1
|
Wang X, Liu S, Yan Z, Yin F, Feng J, Liu H, Liu Y, Li Y. Radiomics Nomograms Based on Multi-sequence MRI for Identifying Cognitive Impairment and Predicting Cognitive Progression in Relapsing-Remitting Multiple Sclerosis. Acad Radiol 2024:S1076-6332(24)00591-9. [PMID: 39198138 DOI: 10.1016/j.acra.2024.08.026] [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: 07/08/2024] [Revised: 08/08/2024] [Accepted: 08/14/2024] [Indexed: 09/01/2024]
Abstract
RATIONALE AND OBJECTIVES To build radiomics nomograms based on multi-sequence MRI to facilitate the identification of cognitive impairment (CI) and prediction of cognitive progression (CP) in patients with relapsing-remitting multiple sclerosis (RRMS). MATERIALS AND METHODS We retrospectively included two RRMS cohorts with multi-sequence MRI and Symbol Digit Modalities Test (SDMT) data: dataset1 (n = 149, for training and validation) and dataset2 (n = 29, for external validation). 80 patients of dataset1 had a 2-year follow-up SDMT. CI and CP were evaluated using SDMT scores at baseline and follow-up. The included DIR sequence aided in identifying cortical lesions. Lesion radiomics and structural features were extracted and selected from multi-sequence MRI, followed by the computation of radiomics and structural scores. The nomogram was developed through multivariate logistic regression, integrating clinical data, radiomics, and structural scores to identify CI in patients. Moreover, a similar method was employed to further construct a nomogram predicting CP in patients. RESULTS The nomogram demonstrated superior performance in identifying patients with CI, with area under the curve (AUC) values of 0.937 (95% Conf. Interval: 0.898-0.975) and 0.876 (0.810-0.943) in internal and external validation sets, compared to models solely based on clinical data, lesion radiomics, and structural features. Furthermore, another nomogram constructed in predicting CP also exhibited outstanding performance, with an AUC value of 0.969 (0.875-1.000) in the validation set. CONCLUSION These nomograms, integrating clinical data, multi-sequence lesions radiomics, and structural features, enable more effective identification of CI and early prediction of CP in RRMS patients, providing important support for clinical decision-making.
Collapse
Affiliation(s)
- Xiaohua Wang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China; College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China
| | - Shangqing Liu
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China
| | - Zichun Yan
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| | - Feiyue Yin
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| | - Jinzhou Feng
- Department of Neurology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| | - Hao Liu
- Yizhun Medical AI, Beijing 100000, China
| | - Yanbing Liu
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China
| | - Yongmei Li
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China.
| |
Collapse
|
2
|
Marzi C, d'Ambrosio A, Diciotti S, Bisecco A, Altieri M, Filippi M, Rocca MA, Storelli L, Pantano P, Tommasin S, Cortese R, De Stefano N, Tedeschi G, Gallo A. Prediction of the information processing speed performance in multiple sclerosis using a machine learning approach in a large multicenter magnetic resonance imaging data set. Hum Brain Mapp 2022; 44:186-202. [PMID: 36255155 PMCID: PMC9783441 DOI: 10.1002/hbm.26106] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2022] [Revised: 06/02/2022] [Accepted: 09/24/2022] [Indexed: 02/05/2023] Open
Abstract
Many patients with multiple sclerosis (MS) experience information processing speed (IPS) deficits, and the Symbol Digit Modalities Test (SDMT) has been recommended as a valid screening test. Magnetic resonance imaging (MRI) has markedly improved the understanding of the mechanisms associated with cognitive deficits in MS. However, which structural MRI markers are the most closely related to cognitive performance is still unclear. We used the multicenter 3T-MRI data set of the Italian Neuroimaging Network Initiative to extract multimodal data (i.e., demographic, clinical, neuropsychological, and structural MRIs) of 540 MS patients. We aimed to assess, through machine learning techniques, the contribution of brain MRI structural volumes in the prediction of IPS deficits when combined with demographic and clinical features. We trained and tested the eXtreme Gradient Boosting (XGBoost) model following a rigorous validation scheme to obtain reliable generalization performance. We carried out a classification and a regression task based on SDMT scores feeding each model with different combinations of features. For the classification task, the model trained with thalamus, cortical gray matter, hippocampus, and lesions volumes achieved an area under the receiver operating characteristic curve of 0.74. For the regression task, the model trained with cortical gray matter and thalamus volumes, EDSS, nucleus accumbens, lesions, and putamen volumes, and age reached a mean absolute error of 0.95. In conclusion, our results confirmed that damage to cortical gray matter and relevant deep and archaic gray matter structures, such as the thalamus and hippocampus, is among the most relevant predictors of cognitive performance in MS.
Collapse
Affiliation(s)
- Chiara Marzi
- MS Center and 3T‐MRI Research Unit, Department of Advanced Medical and Surgical Sciences (DAMSS)University of Campania “Luigi Vanvitelli”NapoliItaly,Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” – DEIAlma Mater Studiorum – University of BolognaBolognaItaly
| | - Alessandro d'Ambrosio
- MS Center and 3T‐MRI Research Unit, Department of Advanced Medical and Surgical Sciences (DAMSS)University of Campania “Luigi Vanvitelli”NapoliItaly
| | - Stefano Diciotti
- Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi” – DEIAlma Mater Studiorum – University of BolognaBolognaItaly,Alma Mater Research Institute for Human‐Centered Artificial IntelligenceUniversity of BolognaBolognaItaly
| | - Alvino Bisecco
- MS Center and 3T‐MRI Research Unit, Department of Advanced Medical and Surgical Sciences (DAMSS)University of Campania “Luigi Vanvitelli”NapoliItaly
| | - Manuela Altieri
- MS Center and 3T‐MRI Research Unit, Department of Advanced Medical and Surgical Sciences (DAMSS)University of Campania “Luigi Vanvitelli”NapoliItaly,Department of PsychologyUniversity of Campania “Luigi Vanvitelli”NapoliItaly
| | - Massimo Filippi
- Neuroimaging Research Unit, Division of NeuroscienceVita‐Salute San Raffaele University, IRCCS San Raffaele Scientific InstituteMilanItaly,Neurology and Neurophysiology UnitVita‐Salute San Raffaele University, IRCCS San Raffaele Scientific InstituteMilanItaly
| | - Maria Assunta Rocca
- Neuroimaging Research Unit, Division of NeuroscienceVita‐Salute San Raffaele University, IRCCS San Raffaele Scientific InstituteMilanItaly,Neurology and Neurophysiology UnitVita‐Salute San Raffaele University, IRCCS San Raffaele Scientific InstituteMilanItaly
| | - Loredana Storelli
- Neuroimaging Research Unit, Division of NeuroscienceVita‐Salute San Raffaele University, IRCCS San Raffaele Scientific InstituteMilanItaly
| | - Patrizia Pantano
- Department of Human NeurosciencesSapienza University of RomeRomeItaly,IRCCS NeuromedPozzilliItaly
| | - Silvia Tommasin
- Department of Human NeurosciencesSapienza University of RomeRomeItaly
| | - Rosa Cortese
- Department of Medicine, Surgery and NeuroscienceUniversity of SienaSienaItaly
| | - Nicola De Stefano
- Department of Medicine, Surgery and NeuroscienceUniversity of SienaSienaItaly
| | - Gioacchino Tedeschi
- MS Center and 3T‐MRI Research Unit, Department of Advanced Medical and Surgical Sciences (DAMSS)University of Campania “Luigi Vanvitelli”NapoliItaly
| | - Antonio Gallo
- MS Center and 3T‐MRI Research Unit, Department of Advanced Medical and Surgical Sciences (DAMSS)University of Campania “Luigi Vanvitelli”NapoliItaly
| | | |
Collapse
|
3
|
Role of Demyelination in the Persistence of Neurological and Mental Impairments after COVID-19. Int J Mol Sci 2022; 23:ijms231911291. [PMID: 36232592 PMCID: PMC9569975 DOI: 10.3390/ijms231911291] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2022] [Revised: 09/16/2022] [Accepted: 09/21/2022] [Indexed: 11/16/2022] Open
Abstract
Long-term neurological and mental complications of COVID-19, the so-called post-COVID syndrome or long COVID, affect the quality of life. The most persistent manifestations of long COVID include fatigue, anosmia/hyposmia, insomnia, depression/anxiety, and memory/attention deficits. The physiological basis of neurological and psychiatric disorders is still poorly understood. This review summarizes the current knowledge of neurological sequelae in post-COVID patients and discusses brain demyelination as a possible mechanism of these complications with a focus on neuroimaging findings. Numerous reviews, experimental and theoretical studies consider brain demyelination as one of the mechanisms of the central neural system impairment. Several factors might cause demyelination, such as inflammation, direct effect of the virus on oligodendrocytes, and cerebrovascular disorders, inducing myelin damage. There is a contradiction between the solid fundamental basis underlying demyelination as the mechanism of the neurological injuries and relatively little published clinical evidence related to demyelination in COVID-19 patients. The reason for this probably lies in the fact that most clinical studies used conventional MRI techniques, which can detect only large, clearly visible demyelinating lesions. A very limited number of studies use specific methods for myelin quantification detected changes in the white matter tracts 3 and 10 months after the acute phase of COVID-19. Future research applying quantitative MRI assessment of myelin in combination with neurological and psychological studies will help in understanding the mechanisms of post-COVID complications associated with demyelination.
Collapse
|
4
|
Denissen S, Engemann DA, De Cock A, Costers L, Baijot J, Laton J, Penner IK, Grothe M, Kirsch M, D'hooghe MB, D'Haeseleer M, Dive D, De Mey J, Van Schependom J, Sima DM, Nagels G. Brain age as a surrogate marker for cognitive performance in multiple sclerosis. Eur J Neurol 2022; 29:3039-3049. [PMID: 35737867 PMCID: PMC9541923 DOI: 10.1111/ene.15473] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Revised: 06/04/2022] [Accepted: 06/15/2022] [Indexed: 11/28/2022]
Abstract
Background and purpose Data from neuro‐imaging techniques allow us to estimate a brain's age. Brain age is easily interpretable as ‘how old the brain looks’ and could therefore be an attractive communication tool for brain health in clinical practice. This study aimed to investigate its clinical utility by investigating the relationship between brain age and cognitive performance in multiple sclerosis (MS). Methods A linear regression model was trained to predict age from brain magnetic resonance imaging volumetric features and sex in a healthy control dataset (HC_train, n = 1673). This model was used to predict brain age in two test sets: HC_test (n = 50) and MS_test (n = 201). Brain‐predicted age difference (BPAD) was calculated as BPAD = brain age minus chronological age. Cognitive performance was assessed by the Symbol Digit Modalities Test (SDMT). Results Brain age was significantly related to SDMT scores in the MS_test dataset (r = −0.46, p < 0.001) and contributed uniquely to variance in SDMT beyond chronological age, reflected by a significant correlation between BPAD and SDMT (r = −0.24, p < 0.001) and a significant weight (−0.25, p = 0.002) in a multivariate regression equation with age. Conclusions Brain age is a candidate biomarker for cognitive dysfunction in MS and an easy to grasp metric for brain health.
Collapse
Affiliation(s)
- S Denissen
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium.,Kolonel Begaultlaan 1b, 3012, Belgium
| | - D A Engemann
- Université Paris-Saclay, CEA, 1 Rue Honoré d'Estienne d'Orves, 91120, Palaiseau, France.,Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Stephanstraße 1A, D-04103, Leipzig, Germany
| | - A De Cock
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium
| | - L Costers
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium.,Kolonel Begaultlaan 1b, 3012, Belgium
| | - J Baijot
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium
| | - J Laton
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium.,Nuffield Department of Clinical Neurosciences, University of Oxford, Headley Way, Headington, Oxford, OX3 9DU, United Kingdom
| | - I K Penner
- Cogito Center for Applied Neurocognition and Neuropsychological Research, Merowingerplatz 1, 40225, Düsseldorf, Germany.,Department of Neurology, Medical Faculty, Heinrich Heine University Düsseldorf, Universitätsstr. 1, 40225, Düsseldorf, Germany
| | - M Grothe
- Department of Neurology, University Medicine Greifswald, Ferdinand-Sauerbruchstraße, 17475, Greifswald, Germany
| | - M Kirsch
- Institute for Diagnostic Radiology and Neuroradiology, University Medicine of Greifswald, Ferdinand-Sauerbruch-Straße, 17489, Greifswald, Germany
| | - M B D'hooghe
- National Multiple Sclerosis Center Melsbroek, Vereeckenstraat 44, 1820, Melsbroek, Belgium.,Center for Neurosciences, Vrije Universiteit Brussel, Laarbeeklaan 103, 1090, Brussels, Belgium
| | - M D'Haeseleer
- National Multiple Sclerosis Center Melsbroek, Vereeckenstraat 44, 1820, Melsbroek, Belgium
| | - D Dive
- Department of Neurology, University Hospital of Liege, Rue Grandfosse 31/33, 4130, Esneux, Belgium
| | - J De Mey
- Department of Radiology, UZ Brussel, Laarbeeklaan 101, 1090, Brussels, Belgium
| | - J Van Schependom
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium.,Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium
| | - D M Sima
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium.,Kolonel Begaultlaan 1b, 3012, Belgium
| | - G Nagels
- AIMS lab, Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussels, Belgium.,Kolonel Begaultlaan 1b, 3012, Belgium.,St Edmund Hall, University of Oxford, Queen's Lane, Oxford, OX1 4AR, UK
| |
Collapse
|
5
|
Chitnis T, Vandercappellen J, King M, Brichetto G. Symptom Interconnectivity in Multiple Sclerosis: A Narrative Review of Potential Underlying Biological Disease Processes. Neurol Ther 2022; 11:1043-1070. [PMID: 35680693 PMCID: PMC9338216 DOI: 10.1007/s40120-022-00368-2] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/22/2022] [Accepted: 05/16/2022] [Indexed: 11/18/2022] Open
Abstract
Introduction Fatigue, cognitive impairment, depression, and pain are highly prevalent symptoms in multiple sclerosis (MS). These often co-occur and may be explained by a common etiology. By reviewing existing literature, we aimed to identify potential underlying biological processes implicated in the interconnectivity between these symptoms. Methods A literature search was conducted to identify articles reporting research into the biological mechanisms responsible for the manifestation of fatigue, cognitive impairment, depression, and pain in MS. PubMed was used to search for articles published from July 2011 to July 2021. We reviewed and assessed findings from the literature to identify biological processes common to the symptoms of interest. Results Of 693 articles identified from the search, 252 were selected following screening of titles and abstracts and assessing reference lists of review articles. Four biological processes linked with two or more of the symptoms of interest were frequently identified from the literature: (1) direct neuroanatomical changes to brain regions linked with symptoms of interest (e.g., thalamic injury associated with cognitive impairment, fatigue, and depression), (2) pro-inflammatory cytokines associated with so-called ‘sickness behavior,’ including manifestation of fatigue, transient cognitive impairment, depression, and pain, (3) dysregulation of monoaminergic pathways leading to depressive symptoms and fatigue, and (4) hyperactivity of the hypothalamic–pituitary-adrenal (HPA) axis as a result of pro-inflammatory cytokines promoting the release of brain noradrenaline, serotonin, and tryptophan, which is associated with symptoms of depression and cognitive impairment. Conclusion The co-occurrence of fatigue, cognitive impairment, depression, and pain in MS appears to be associated with a common set of etiological factors, namely neuroanatomical changes, pro-inflammatory cytokines, dysregulation of monoaminergic pathways, and a hyperactive HPA axis. This association of symptoms and biological processes has important implications for disease management strategies and, eventually, could help find a common therapeutic pathway that will impact both inflammation and neuroprotection. Supplementary Information The online version contains supplementary material available at 10.1007/s40120-022-00368-2.
Collapse
Affiliation(s)
- Tanuja Chitnis
- Department of Neurology, Brigham and Women's Hospital, 75 Francis Street, Boston, MA, 02115, USA.
| | | | - Miriam King
- Novartis Pharma AG, Fabrikstrasse 12-2, 4056, Basel, Switzerland
| | - Giampaolo Brichetto
- Associazione Italiana Sclerosi Multipla Rehabilitation Center, Via Operai, 30, 16149, Genoa, GE, Italy
| |
Collapse
|
6
|
Sjøgård M, Wens V, Van Schependom J, Costers L, D'hooghe M, D'haeseleer M, Woolrich M, Goldman S, Nagels G, De Tiège X. Brain dysconnectivity relates to disability and cognitive impairment in multiple sclerosis. Hum Brain Mapp 2020; 42:626-643. [PMID: 33242237 PMCID: PMC7814767 DOI: 10.1002/hbm.25247] [Citation(s) in RCA: 22] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2019] [Revised: 09/10/2020] [Accepted: 09/29/2020] [Indexed: 12/27/2022] Open
Abstract
The pathophysiology of cognitive dysfunction in multiple sclerosis (MS) is still unclear. This magnetoencephalography (MEG) study investigates the impact of MS on brain resting-state functional connectivity (rsFC) and its relationship to disability and cognitive impairment. We investigated rsFC based on power envelope correlation within and between different frequency bands, in a large cohort of participants consisting of 99 MS patients and 47 healthy subjects. Correlations were investigated between rsFC and outcomes on disability, disease duration and 7 neuropsychological scores within each group, while stringently correcting for multiple comparisons and possible confounding factors. Specific dysconnections correlating with MS-induced physical disability and disease duration were found within the sensorimotor and language networks, respectively. Global network-level reductions in within- and cross-network rsFC were observed in the default-mode network. Healthy subjects and patients significantly differed in their scores on cognitive fatigue and verbal fluency. Healthy subjects and patients showed different correlation patterns between rsFC and cognitive fatigue or verbal fluency, both of which involved a shift in patients from the posterior default-mode network to the language network. Introducing electrophysiological rsFC in a regression model of verbal fluency and cognitive fatigue in MS patients significantly increased the explained variance compared to a regression limited to structural MRI markers (relative thalamic volume and lesion load). This MEG study demonstrates that MS induces distinct changes in the resting-state functional brain architecture that relate to disability, disease duration and specific cognitive functioning alterations. It highlights the potential value of electrophysiological intrinsic rsFC for monitoring the cognitive impairment in patients with MS.
Collapse
Affiliation(s)
- Martin Sjøgård
- Laboratoire de Cartographie fonctionnelle du Cerveau, UNI-ULB Neuroscience Institute, Université libre de Bruxelles (ULB), Brussels, Belgium
| | - Vincent Wens
- Laboratoire de Cartographie fonctionnelle du Cerveau, UNI-ULB Neuroscience Institute, Université libre de Bruxelles (ULB), Brussels, Belgium.,Department of Functional Neuroimaging, Service of Nuclear Medicine, CUB-Hôpital Erasme, Université libre de Bruxelles (ULB), Brussels, Belgium
| | - Jeroen Van Schependom
- Center for Neurosciences, Vrije Universiteit Brussel, Brussels, Belgium.,National MS Center, Belgium
| | - Lars Costers
- Center for Neurosciences, Vrije Universiteit Brussel, Brussels, Belgium
| | - Marie D'hooghe
- Center for Neurosciences, Vrije Universiteit Brussel, Brussels, Belgium.,National MS Center, Belgium
| | - Miguel D'haeseleer
- Center for Neurosciences, Vrije Universiteit Brussel, Brussels, Belgium.,National MS Center, Belgium
| | - Mark Woolrich
- Oxford Centre for Human Brain Activity, Wellcome Centre for Integrative Neuroimaging, Department of Psychiatry, University of Oxford, Oxford, UK
| | - Serge Goldman
- Laboratoire de Cartographie fonctionnelle du Cerveau, UNI-ULB Neuroscience Institute, Université libre de Bruxelles (ULB), Brussels, Belgium.,Department of Functional Neuroimaging, Service of Nuclear Medicine, CUB-Hôpital Erasme, Université libre de Bruxelles (ULB), Brussels, Belgium
| | - Guy Nagels
- Center for Neurosciences, Vrije Universiteit Brussel, Brussels, Belgium.,National MS Center, Belgium.,St Edmund Hall, University of Oxford, Oxford, UK
| | - Xavier De Tiège
- Laboratoire de Cartographie fonctionnelle du Cerveau, UNI-ULB Neuroscience Institute, Université libre de Bruxelles (ULB), Brussels, Belgium.,Department of Functional Neuroimaging, Service of Nuclear Medicine, CUB-Hôpital Erasme, Université libre de Bruxelles (ULB), Brussels, Belgium
| |
Collapse
|
7
|
Buyukturkoglu K, Zeng D, Bharadwaj S, Tozlu C, Mormina E, Igwe KC, Lee S, Habeck C, Brickman AM, Riley CS, De Jager PL, Sumowski JF, Leavitt VM. Classifying multiple sclerosis patients on the basis of SDMT performance using machine learning. Mult Scler 2020; 27:107-116. [DOI: 10.1177/1352458520958362] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Abstract
Objective: To build a model to predict cognitive status reflecting structural, functional, and white matter integrity changes in early multiple sclerosis (MS). Methods: Based on Symbol Digit Modalities Test (SDMT) performance, 183 early MS patients were assigned “lower” or “higher” performance groups. Three-dimensional (3D)-T2, T1, diffusion weighted, and resting-state magnetic resonance imaging (MRI) data were acquired in 3T. Using Random Forest, five models were trained to classify patients into two groups based on 1—demographic/clinical, 2—lesion volume/location, 3—local/global tissue volume, 4—local/global diffusion tensor imaging, and 5—whole-brain resting-state-functional-connectivity measures. In a final model, all important features from previous models were concatenated. Area under the receiver operating characteristic curve (AUC) values were calculated to evaluate classifier performance. Results: The highest AUC value (0.90) was achieved by concatenating all important features from neuroimaging models. The top 10 contributing variables included volumes of bilateral nucleus accumbens and right thalamus, mean diffusivity of left cingulum-angular bundle, and functional connectivity among hubs of seven large-scale networks. Conclusion: These results provide an indication of a non-random brain pattern mostly compromising areas involved in attentional processes specific to patients who perform worse in SDMT. High accuracy of the final model supports this pattern as a potential neuroimaging biomarker of subtle cognitive changes in early MS.
Collapse
Affiliation(s)
- Korhan Buyukturkoglu
- Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA
| | - Dana Zeng
- Department of Biostatistics, Columbia University, New York, NY, USA
| | - Srinidhi Bharadwaj
- Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA
| | - Ceren Tozlu
- Department of Radiology, Weill Cornell Medicine, New York, NY, USA
| | - Enricomaria Mormina
- Department of Clinical and Experimental Medicine, Policlinico Universitario “G. Martino,” University of Messina, Messina, Italy/Department of Biomedical and Dental Sciences and Morphofunctional Imaging, University of Messina, Messina, Italy
| | - Kay C Igwe
- Department of Neurology, Taub Institute for Research on Alzheimer’s Disease and the Aging Brain, G.H. Sergievsky Center, College of Physicians and Surgeons, Columbia University, New York, NY, USA
| | - Seonjoo Lee
- Department of Biostatistics, Columbia University, New York, NY, USA/Mental Health Data Science, Research Foundation for Mental Hygiene, Inc, New York State Psychiatric Institute, New York, NY, USA
| | - Christian Habeck
- Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA
| | - Adam M Brickman
- Department of Neurology, Taub Institute for Research on Alzheimer’s Disease and the Aging Brain, G.H. Sergievsky Center, College of Physicians and Surgeons, Columbia University, New York, NY, USA
| | - Claire S Riley
- Multiple Sclerosis Center, Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA
| | - Philip L De Jager
- Multiple Sclerosis Center, Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA/Center for Translational & Computational Neuroimmunology, Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA
| | - James F Sumowski
- Corinne Goldsmith Dickinson Center for Multiple Sclerosis, Mount Sinai Hospital, New York, NY, USA
| | - Victoria M Leavitt
- Department of Neurology, Columbia University Irving Medical Center, New York, NY, USA
| |
Collapse
|
8
|
Zhao L, Ng A, Chen Q, Lam B, Abrigo J, Au C, Mok VCT, Wong A, Lau AY. Impaired cognition is related to microstructural integrity in relapsing remitting multiple sclerosis. Ann Clin Transl Neurol 2020; 7:1193-1203. [PMID: 32519512 PMCID: PMC7359116 DOI: 10.1002/acn3.51100] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2020] [Revised: 04/27/2020] [Accepted: 05/19/2020] [Indexed: 01/06/2023] Open
Abstract
Background Cognitive impairment is common in multiple sclerosis (MS). However, the relationship between cognitive deficits and microstructural abnormalities in Chinese MS patients remains unclear. We aimed to investigate the importance of microstructural abnormalities and the associations with cognitive impairment in Chinese MS patients. Methods Three‐dimensional T1‐weighted magnetic resonance imaging (MRI) scans were obtained from 36 relapsing remitting MS patients. Diffusion tensor imaging (DTI) scans were acquired for 29 (81%) patients. Cognitive impairment was assessed using a comprehensive neuropsychological battery. Patients were classified into cognitively impaired (CI) group and cognitively preserved (CP) group. Using volBrain and FSL software, we assessed white matter lesion burden, white matter (WM) and gray matter (GM) volumetric as well as microstructural diffusivity. MRI variables explaining cognitive impairment were analyzed. Results Fifteen (42%) patients were classified as CI. Verbal learning and memory was the most commonly impaired domain (n = 16, 44%). CI patients had lower mean skeleton fractional anisotropy (FA) value than CP patients (275.45 vs. 283.61 × 10−3, P = 0.023). The final predicting model including demographic variables and global skeleton mean diffusivity (MD) explained 43.6% of variance of the presence of cognitive impairment (β = 0.131, P = 0.041). CI patients showed a widespread change of microstructural integrity comparing to CP patients, which was rarely overlapping with lesion probability map. Microstructural abnormalities in corpus callosum were associated with performance in verbal learning and memory, processing speed and selective attention (P < 0.05). Conclusion Loss of microstructural integrity demonstrated by DTI helps explain cognitive dysfunction in Chinese MS patients.
Collapse
Affiliation(s)
- Lin Zhao
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Angel Ng
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Qianyun Chen
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Bonnie Lam
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Jill Abrigo
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Cheryl Au
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Vincent C T Mok
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Adrian Wong
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Alexander Y Lau
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong SAR, China
| |
Collapse
|
9
|
Tavazzi E, Bergsland N, Kuhle J, Jakimovski D, Ramanathan M, Maceski AM, Tomic D, Hagemeier J, Kropshofer H, Leppert D, Dwyer MG, Weinstock-Guttman B, Benedict RHB, Zivadinov R. A multimodal approach to assess the validity of atrophied T2-lesion volume as an MRI marker of disease progression in multiple sclerosis. J Neurol 2019; 267:802-811. [PMID: 31768628 DOI: 10.1007/s00415-019-09643-z] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2019] [Revised: 11/14/2019] [Accepted: 11/14/2019] [Indexed: 02/02/2023]
Abstract
BACKGROUND Atrophied T2-lesion volume (LV) is a novel MRI marker representing brain-lesion loss due to atrophy, able to predict long-term disability progression and conversion to secondary-progressive multiple sclerosis (MS). OBJECTIVE To better characterize atrophied T2-LV via comparison with other multidisciplinary markers of MS progression. METHODS We studied 127 MS patients (85 relapsing-remitting, RRMS and 42 progressive, PMS) and 20 clinically isolated syndrome (CIS) utilizing MRI, optical coherence tomography, and serum neurofilament light chain (sNfL) at baseline and at 5-year follow-up. Symbol Digit Modalities Test (SDMT) was obtained at follow-up. Atrophied T2-LV was calculated by combining baseline lesion masks with follow-up CSF partial-volume maps. Measures were compared between MS patients who developed or not disease progression (DP). Partial correlations between atrophied T2-LV and other biomarkers were performed, and corrected for multiple comparisons. RESULTS Atrophied T2-LV was the only biomarker that significantly differentiated DP from non-DP patients over the follow-up (p = 0.007). In both DP and non-DP groups, atrophied T2-LV was associated with baseline T2-LV and T1-LV (both p = 0.003), absolute change of T1-LV (DP p = 0.038; non-DP p = 0.003) and percentage of brain volume change (both p = 0.003). Furthermore, in the DP group, atrophied T2-LV was related to baseline brain parenchymal (p = 0.017) and thalamic (p = 0.003) volumes, thalamic volume change and follow-up SDMT (both p = 0.003). In non-DP patients, atrophied T2-LV was significantly related to baseline sNfL (p = 0.008), contrast-enhancing LV (p = 0.02) and percentage ventricular volume change (p = 0.003). CONCLUSION Atrophied T2-LV is associated with disability accrual in MS, and to several multimodal markers of disease evolution.
Collapse
Affiliation(s)
- Eleonora Tavazzi
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, 100 High Street, Buffalo, NY, 14203, USA
| | - Niels Bergsland
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, 100 High Street, Buffalo, NY, 14203, USA
| | - Jens Kuhle
- Departments of Medicine, Biomedicine and Clinical Research, Neurologic Clinic and Policlinic, University Hospital Basel, University of Basel, Basel, Switzerland
| | - Dejan Jakimovski
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, 100 High Street, Buffalo, NY, 14203, USA
| | - Murali Ramanathan
- Department of Pharmaceutical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA
| | - Aleksandra M Maceski
- Departments of Medicine, Biomedicine and Clinical Research, Neurologic Clinic and Policlinic, University Hospital Basel, University of Basel, Basel, Switzerland
| | | | - Jesper Hagemeier
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, 100 High Street, Buffalo, NY, 14203, USA
| | | | | | - Michael G Dwyer
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, 100 High Street, Buffalo, NY, 14203, USA
- Center for Biomedical Imaging at Clinical Translational Science Institute, University at Buffalo, State University of New York, Buffalo, NY, USA
| | - Bianca Weinstock-Guttman
- Jacobs MS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA
| | - Ralph H B Benedict
- Jacobs MS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA
| | - Robert Zivadinov
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, 100 High Street, Buffalo, NY, 14203, USA.
- Center for Biomedical Imaging at Clinical Translational Science Institute, University at Buffalo, State University of New York, Buffalo, NY, USA.
| |
Collapse
|
10
|
Cognitive Function in Hospitalized Patients with Multiple Sclerosis: A Case-Control Study. ARCHIVES OF NEUROSCIENCE 2019. [DOI: 10.5812/ans.89632] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
11
|
Liguori M, Nuzziello N, Simone M, Amoroso N, Viterbo RG, Tangaro S, Consiglio A, Giordano P, Bellotti R, Trojano M. Association between miRNAs expression and cognitive performances of Pediatric Multiple Sclerosis patients: A pilot study. Brain Behav 2019; 9:e01199. [PMID: 30656857 PMCID: PMC6379516 DOI: 10.1002/brb3.1199] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/12/2018] [Accepted: 11/28/2018] [Indexed: 12/11/2022] Open
Abstract
INTRODUCTION The Pediatric onset of Multiple Sclerosis (PedMS) occurs in up to 10% of all cases. Cognitive impairment is one of the frequent symptoms, exerting severe impact in patients' quality of life and school performances. The underlying pathogenic mechanisms are not fully understood, and molecular markers predictive of cognitive dysfunctions need to be identified. On these grounds, we searched for molecular signature/s (i.e., miRNAs and target genes) associated with cognitive impairment in a selected population of PedMS patients. Additionally, changes of their regional brain volumes associated with the miRNAs of interest were investigated. METHODS Nineteen PedMS subjects received a full cognitive evaluation; total RNA from peripheral blood samples was processed by next-generation sequencing followed by a bioinformatics/biostatistics analysis. RESULTS The expression of 11 miRNAs significantly correlated with the scores obtained at different cognitive tests; among the others, eight miRNAs correlated with the Trail Making Tests. The computational target prediction identified 337 genes targeted by the miRNAs of interest; a tangled network of molecular connections was hypothesized, where genes like BST1, NTNG2, SPTB, and STAB1, already associated with cognitive dysfunctions, were nodes of the net. Furthermore, the expression of some miRNAs significantly correlated with cerebral volumes, for example, four miRNAs with the cerebellum cortex. CONCLUSIONS As far as we know, this is the first evaluation exploring miRNAs in the cognitive performances of PedMS. Although none of these results survived the multiple tests' corrections, we believe that they may represent a step forward the identification of biomarkers useful for monitoring and targeting the onset/progression of cognitive impairments in MS.
Collapse
Affiliation(s)
- Maria Liguori
- National Research CouncilBari UnitInstitute of Biomedical TechnologiesBariItaly
| | - Nicoletta Nuzziello
- National Research CouncilBari UnitInstitute of Biomedical TechnologiesBariItaly
| | - Marta Simone
- Unit for Severe Disabilities in Developmental Age and Young Adults, Developmental Neurology and NeurorehabilitationScientific Institute IRCCS E. MedeaBrindisiItaly
- Department of Basic Sciences, Neurosciences and Sense OrgansUniversity of BariBariItaly
| | - Nicola Amoroso
- Dipartimento Interateneo di Fisica “M. Merlin”Università degli studi di Bari “A. Moro”BariItaly
- Istituto Nazionale di Fisica Nucleare, Sezione di BariBariItaly
| | - Rosa Gemma Viterbo
- Department of Basic Sciences, Neurosciences and Sense OrgansUniversity of BariBariItaly
| | - Sabina Tangaro
- Istituto Nazionale di Fisica Nucleare, Sezione di BariBariItaly
| | - Arianna Consiglio
- National Research CouncilBari UnitInstitute of Biomedical TechnologiesBariItaly
| | - Paola Giordano
- General Paediatric Unit “B. Trambusti”, Azienda Policlinico‐Giovanni XXIIIUniversity of BariBariItaly
| | - Roberto Bellotti
- Dipartimento Interateneo di Fisica “M. Merlin”Università degli studi di Bari “A. Moro”BariItaly
- Istituto Nazionale di Fisica Nucleare, Sezione di BariBariItaly
| | - Maria Trojano
- Department of Basic Sciences, Neurosciences and Sense OrgansUniversity of BariBariItaly
| |
Collapse
|