cognitive & Motor," which differed in dementia and mortality rates. Parkinson disease participants ("Motor Only": n = 61, "Psychiatric & Motor": n = 17, "Cognitive & Motor": n = 70) and controls (n = 55) completed longitudinal, comprehensive motor, cognitive, and psychiatric evaluations (average follow-up = 4.6 years). Hierarchical linear modeling examined group differences in symptom progression. A three-way interaction among time, group, and symptom duration (or baseline age, separately) was incorporated to examine disease stages. RESULTS All three subtypes increased in motor dysfunction compared to controls. The "Motor Only" subtype did not show significant cognitive or psychiatric changes compared to the other two subtypes. The "Cognitive & Motor" subtype's cognitive dysfunction at baseline further declined compared to the other two subtypes, while also increasing in psychiatric symptoms. The "Psychiatric & Motor" subtype's elevated psychiatric symptoms at baseline remained steady or improved over time, with mild, steady decline in cognition. The pattern of behavioral changes and analyses for disease staging yielded no evidence for sequential disease stages. INTERPRETATION Parkinson disease clinical subtypes progress in clear, temporally distinct patterns from one another, particularly in cognitive and psychiatric features. This highlights the importance of comprehensive clinical examinations as the order of symptom presentation impacts clinical prognosis.
Collapse
Affiliation(s)
- Peter S. Myers
- Department of NeurologyWashington University School of MedicineSt. LouisMissouriUSA
| | - Joshua J. Jackson
- Department of Psychological and Brain SciencesWashington University in St. LouisSt. LouisMissouriUSA
| | - Amber K. Clover
- Department of NeurologyWashington University School of MedicineSt. LouisMissouriUSA
| | | | - Erin R. Foster
- Department of NeurologyWashington University School of MedicineSt. LouisMissouriUSA
- Department of PsychiatryWashington University School of MedicineSt. LouisMissouriUSA
- Program in Occupational TherapyWashington University School of MedicineSt. LouisMissouriUSA
| | - Baijayanta Maiti
- Department of NeurologyWashington University School of MedicineSt. LouisMissouriUSA
| | - Joel S. Perlmutter
- Department of NeurologyWashington University School of MedicineSt. LouisMissouriUSA
- Program in Occupational TherapyWashington University School of MedicineSt. LouisMissouriUSA
- Department of RadiologyWashington University School of MedicineSt. LouisMissouriUSA
- Department of NeuroscienceWashington University School of MedicineSt. LouisMissouriUSA
- Program in Physical TherapyWashington University School of MedicineSt. LouisMissouriUSA
| | - Meghan C. Campbell
- Department of NeurologyWashington University School of MedicineSt. LouisMissouriUSA
- Department of RadiologyWashington University School of MedicineSt. LouisMissouriUSA
| |
Collapse
|
30
|
Short-term deceleration capacity of heart rate: a sensitive marker of cardiac autonomic dysfunction in idiopathic Parkinson's disease. Clin Auton Res 2021; 31:729-736. [PMID: 34251546 DOI: 10.1007/s10286-021-00815-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2021] [Accepted: 06/22/2021] [Indexed: 10/20/2022]
Abstract
PURPOSE Cardiac autonomic dysfunction in idiopathic Parkinson's disease (PD) manifests as reduced heart rate variability (HRV). In the present study, we explored the deceleration capacity of heart rate (DC) in patients with idiopathic PD, an advanced HRV marker that has proven clinical utility. METHODS Standard and advanced HRV measures derived from 7-min electrocardiograms in 20 idiopathic PD patients and 27 healthy controls were analyzed. HRV measures were compared using regression analysis, controlling for age, sex, and mean heart rate. RESULTS Significantly reduced HRV was found only in the subcohort of PD patients older than 60 years. Low- frequency power and global HRV measures were lower in patients than in controls, but standard beat-to-beat HRV markers (i.e., rMSSD and high-frequency power) were not significantly different between groups. DC was significantly reduced in the subcohort of PD patients older than 60 years compared to controls. CONCLUSIONS Deceleration-related oscillations of HRV were significantly reduced in the older PD patients compared to healthy controls, suggesting that short-term DC may be a sensitive marker of cardiac autonomic dysfunction in PD. DC may be complementary to traditional markers of short-term HRV for the evaluation of autonomic modulation in PD. Further study to examine the association between DC and cardiac adverse events in PD is needed to clarify the clinical relevance of DC in this population.
Collapse
|
31
|
Salmanpour MR, Shamsaei M, Rahmim A. Feature selection and machine learning methods for optimal identification and prediction of subtypes in Parkinson's disease. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 206:106131. [PMID: 34015757 DOI: 10.1016/j.cmpb.2021.106131] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/28/2020] [Accepted: 04/21/2021] [Indexed: 06/12/2023]
Abstract
OBJECTIVES The present work focuses on assessment of Parkinson's disease (PD), including both PD subtype identification (unsupervised task) and prediction (supervised task). We specifically investigate optimal feature selection and machine learning algorithms for these tasks. METHODS We selected 885 PD subjects as derived from longitudinal datasets (years 0-4; Parkinson's Progressive Marker Initiative), and investigated 981 features including motor, non-motor, and imaging features (SPECT-based radiomics features extracted using our standardized SERA software). Two different hybrid machine learning systems (HMLS) were constructed and applied to the data in order to select optimal combinations in both tasks: (i) identification of subtypes in PD (unsupervised-clustering), and (ii) prediction of these subtypes in year 4 (supervised-classification). From the original data based on years 0 (baseline) and 1, we created new datasets as inputs to the prediction task: (i,ii) CSD0 and CSD01: cross-sectional datasets from year 0 only and both years 0 & 1, respectively; (iii) TD01: timeless dataset from both years 0 & 1. In addition, PD subtype in year 4 was considered as outcome. Finally, high score features were derived via ensemble voting based on their prioritizations from feature selector algorithms (FSAs). RESULTS In clustering task, the most optimal combinations (out of 981) were selected by individual FSAs to enable high correlation compared to using all features (arriving at 547). In prediction task, we were able to select optimal combinations, resulting in an accuracy >90% only for timeless dataset (TD01); there, we were able to select the most optimal combination using 77 features, directly selected by FSAs. In both tasks, however, using combination of only high score features from ensemble voting did not enable acceptable performances, showing optimal feature selection via individual FSAs to be more effective. CONCLUSION Combining non-imaging information with SPECT-based radiomics features, and optimal utilization of HMLSs, can enable robust identification of subtypes as well as appropriate prediction of these subtypes in PD patients. Moreover, use of timeless dataset, beyond cross-sectional datasets, enabled predictive accuracies over 90%. Overall, we showed that radiomics features extracted from SPECT images are important in clustering as well as prediction of PD subtypes.
Collapse
Affiliation(s)
- Mohammad R Salmanpour
- Department of Energy Engineering and Physics, Amirkabir University of Technology, Tehran, Iran; Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada
| | - Mojtaba Shamsaei
- Department of Energy Engineering and Physics, Amirkabir University of Technology, Tehran, Iran
| | - Arman Rahmim
- Department of Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada; Department of Radiology, University of British Columbia, Vancouver, BC, Canada.
| |
Collapse
|
32
|
Ferreira-Santos D, Rodrigues PP. Enhancing Obstructive Sleep Apnea Diagnosis With Screening Through Disease Phenotypes: Algorithm Development and Validation. JMIR Med Inform 2021; 9:e25124. [PMID: 34156340 PMCID: PMC8277326 DOI: 10.2196/25124] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2020] [Revised: 01/22/2021] [Accepted: 03/16/2021] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND The American Academy of Sleep Medicine guidelines suggest that clinical prediction algorithms can be used in patients with obstructive sleep apnea (OSA) without replacing polysomnography, which is the gold standard. OBJECTIVE This study aims to develop a clinical decision support system for OSA diagnosis according to its standard definition (apnea-hypopnea index plus symptoms), identifying individuals with high pretest probability based on risk and diagnostic factors. METHODS A total of 47 predictive variables were extracted from a cohort of patients who underwent polysomnography. A total of 14 variables that were univariately significant were then used to compute the distance between patients with OSA, defining a hierarchical clustering structure from which patient phenotypes were derived and described. Affinity from individuals at risk of OSA phenotypes was later computed, and cluster membership was used as an additional predictor in a Bayesian network classifier (model B). RESULTS A total of 318 patients at risk were included, of whom 207 (65.1%) individuals were diagnosed with OSA (111, 53.6% with mild; 50, 24.2% with moderate; and 46, 22.2% with severe). On the basis of predictive variables, 3 phenotypes were defined (74/207, 35.7% low; 104/207, 50.2% medium; and 29/207, 14.1% high), with an increasing prevalence of symptoms and comorbidities, the latter describing older and obese patients, and a substantial increase in some comorbidities, suggesting their beneficial use as combined predictors (median apnea-hypopnea indices of 10, 14, and 31, respectively). Cross-validation results demonstrated that the inclusion of OSA phenotypes as an adjusting predictor in a Bayesian classifier improved screening specificity (26%, 95% CI 24-29, to 38%, 95% CI 35-40) while maintaining a high sensitivity (93%, 95% CI 91-95), with model B doubling the diagnostic model effectiveness (diagnostic odds ratio of 8.14). CONCLUSIONS Defined OSA phenotypes are a sensitive tool that enhances our understanding of the disease and allows the derivation of a predictive algorithm that can clearly outperform symptom-based guideline recommendations as a rule-out approach for screening.
Collapse
Affiliation(s)
- Daniela Ferreira-Santos
- MEDCIDS-FMUP - Community Medicine, Information and Decision Sciences, Faculty of Medicine of the University of Porto, Porto, Portugal.,CINTESIS - Center for Health Technology and Services Research, Porto, Portugal
| | - Pedro Pereira Rodrigues
- MEDCIDS-FMUP - Community Medicine, Information and Decision Sciences, Faculty of Medicine of the University of Porto, Porto, Portugal.,CINTESIS - Center for Health Technology and Services Research, Porto, Portugal
| |
Collapse
|
33
|
Salles PA, Mata IF, Fernandez HH. Should we start integrating genetic data in decision-making on device-aided therapies in Parkinson disease? A point of view. Parkinsonism Relat Disord 2021; 88:51-57. [PMID: 34119931 DOI: 10.1016/j.parkreldis.2021.05.013] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/16/2020] [Revised: 04/26/2021] [Accepted: 05/12/2021] [Indexed: 12/14/2022]
Abstract
Parkinson disease (PD) is a complex heterogeneous neurodegenerative disorder. Association studies have revealed numerous genetic risk loci and variants, and about 5-10% suffer from a monogenic form. Because the presentation and course of PD is unique to each patient, personalized symptomatic treatment should ideally be offered to treat the most disabling motor and non-motor symptoms. Indeed, clinical milestones and treatment complications that appear during disease progression are influenced by the genetic imprint. With recent advances in PD, more patients live longer to become eligible for device-aided therapies, such as apomorphine continuous subcutaneous infusion, levodopa duodenal gel infusion, and deep brain stimulation surgery, each with its own inclusion and exclusion criteria, advantages and disadvantages. Because genetic variants influence the expression of particular clinical profiles, factors for better or worse outcomes for device-aided therapies may then be proactively identified. For example, mutations in PRKN, LRRK2 and GBA express phenotypes that favor suitability for different device therapies, although with marked differences in the therapeutic window; whereas multiplications of SNCA express phenotypes that make them less desirable for device therapies.
Collapse
Affiliation(s)
- Philippe A Salles
- Center for Neurological Restoration, Cleveland Clinic Neurological Institute, OH, USA; Movement Disorders Center, CETRAM, Santiago, Chile.
| | - Ignacio F Mata
- Lerner Research Institute, Genomic Medicine, Cleveland Clinic Foundation, Cleveland, OH, USA.
| | - Hubert H Fernandez
- Center for Neurological Restoration, Cleveland Clinic Neurological Institute, OH, USA.
| |
Collapse
|
34
|
La Cognata V, Morello G, Cavallaro S. Omics Data and Their Integrative Analysis to Support Stratified Medicine in Neurodegenerative Diseases. Int J Mol Sci 2021; 22:ijms22094820. [PMID: 34062930 PMCID: PMC8125201 DOI: 10.3390/ijms22094820] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2021] [Revised: 04/23/2021] [Accepted: 04/29/2021] [Indexed: 12/17/2022] Open
Abstract
Molecular and clinical heterogeneity is increasingly recognized as a common characteristic of neurodegenerative diseases (NDs), such as Alzheimer's disease, Parkinson's disease and amyotrophic lateral sclerosis. This heterogeneity makes difficult the development of early diagnosis and effective treatment approaches, as well as the design and testing of new drugs. As such, the stratification of patients into meaningful disease subgroups, with clinical and biological relevance, may improve disease management and the development of effective treatments. To this end, omics technologies-such as genomics, transcriptomics, proteomics and metabolomics-are contributing to offer a more comprehensive view of molecular pathways underlying the development of NDs, helping to differentiate subtypes of patients based on their specific molecular signatures. In this article, we discuss how omics technologies and their integration have provided new insights into the molecular heterogeneity underlying the most prevalent NDs, aiding to define early diagnosis and progression markers as well as therapeutic targets that can translate into stratified treatment approaches, bringing us closer to the goal of personalized medicine in neurology.
Collapse
|
35
|
Rauth S, Karmakar S, Batra SK, Ponnusamy MP. Recent advances in organoid development and applications in disease modeling. Biochim Biophys Acta Rev Cancer 2021; 1875:188527. [PMID: 33640383 PMCID: PMC8068668 DOI: 10.1016/j.bbcan.2021.188527] [Citation(s) in RCA: 43] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2021] [Revised: 02/17/2021] [Accepted: 02/18/2021] [Indexed: 12/15/2022]
Abstract
An improved understanding of stem cell niches, organogenesis, and disease models has paved the way for developing a three-dimensional (3D) organoid culture system. Organoid cultures can be derived from primary tissues (single cells or tissue subunits), adult stem cells (ASCs), induced pluripotent stem cells (iPSCs), or embryonic stem cells (ESCs). As a significant technological breakthrough, 3D organoid models offer a promising approach for understanding the complexities of human diseases ranging from the mechanistic investigation of disease pathogenesis to therapy. Here, we discuss the recent applications, advantages, and limitations of organoids as in vitro models for studying metabolomics, drug development, infectious diseases, and the gut microbiome. We further discuss the use of organoids in cancer modeling using high throughput sequencing approaches.
Collapse
Affiliation(s)
- Sanchita Rauth
- Department of Biochemistry and Molecular Biology, College of Medicine, University of Nebraska Medical Center, Omaha, NE 68198-5870, USA
| | - Saswati Karmakar
- Department of Biochemistry and Molecular Biology, College of Medicine, University of Nebraska Medical Center, Omaha, NE 68198-5870, USA
| | - Surinder K Batra
- Department of Biochemistry and Molecular Biology, College of Medicine, University of Nebraska Medical Center, Omaha, NE 68198-5870, USA; Eppley Institute for Research in Cancer and Allied Diseases, Fred & Pamela Buffett Cancer Center, University of Nebraska Medical Center, Omaha, NE, USA.
| | - Moorthy P Ponnusamy
- Department of Biochemistry and Molecular Biology, College of Medicine, University of Nebraska Medical Center, Omaha, NE 68198-5870, USA; Eppley Institute for Research in Cancer and Allied Diseases, Fred & Pamela Buffett Cancer Center, University of Nebraska Medical Center, Omaha, NE, USA.
| |
Collapse
|
36
|
Imaging the Functional Neuroanatomy of Parkinson's Disease: Clinical Applications and Future Directions. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:ijerph18052356. [PMID: 33670940 PMCID: PMC7967767 DOI: 10.3390/ijerph18052356] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/24/2020] [Revised: 02/11/2021] [Accepted: 02/21/2021] [Indexed: 12/17/2022]
Abstract
The neurobiology of Parkinson’s disease and its progression has been investigated during the last few decades. Braak et al. proposed neuropathological stages of this disease based on the recognizable topographical extent of Lewy body lesions. This pathological process involves specific brain areas with an ascending course from the brain stem to the cortex. Post-mortem studies are of importance to better understand not only the progression of motor symptoms, but also the involvement of other domains, including cognition and behavior. The correlation between the neuropathological expansion of the disease and the clinical phases remains demanding. Neuroimaging, including magnetic resonance imaging (MRI), positron emission tomography (PET), and single photon emission computed tomography (SPECT), could help to bridge this existing gap by providing in vivo evidence of the extension of the disorders. In the last decade, we observed an overabundance of reports regarding the sensitivity of neuroimaging techniques. All these studies were aimed at improving the accuracy of Parkinson’s disease (PD) diagnosis and discriminating it from other causes of parkinsonism. In this review, we look at the recent literature concerning PD and address the new frontier of diagnostic accuracy in terms of identification of early stages of the disease and conventional neuroimaging techniques that, in vivo, are capable of photographing the basal ganglia network and its cerebral connections.
Collapse
|
37
|
Tremblay C, Abbasi N, Zeighami Y, Yau Y, Dadar M, Rahayel S, Dagher A. Sex effects on brain structure in de novo Parkinson's disease: a multimodal neuroimaging study. Brain 2021; 143:3052-3066. [PMID: 32980872 DOI: 10.1093/brain/awaa234] [Citation(s) in RCA: 46] [Impact Index Per Article: 15.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2019] [Revised: 05/06/2020] [Accepted: 06/10/2020] [Indexed: 02/07/2023] Open
Abstract
Parkinson's disease varies in severity and age of onset. One source of this variability is sex. Males are twice as likely as females to develop Parkinson's disease, and tend to have more severe symptoms and greater speed of progression. However, to date, there is little information in large cohorts on sex differences in the patterns of neurodegeneration. Here we used MRI and clinical information from the Parkinson Progression Markers Initiative to measure structural brain differences between sexes in Parkinson's disease after regressing out the expected effect of age and sex. We derived atrophy maps from deformation-based morphometry of T1-weighted MRI and connectivity from diffusion-weighted MRI in de novo Parkinson's disease patients (149 males: 83 females) with comparable clinical severity, and healthy control participants (78 males: 39 females). Overall, even though the two patient groups were matched for disease duration and severity, males demonstrated generally greater brain atrophy and disrupted connectivity. Males with Parkinson's disease had significantly greater tissue loss than females in 11 cortical regions including bilateral frontal and left insular lobe, right postcentral gyrus, left inferior temporal and cingulate gyrus and left thalamus, while females had greater atrophy in six cortical regions, including regions in the left frontal lobe, right parietal lobe, left insular gyrus and right occipital cortex. Local efficiency of white matter connectivity showed greater disruption in males in multiple regions such as basal ganglia, hippocampus, amygdala and thalamus. These findings support the idea that development of Parkinson's disease may involve different pathological mechanisms and yield distinct prognosis in males and females, which may have implications for research into neuroprotection, and stratification for clinical trials.
Collapse
Affiliation(s)
- Christina Tremblay
- McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada
| | - Nooshin Abbasi
- McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada
| | - Yashar Zeighami
- McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada
| | - Yvonne Yau
- McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada
| | - Mahsa Dadar
- McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada
| | - Shady Rahayel
- McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada.,Centre for Advanced Research in Sleep Medicine, Hôpital du Sacré-Cœur de Montréal, Montreal, Canada
| | - Alain Dagher
- McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada
| |
Collapse
|
38
|
A Novel Approach for Cognitive Clustering of Parkinsonisms through Affinity Propagation. ALGORITHMS 2021. [DOI: 10.3390/a14020049] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
Cluster analysis is widely applied in the neuropsychological field for exploring patterns in cognitive profiles, but traditional hierarchical and non-hierarchical approaches could be often poorly effective or even inapplicable on certain type of data. Moreover, these traditional approaches need the initial specification of the number of clusters, based on a priori knowledge not always owned. For this reason, we proposed a novel method for cognitive clustering through the affinity propagation (AP) algorithm. In particular, we applied the AP clustering on the regression residuals of the Mini Mental State Examination scores—a commonly used screening tool for cognitive impairment—of a cohort of 49 Parkinson’s disease, 48 Progressive Supranuclear Palsy and 44 healthy control participants. We found four clusters, where two clusters (68 and 30 participants) showed almost intact cognitive performance, one cluster had a moderate cognitive impairment (34 participants), and the last cluster had a more extensive cognitive deficit (8 participants). The findings showed, for the first time, an intra- and inter-diagnostic heterogeneity in the cognitive profile of Parkinsonisms patients. Our novel method of unsupervised learning could represent a reliable tool for supporting the neuropsychologists in understanding the natural structure of the cognitive performance in the neurodegenerative diseases.
Collapse
|
39
|
An Innovative Personalised Management Program for Older Adults with Parkinson's Disease: New Concepts and Future Directions. J Pers Med 2021; 11:jpm11010043. [PMID: 33466580 PMCID: PMC7828689 DOI: 10.3390/jpm11010043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2020] [Revised: 01/06/2021] [Accepted: 01/08/2021] [Indexed: 11/17/2022] Open
Abstract
Introduction: Parkinson’s disease is a heterogeneous clinical syndrome. Parkinson’s disease in older persons presents with a diverse array of clinical manifestations leading to unique care needs. This raises the need for the healthcare community to proactively address the care needs of older persons with Parkinson’s disease. Though it is tempting to categorise different phenotypes of Parkinson’s disease, a strong evidence based for the same is lacking. There is considerable literature describing the varying clinical manifestations in old age. This article aims to review the literature looking for strategies in personalising the management of an older person with Parkinson’s disease.
Collapse
|
40
|
Sheng L, Zhao P, Ma H, Radua J, Yi Z, Shi Y, Zhong J, Dai Z, Pan P. Cortical thickness in Parkinson's disease: a coordinate-based meta-analysis. Aging (Albany NY) 2021; 13:4007-4023. [PMID: 33461168 PMCID: PMC7906199 DOI: 10.18632/aging.202368] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2020] [Accepted: 11/30/2020] [Indexed: 12/24/2022]
Abstract
Parkinson's disease (PD) is a common age-related neurodegenerative disease that affects the structural architecture of the cerebral cortex. Cortical thickness (CTh) via surface-based morphometry (SBM) analysis is a popular measure to assess brain structural alterations in the gray matter in PD. However, the results of CTh analysis in PD lack consistency and have not been systematically reviewed. We conducted a comprehensive coordinate-based meta-analysis (CBMA) of 38 CTh studies (57 comparison datasets) in 1,843 patients with PD using the latest seed-based d mapping software. Compared with 1,172 healthy controls, no significantly consistent CTh alterations were found in patients with PD, suggesting CTh as an unreliable neuroimaging marker for PD. The lack of consistent CTh alterations in PD could be ascribed to the heterogeneity in clinical populations, variations in imaging methods, and underpowered small sample sizes. These results highlight the need to control for potential confounding factors to produce robust and reproducible CTh results in PD.
Collapse
Affiliation(s)
- LiQin Sheng
- Department of Neurology, Kunshan Hospital of Traditional Chinese Medicine, Kunshan, PR China
| | - PanWen Zhao
- Department of Central Laboratory, The Yancheng School of Clinical Medicine of Nanjing Medical University, Yancheng, PR China
| | - HaiRong Ma
- Department of Neurology, Kunshan Hospital of Traditional Chinese Medicine, Kunshan, PR China
| | - Joaquim Radua
- Imaging of Mood- and Anxiety-Related Disorders (IMARD) Group, Institut d’Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), CIBERSAM, Barcelona, Spain
- Early Psychosis: Interventions and Clinical-Detection (EPIC) Laboratory, Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, UK
- Centre for Psychiatric Research and Education, Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - ZhongQuan Yi
- Department of Central Laboratory, The Yancheng School of Clinical Medicine of Nanjing Medical University, Yancheng, PR China
| | - YuanYuan Shi
- Department of Central Laboratory, The Yancheng School of Clinical Medicine of Nanjing Medical University, Yancheng, PR China
| | - JianGuo Zhong
- Department of Neurology, The Yancheng School of Clinical Medicine of Nanjing Medical University, Yancheng, PR China
| | - ZhenYu Dai
- Department of Radiology, The Yancheng School of Clinical Medicine of Nanjing Medical University, Yancheng, PR China
| | - PingLei Pan
- Department of Neurology, The Yancheng School of Clinical Medicine of Nanjing Medical University, Yancheng, PR China
| |
Collapse
|
41
|
LeWitt PA, Chaudhuri KR. Unmet needs in Parkinson disease: Motor and non-motor. Parkinsonism Relat Disord 2020; 80 Suppl 1:S7-S12. [PMID: 33349582 DOI: 10.1016/j.parkreldis.2020.09.024] [Citation(s) in RCA: 60] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/20/2020] [Revised: 08/25/2020] [Accepted: 09/15/2020] [Indexed: 12/28/2022]
Abstract
Compared to other neurodegenerative diseases, Parkinson's disease (PD) is distinctive in terms of marked symptomatic variability and prognosis, as well as for the wide variety of symptomatic treatment options. Despite several decades of advances in medications and neurosurgical approaches, there remains an unmet need for symptomatic motor control. Better control of tremor, gait and balance, posture, dexterity, and communication skills are major challenges for better therapeutics of the PD movement disorder. Non-motor symptoms (NMS), which often precede motor impairments, add complexity to the burden of PD and its management. Recognized by James Parkinson MD two centuries ago, and despite 21st century neurological advances, a range of NMS plague the patient's journey, from prodromal to palliative stages. Characterizing the clinical phenotype of the entire non-motor profile of PD is challenging. Further research and understanding are needed for discovering biomarkers of certain NMS, such as dementia, fatigue, pain, sleep, and apathy. More work is needed to gather a robust evidence base for guiding treatment of troubling NMS, which exert a major impact on quality of life for people with PD and their caregivers.
Collapse
Affiliation(s)
- Peter A LeWitt
- Department of Neurology, Wayne State University School of Medicine, Detroit, MI, USA; Department of Neurology, Henry Ford Hospital, Detroit, MI, USA.
| | - K Ray Chaudhuri
- King's College London and Parkinson's Foundation Centre of Excellence, King's College Hospital, London, United Kingdom
| |
Collapse
|
42
|
Robust identification of Parkinson's disease subtypes using radiomics and hybrid machine learning. Comput Biol Med 2020; 129:104142. [PMID: 33260101 DOI: 10.1016/j.compbiomed.2020.104142] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2020] [Revised: 11/20/2020] [Accepted: 11/21/2020] [Indexed: 12/21/2022]
Abstract
OBJECTIVES It is important to subdivide Parkinson's disease (PD) into subtypes, enabling potentially earlier disease recognition and tailored treatment strategies. We aimed to identify reproducible PD subtypes robust to variations in the number of patients and features. METHODS We applied multiple feature-reduction and cluster-analysis methods to cross-sectional and timeless data, extracted from longitudinal datasets (years 0, 1, 2 & 4; Parkinson's Progressive Marker Initiative; 885 PD/163 healthy-control visits; 35 datasets with combinations of non-imaging, conventional-imaging, and radiomics features from DAT-SPECT images). Hybrid machine-learning systems were constructed invoking 16 feature-reduction algorithms, 8 clustering algorithms, and 16 classifiers (C-index clustering evaluation used on each trajectory). We subsequently performed: i) identification of optimal subtypes, ii) multiple independent tests to assess reproducibility, iii) further confirmation by a statistical approach, iv) test of reproducibility to the size of the samples. RESULTS When using no radiomics features, the clusters were not robust to variations in features, whereas, utilizing radiomics information enabled consistent generation of clusters through ensemble analysis of trajectories. We arrived at 3 distinct subtypes, confirmed using the training and testing process of k-means, as well as Hotelling's T2 test. The 3 identified PD subtypes were 1) mild; 2) intermediate; and 3) severe, especially in terms of dopaminergic deficit (imaging), with some escalating motor and non-motor manifestations. CONCLUSION Appropriate hybrid systems and independent statistical tests enable robust identification of 3 distinct PD subtypes. This was assisted by utilizing radiomics features from SPECT images (segmented using MRI). The PD subtypes provided were robust to the number of the subjects, and features.
Collapse
|
43
|
Belvisi D, Fabbrini A, De Bartolo MI, Costanzo M, Manzo N, Fabbrini G, Defazio G, Conte A, Berardelli A. The Pathophysiological Correlates of Parkinson's Disease Clinical Subtypes. Mov Disord 2020; 36:370-379. [PMID: 33037859 DOI: 10.1002/mds.28321] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2020] [Revised: 09/07/2020] [Accepted: 09/10/2020] [Indexed: 12/24/2022] Open
Abstract
BACKGROUND Possible pathophysiological mechanisms underlying Parkinson's disease (PD) clinical subtypes are unknown. The objective of this study was to identify pathophysiological substrate of PD subtypes using neurophysiological techniques. METHODS One hundred de novo PD patients participated. We collected patient demographic and clinical data, which were used to perform a hierarchical cluster analysis. The neurophysiological assessment tested primary motor cortex excitability and plasticity using transcranial magnetic stimulation. To evaluate motor performance, we performed a kinematic analysis of fast index finger abduction. To investigate sensory function and sensorimotor mechanisms, we measured the somatosensory temporal discrimination threshold at rest and during movement, respectively. RESULTS Hierarchical cluster analysis identified 2 clinical clusters. Cluster I ("mild motor-predominant") included patients who had milder motor and nonmotor symptoms severity than cluster II patients, who had a combination of severe motor and nonmotor manifestations (diffuse malignant). We observed that the diffuse malignant subtype had increased cortical excitability and reduced plasticity compared with the mild motor-predominant subtype. Kinematic analysis of motor performance demonstrated that the diffuse malignant subtype was significantly slower than the mild motor-predominant subtype. Conversely, we did not observe any significant differences in sensory function or sensorimotor integration between the two PD subtypes. CONCLUSIONS De novo PD subtypes showed different patterns of motor system dysfunction, whereas sensory function and sensorimotor integration mechanisms did not differ between subtypes. Our findings suggest that the subtyping of PD patients is not a mere clinical classification but reflects different pathophysiological mechanisms. Neurophysiological parameters may represent promising biomarkers to evaluate PD subtypes and their progression. © 2020 International Parkinson and Movement Disorder Society.
Collapse
Affiliation(s)
- Daniele Belvisi
- IRCCS Neuromed, Pozzilli, Italy.,Department of Human Neurosciences, Sapienza University of Rome, Rome, Italy
| | | | | | - Matteo Costanzo
- Department of Human Neurosciences, Sapienza University of Rome, Rome, Italy
| | | | - Giovanni Fabbrini
- IRCCS Neuromed, Pozzilli, Italy.,Department of Human Neurosciences, Sapienza University of Rome, Rome, Italy
| | - Giovanni Defazio
- Department of Medical Sciences and Public Health, University of Cagliari, Monserrato, Italy
| | - Antonella Conte
- IRCCS Neuromed, Pozzilli, Italy.,Department of Human Neurosciences, Sapienza University of Rome, Rome, Italy
| | - Alfredo Berardelli
- IRCCS Neuromed, Pozzilli, Italy.,Department of Human Neurosciences, Sapienza University of Rome, Rome, Italy
| |
Collapse
|
44
|
Characterization of idiopathic Parkinson's disease subgroups using quantitative gait analysis and corresponding subregional striatal uptake visualized using 18F-FP-CIT positron emission tomography. Gait Posture 2020; 82:167-173. [PMID: 32932077 DOI: 10.1016/j.gaitpost.2020.09.002] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/09/2020] [Revised: 08/31/2020] [Accepted: 09/01/2020] [Indexed: 02/02/2023]
Abstract
BACKGROUND Gait disturbance is one of the most common symptoms among patients with idiopathic Parkinson's disease (IPD). Nevertheless, Parkinson's disease subtype clustering according to gait characteristics has not been thoroughly investigated. RESEARCH QUESTION The aim of this study was to identify subgroups according to gait pattern among patients with IPD. METHODS This study included 88 patients with IPD who underwent 18F-fluorinated-N-3-fluoropropyl-2-β-carboxymethoxy-3-β-4-iodophenyl-nortropane positron emission tomography (18F-FP-CIT PET) and three-dimensional gait analysis (3DGA) between January 1, 2014 and December 31, 2016. We performed cluster analysis using temporal-spatial gait variables (gait speed, stride length, cadence, and step width) and divided patients into four subgroups. The kinematic and kinetic gait variables in 3DGA were compared among the four subgroups. Furthermore, we compared the uptake patterns of striatum among the four subgroups using 18F-FP-CIT PET. RESULTS The patients were clustered into subgroups based on gait hypokinesia and cadence compensation. Group 1 had decreased stride length compensating with increased cadence. Group 2 had decreased stride length without cadence compensation and wider step width. Group 3 had relatively spared stride length with decreased cadence. Group 4 had spared stride length and cadence. The uptake of posterior putamen was significantly decreased in Group 3 compared with Group 4. SIGNIFICANCE Gait hypokinesia and cadence can help to classify gait patterns in IPD patients. Our subgroups may reflect the different gait patterns in IPD patients.
Collapse
|
45
|
Implementation of Cluster-Based Management Strategies for Patients With Chronic Kidney Disease. J Nurse Pract 2020. [DOI: 10.1016/j.nurpra.2020.07.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
46
|
Chung SJ, Lee S, Yoo HS, Lee YH, Lee HS, Choi Y, Lee PH, Yun M, Sohn YH. Association of the Non-Motor Burden with Patterns of Striatal Dopamine Loss in de novo Parkinson's Disease. JOURNAL OF PARKINSONS DISEASE 2020; 10:1541-1549. [PMID: 32925098 DOI: 10.3233/jpd-202127] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
BACKGROUND Striatal dopamine deficits play a key role in the pathogenesis of Parkinson's disease (PD), and several non-motor symptoms (NMSs) have a dopaminergic component. OBJECTIVE To investigate the association between early NMS burden and the patterns of striatal dopamine depletion in patients with de novo PD. METHODS We consecutively recruited 255 patients with drug-naïve early-stage PD who underwent 18F-FP-CIT PET scans. The NMS burden of each patient was assessed using the NMS Questionnaire (NMSQuest), and patients were divided into the mild NMS burden (PDNMS-mild) (NMSQuest score <6; n = 91) and severe NMS burden groups (PDNMS-severe) (NMSQuest score >9; n = 90). We compared the striatal dopamine transporter (DAT) activity between the groups. RESULTS Patients in the PDNMS-severe group had more severe parkinsonian motor signs than those in the PDNMS-mild group, despite comparable DAT activity in the posterior putamen. DAT activity was more severely depleted in the PDNMS-severe group in the caudate and anterior putamen compared to that in the PDMNS-mild group. The inter-sub-regional ratio of the associative/limbic striatum to the sensorimotor striatum was lower in the PDNMS-severe group, although this value itself lacked fair accuracy for distinguishing between the patients with different NMS burdens. CONCLUSION This study demonstrated that PD patients with severe NMS burden exhibited severe motor deficits and relatively diffuse dopamine depletion throughout the striatum. These findings suggest that the level of NMS burden could be associated with distinct patterns of striatal dopamine depletion, which could possibly indicate the overall pathological burden in PD.
Collapse
Affiliation(s)
- Seok Jong Chung
- Department of Neurology, Yonsei University College of Medicine, Seoul, South Korea.,Department of Neurology, Yongin Severance Hospital, Yonsei University Health System, Yongin, South Korea
| | - Sangwon Lee
- Department of Nuclear Medicine, Yonsei University College of Medicine, Seoul, South Korea
| | - Han Soo Yoo
- Department of Neurology, Yonsei University College of Medicine, Seoul, South Korea
| | - Yang Hyun Lee
- Department of Neurology, Yonsei University College of Medicine, Seoul, South Korea
| | - Hye Sun Lee
- Biostatistics Collaboration Unit, Yonsei University College of Medicine, Seoul, South Korea
| | - Yonghoon Choi
- Department of Nuclear Medicine, Yonsei University College of Medicine, Seoul, South Korea
| | - Phil Hyu Lee
- Department of Neurology, Yonsei University College of Medicine, Seoul, South Korea
| | - Mijin Yun
- Department of Nuclear Medicine, Yonsei University College of Medicine, Seoul, South Korea
| | - Young H Sohn
- Department of Neurology, Yonsei University College of Medicine, Seoul, South Korea
| |
Collapse
|
47
|
Galet B, Cheval H, Ravassard P. Patient-Derived Midbrain Organoids to Explore the Molecular Basis of Parkinson's Disease. Front Neurol 2020; 11:1005. [PMID: 33013664 PMCID: PMC7500100 DOI: 10.3389/fneur.2020.01005] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2020] [Accepted: 07/30/2020] [Indexed: 12/20/2022] Open
Abstract
Induced pluripotent stem cell-derived organoids offer an unprecedented access to complex human tissues that recapitulate features of architecture, composition and function of in vivo organs. In the context of Parkinson's Disease (PD), human midbrain organoids (hMO) are of significant interest, as they generate dopaminergic neurons expressing markers of Substantia Nigra identity, which are the most vulnerable to degeneration. Combined with genome editing approaches, hMO may thus constitute a valuable tool to dissect the genetic makeup of PD by revealing the effects of risk variants on pathological mechanisms in a representative cellular environment. Furthermore, the flexibility of organoid co-culture approaches may also enable the study of neuroinflammatory and neurovascular processes, as well as interactions with other brain regions that are also affected over the course of the disease. We here review existing protocols to generate hMO, how they have been used so far to model PD, address challenges inherent to organoid cultures, and discuss applicable strategies to dissect the molecular pathophysiology of the disease. Taken together, the research suggests that this technology represents a promising alternative to 2D in vitro models, which could significantly improve our understanding of PD and help accelerate therapeutic developments.
Collapse
Affiliation(s)
- Benjamin Galet
- Molecular Pathophysiology of Parkinson's Disease Group, Paris Brain Institute (ICM), INSERM U, CNRS UMR 7225, Sorbonne University, Paris, France
| | | | | |
Collapse
|
48
|
Chung SJ, Lee JJ, Lee PH, Sohn YH. Emerging Concepts of Motor Reserve in Parkinson's Disease. J Mov Disord 2020; 13:171-184. [PMID: 32854486 PMCID: PMC7502292 DOI: 10.14802/jmd.20029] [Citation(s) in RCA: 31] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2020] [Accepted: 07/05/2020] [Indexed: 01/18/2023] Open
Abstract
The concept of cognitive reserve (CR) in Alzheimer's disease (AD) explains the differences between individuals in their susceptibility to AD-related pathologies. An enhanced CR may lead to less cognitive deficits despite severe pathological lesions. Parkinson's disease (PD) is also a common neurodegenerative disease and is mainly characterized by motor dysfunction related to striatal dopaminergic depletion. The degree of motor deficits in PD is closely correlated to the degree of dopamine depletion; however, significant individual variations still exist. Therefore, we hypothesized that the presence of motor reserve (MR) in PD explains the individual differences in motor deficits despite similar levels of striatal dopamine depletion. Since 2015, we have performed a series of studies investigating MR in de novo patients with PD using the data of initial clinical presentation and dopamine transporter PET scan. In this review, we summarized the results of these published studies. In particular, some premorbid experiences (i.e., physical activity and education) and modifiable factors (i.e., body mass index and white matter hyperintensity on brain image studies) could modulate an individual's capacity to tolerate PD pathology, which can be maintained throughout disease progression.
Collapse
Affiliation(s)
- Seok Jong Chung
- Department of Neurology, Yonsei University College of Medicine, Seoul, Korea.,Department of Neurology, Yongin Severance Hospital, Yonsei University Health System, Yongin, Korea
| | - Jae Jung Lee
- Department of Neurology, Ilsan Paik Hospital, Inje University College of Medicine, Goyang, Korea
| | - Phil Hyu Lee
- Department of Neurology, Yonsei University College of Medicine, Seoul, Korea.,Severance Biomedical Science Institute, Yonsei University College of Medicine, Seoul, Korea
| | - Young H Sohn
- Department of Neurology, Yonsei University College of Medicine, Seoul, Korea
| |
Collapse
|
49
|
Campbell MC, Myers PS, Weigand AJ, Foster ER, Cairns NJ, Jackson JJ, Lessov‐Schlaggar CN, Perlmutter JS. Parkinson disease clinical subtypes: key features & clinical milestones. Ann Clin Transl Neurol 2020; 7:1272-1283. [PMID: 32602253 PMCID: PMC7448190 DOI: 10.1002/acn3.51102] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2020] [Revised: 05/15/2020] [Accepted: 05/22/2020] [Indexed: 12/20/2022] Open
Abstract
OBJECTIVES Based on multi-domain classification of Parkinson disease (PD) subtypes, we sought to determine the key features that best differentiate subtypes and the utility of PD subtypes to predict clinical milestones. METHODS Prospective cohort of 162 PD participants with ongoing, longitudinal follow-up. Latent class analysis (LCA) delineated subtypes based on score patterns across baseline motor, cognitive, and psychiatric measures. Discriminant analyses identified key features that distinguish subtypes at baseline. Cox regression models tested PD subtype differences in longitudinal conversion to clinical milestones, including deep brain stimulation (DBS), dementia, and mortality. RESULTS LCA identified distinct subtypes: "motor only" (N = 63) characterized by primary motor deficits; "psychiatric & motor" (N = 17) characterized by prominent psychiatric symptoms and moderate motor deficits; "cognitive & motor" (N = 82) characterized by impaired cognition and moderate motor deficits. Depression, executive function, and apathy best discriminated subtypes. Since enrollment, 22 had DBS, 48 developed dementia, and 46 have died. Although there were no subtype differences in rate of DBS, dementia occurred at a higher rate in the "cognitive & motor" subtype. Surprisingly, mortality risk was similarly elevated for both "cognitive & motor" and "psychiatric & motor" subtypes compared to the "motor only" subtype (relative risk = 3.15, 2.60). INTERPRETATION Psychiatric and cognitive features, rather than motor deficits, distinguish clinical PD subtypes and predict greater risk of subsequent dementia and mortality. These results emphasize the value of multi-domain assessments to better characterize clinical variability in PD. Further, differences in dementia and mortality rates demonstrate the prognostic utility of PD subtypes.
Collapse
Affiliation(s)
- Meghan C. Campbell
- Department of NeurologyWashington University School of MedicineSt. LouisMO
- Department of RadiologyWashington University School of MedicineSt. LouisMO
| | - Peter S. Myers
- Department of NeurologyWashington University School of MedicineSt. LouisMO
| | - Alexandra J. Weigand
- Department of Psychological and Brain SciencesWashington University in St. LouisSt. LouisMO
| | - Erin R. Foster
- Department of NeurologyWashington University School of MedicineSt. LouisMO
- Program in Occupational TherapyWashington University School of MedicineSt. LouisMO
- Department of PsychiatryWashington University School of MedicineSt. LouisMO
| | - Nigel J. Cairns
- Department of NeurologyWashington University School of MedicineSt. LouisMO
- College of Medicine and HealthUniversity of ExeterExeterUK
| | - Joshua J. Jackson
- Department of Psychological and Brain SciencesWashington University in St. LouisSt. LouisMO
| | | | - Joel S. Perlmutter
- Department of NeurologyWashington University School of MedicineSt. LouisMO
- Department of RadiologyWashington University School of MedicineSt. LouisMO
- Program in Occupational TherapyWashington University School of MedicineSt. LouisMO
- Department of NeuroscienceWashington University School of MedicineSt. LouisMO
- Program in Physical TherapyWashington University School of MedicineSt. LouisMO
| |
Collapse
|
50
|
Schulz MA, Chapman-Rounds M, Verma M, Bzdok D, Georgatzis K. Inferring disease subtypes from clusters in explanation space. Sci Rep 2020; 10:12900. [PMID: 32732917 PMCID: PMC7393364 DOI: 10.1038/s41598-020-68858-7] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2020] [Accepted: 06/05/2020] [Indexed: 01/01/2023] Open
Abstract
Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional biomedical data is often impossible for humans and challenging for machines. We introduce a new approach to facilitate the discovery of disease subtypes: Instead of analyzing the original data, we train a diagnostic classifier (healthy vs. diseased) and extract instance-wise explanations for the classifier's decisions. The distribution of instances in the explanation space of our diagnostic classifier amplifies the different reasons for belonging to the same class-resulting in a representation that is uniquely useful for discovering latent subtypes. We compare our ability to recover subtypes via cluster analysis on model explanations to classical cluster analysis on the original data. In multiple datasets with known ground-truth subclasses, particularly on UK Biobank brain imaging data and transcriptome data from the Cancer Genome Atlas, we show that cluster analysis on model explanations substantially outperforms the classical approach. While we believe clustering in explanation space to be particularly valuable for inferring disease subtypes, the method is more general and applicable to any kind of sub-type identification.
Collapse
Affiliation(s)
- Marc-Andre Schulz
- Department of Psychiatry, Psychotherapy and Psychosomatics, RWTH Aachen University, Aachen, Germany.
- QuantumBlack, London, UK.
| | - Matt Chapman-Rounds
- School of Informatics, University of Edinburgh, Edinburgh, UK
- QuantumBlack, London, UK
| | - Manisha Verma
- Verizon Media, Boston, MA, USA
- QuantumBlack, London, UK
| | - Danilo Bzdok
- Department of Biomedical Engineering, McConnell Brain Imaging Centre (BIC), Montreal Neurological Institute (MNI), Faculty of Medicine, McGill University, Montreal, Canada
- Mila - Quebec Artificial Intelligence Institute, Montreal, Canada
| | | |
Collapse
|