1
|
Rajagopal SK, Beltz AM, Hampstead BM, Polk TA. Estimating individual trajectories of structural and cognitive decline in mild cognitive impairment for early prediction of progression to dementia of the Alzheimer's type. Sci Rep 2024; 14:12906. [PMID: 38839800 PMCID: PMC11153588 DOI: 10.1038/s41598-024-63301-7] [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: 12/27/2023] [Accepted: 05/27/2024] [Indexed: 06/07/2024] Open
Abstract
Only a third of individuals with mild cognitive impairment (MCI) progress to dementia of the Alzheimer's type (DAT). Identifying biomarkers that distinguish individuals with MCI who will progress to DAT (MCI-Converters) from those who will not (MCI-Non-Converters) remains a key challenge in the field. In our study, we evaluate whether the individual rates of loss of volumes of the Hippocampus and entorhinal cortex (EC) with age in the MCI stage can predict progression to DAT. Using data from 758 MCI patients in the Alzheimer's Disease Neuroimaging Database, we employ Linear Mixed Effects (LME) models to estimate individual trajectories of regional brain volume loss over 12 years on average. Our approach involves three key analyses: (1) mapping age-related volume loss trajectories in MCI-Converters and Non-Converters, (2) using logistic regression to predict progression to DAT based on individual rates of hippocampal and EC volume loss, and (3) examining the relationship between individual estimates of these volumetric changes and cognitive decline across different cognitive functions-episodic memory, visuospatial processing, and executive function. We find that the loss of Hippocampal volume is significantly more rapid in MCI-Converters than Non-Converters, but find no such difference in EC volumes. We also find that the rate of hippocampal volume loss in the MCI stage is a significant predictor of conversion to DAT, while the rate of volume loss in the EC and other additional regions is not. Finally, individual estimates of rates of regional volume loss in both the Hippocampus and EC, and other additional regions, correlate strongly with individual rates of cognitive decline. Across all analyses, we find significant individual variation in the initial volumes and the rates of changes in volume with age in individuals with MCI. This study highlights the importance of personalized approaches in predicting AD progression, offering insights for future research and intervention strategies.
Collapse
Affiliation(s)
| | - Adriene M Beltz
- Department of Psychology, University of Michigan, Ann Arbor, MI, USA
| | - Benjamin M Hampstead
- Department of Psychiatry, University of Michigan, Ann Arbor, MI, USA
- VA Ann Arbor Healthcare System, Ann Arbor, MI, USA
| | - Thad A Polk
- Department of Psychology, University of Michigan, Ann Arbor, MI, USA
| |
Collapse
|
2
|
Wang X, Peng L, Zhan S, Yin X, Huang L, Huang J, Yang J, Zhang Y, Zeng Y, Liang S. Alterations in hippocampus-centered morphological features and function of the progression from normal cognition to mild cognitive impairment. Asian J Psychiatr 2024; 93:103921. [PMID: 38237533 DOI: 10.1016/j.ajp.2024.103921] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/29/2023] [Revised: 12/21/2023] [Accepted: 01/06/2024] [Indexed: 03/08/2024]
Abstract
Mild cognitive impairment (MCI) is a significant precursor to dementia, highlighting the critical need for early identification of individuals at high risk of MCI to prevent cognitive decline. The study aimed to investigate the changes in brain structure and function before the onset of MCI. This study enrolled 19 older adults with progressive normal cognition (pNC) to MCI and 19 older adults with stable normal cognition (sNC). The gray matter (GM) volume and functional connectivity (FC) were estimated via magnetic resonance imaging during their normal cognition state 3 years prior. Additionally, spatial associations between FC maps and neurochemical profiles were examined using JuSpace. Compared to the sNC group, the pNC group showed decreased volume in the left hippocampus and left amygdala. The significantly positive correlation was observed between the GM volume of the left hippocampus and the MMSE scores after 3 years in pNC group. Besides, it showed that the pNC group had increased FC between the left hippocampus and the anterior-posterior cingulate gyrus, which was significantly correlated with the spatial distribution of dopamine D2 and noradrenaline transporter. Taken together, the study identified the abnormal brain characteristics before the onset of MCI, which might provide insight into clinical research.
Collapse
Affiliation(s)
- Xiuxiu Wang
- National-Local Joint Engineering Research Center of Rehabilitation Medicine Technology, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China; College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Lixin Peng
- College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Shiqi Zhan
- College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Xiaolong Yin
- National-Local Joint Engineering Research Center of Rehabilitation Medicine Technology, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China; Rehabilitation Industry Institute, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Li Huang
- National-Local Joint Engineering Research Center of Rehabilitation Medicine Technology, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China; Rehabilitation Industry Institute, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Jiayang Huang
- College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Junchao Yang
- College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Yusi Zhang
- College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Yi Zeng
- College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
| | - Shengxiang Liang
- National-Local Joint Engineering Research Center of Rehabilitation Medicine Technology, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China; Rehabilitation Industry Institute, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China; Traditional Chinese Medicine Rehabilitation Research Center of State Administration of Traditional Chinese Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China; Fujian Key Laboratory of Cognitive Rehabilitation, Affiliated Rehabilitation Hospital of Fujian University of Traditional Chinese Medicine, Fuzhou, Fuzhou 350001, China.
| |
Collapse
|
3
|
Devanarayan V, Ye Y, Charil A, Andreozzi E, Sachdev P, Llano DA, Tian L, Zhu L, Hampel H, Kramer L, Dhadda S, Irizarry M. Predicting clinical progression trajectories of early Alzheimer's disease patients. Alzheimers Dement 2024; 20:1725-1738. [PMID: 38087949 PMCID: PMC10984448 DOI: 10.1002/alz.13565] [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: 04/26/2023] [Revised: 09/06/2023] [Accepted: 11/07/2023] [Indexed: 03/16/2024]
Abstract
BACKGROUND Models for forecasting individual clinical progression trajectories in early Alzheimer's disease (AD) are needed for optimizing clinical studies and patient monitoring. METHODS Prediction models were constructed using a clinical trial training cohort (TC; n = 934) via a gradient boosting algorithm and then evaluated in two validation cohorts (VC 1, n = 235; VC 2, n = 421). Model inputs included baseline clinical features (cognitive function assessments, APOE ε4 status, and demographics) and brain magnetic resonance imaging (MRI) measures. RESULTS The model using clinical features achieved R2 of 0.21 and 0.31 for predicting 2-year cognitive decline in VC 1 and VC 2, respectively. Adding MRI features improved the R2 to 0.29 in VC 1, which employed the same preprocessing pipeline as the TC. Utilizing these model-based predictions for clinical trial enrichment reduced the required sample size by 20% to 49%. DISCUSSION Our validated prediction models enable baseline prediction of clinical progression trajectories in early AD, benefiting clinical trial enrichment and various applications.
Collapse
Affiliation(s)
- Viswanath Devanarayan
- Clinical Evidence GenerationEisai Inc.NutleyNew JerseyUSA
- Department of MathematicsStatistics and Computer ScienceUniversity of Illinois ChicagoChicagoIllinoisUSA
| | - Yuanqing Ye
- Clinical Evidence GenerationEisai Inc.NutleyNew JerseyUSA
| | - Arnaud Charil
- Clinical Evidence GenerationEisai Inc.NutleyNew JerseyUSA
| | | | | | - Daniel A. Llano
- Carle Illinois College of MedicineUrbanaIllinoisUSA
- Department of Molecular and Integrative PhysiologyUniversity of Illinois Urbana‐ChampaignUrbanaIllinoisUSA
| | - Lu Tian
- Department of Biomedical Data ScienceStanford University School of MedicinePalo AltoCaliforniaUSA
| | - Liang Zhu
- Clinical Evidence GenerationEisai Inc.NutleyNew JerseyUSA
| | - Harald Hampel
- Clinical Evidence GenerationEisai Inc.NutleyNew JerseyUSA
| | - Lynn Kramer
- Clinical Evidence GenerationEisai Inc.NutleyNew JerseyUSA
| | - Shobha Dhadda
- Clinical Evidence GenerationEisai Inc.NutleyNew JerseyUSA
| | | | | |
Collapse
|
4
|
Young AL, Oxtoby NP, Garbarino S, Fox NC, Barkhof F, Schott JM, Alexander DC. Data-driven modelling of neurodegenerative disease progression: thinking outside the black box. Nat Rev Neurosci 2024; 25:111-130. [PMID: 38191721 DOI: 10.1038/s41583-023-00779-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/30/2023] [Indexed: 01/10/2024]
Abstract
Data-driven disease progression models are an emerging set of computational tools that reconstruct disease timelines for long-term chronic diseases, providing unique insights into disease processes and their underlying mechanisms. Such methods combine a priori human knowledge and assumptions with large-scale data processing and parameter estimation to infer long-term disease trajectories from short-term data. In contrast to 'black box' machine learning tools, data-driven disease progression models typically require fewer data and are inherently interpretable, thereby aiding disease understanding in addition to enabling classification, prediction and stratification. In this Review, we place the current landscape of data-driven disease progression models in a general framework and discuss their enhanced utility for constructing a disease timeline compared with wider machine learning tools that construct static disease profiles. We review the insights they have enabled across multiple neurodegenerative diseases, notably Alzheimer disease, for applications such as determining temporal trajectories of disease biomarkers, testing hypotheses about disease mechanisms and uncovering disease subtypes. We outline key areas for technological development and translation to a broader range of neuroscience and non-neuroscience applications. Finally, we discuss potential pathways and barriers to integrating disease progression models into clinical practice and trial settings.
Collapse
Affiliation(s)
- Alexandra L Young
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK.
- Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
| | - Neil P Oxtoby
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK.
| | - Sara Garbarino
- Life Science Computational Laboratory, IRCCS Ospedale Policlinico San Martino, Genova, Italy
| | - Nick C Fox
- Dementia Research Centre, UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Frederik Barkhof
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Department of Radiology & Nuclear Medicine, Amsterdam University Medical Center, Amsterdam, The Netherlands
| | - Jonathan M Schott
- Dementia Research Centre, UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Daniel C Alexander
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
| |
Collapse
|
5
|
Di Folco C, Couronné R, Arnulf I, Mangone G, Leu-Semenescu S, Dodet P, Vidailhet M, Corvol JC, Lehéricy S, Durrleman S. Charting Disease Trajectories from Isolated REM Sleep Behavior Disorder to Parkinson's Disease. Mov Disord 2024; 39:64-75. [PMID: 38006282 DOI: 10.1002/mds.29662] [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: 10/10/2022] [Revised: 10/03/2023] [Accepted: 10/30/2023] [Indexed: 11/26/2023] Open
Abstract
BACKGROUND Clinical presentation and progression dynamics are variable in patients with Parkinson's disease (PD). Disease course mapping is an innovative disease modelling technique that summarizes the range of possible disease trajectories and estimates dimensions related to onset, sequence, and speed of progression of disease markers. OBJECTIVE To propose a disease course map for PD and investigate progression profiles in patients with or without rapid eye movement sleep behavioral disorders (RBD). METHODS Data of 919 PD patients and 88 isolated RBD patients from three independent longitudinal cohorts were analyzed (follow-up duration = 5.1; 95% confidence interval, 1.1-8.1] years). Disease course map was estimated by using eight clinical markers (motor and non-motor symptoms) and four imaging markers (dopaminergic denervation). RESULTS PD course map showed that the first changes occurred in the contralateral putamen 13 years before diagnosis, followed by changes in motor symptoms, dysautonomia, sleep-all before diagnosis-and finally cognitive decline at the time of diagnosis. The model showed earlier disease onset, earlier non-motor and later motor symptoms, more rapid progression of cognitive decline in PD patients with RBD than PD patients without RBD. This pattern was even more pronounced in patients with isolated RBD with early changes in sleep, followed by cognition and non-motor symptoms and later changes in motor symptoms. CONCLUSIONS Our findings are consistent with the presence of distinct patterns of progression between patients with and without RBD. Understanding heterogeneity of PD progression is key to decipher the underlying pathophysiology and select homogeneous subgroups of patients for precision medicine. © 2023 International Parkinson and Movement Disorder Society.
Collapse
Affiliation(s)
- Cécile Di Folco
- Inria, Centre de Paris, Paris, France
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Raphaël Couronné
- Inria, Centre de Paris, Paris, France
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Isabelle Arnulf
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Graziella Mangone
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Smaranda Leu-Semenescu
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Pauline Dodet
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Marie Vidailhet
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Jean-Christophe Corvol
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Stéphane Lehéricy
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| | - Stanley Durrleman
- Inria, Centre de Paris, Paris, France
- Paris Brain Institute-ICM, Paris, France
- Inserm, Paris, France
- CNRS, Paris, France
- Sorbonne Université, Paris, France
- AP-HP, Hôpital de la Pitié Salpêtrière, Paris, France
| |
Collapse
|