Unsupervised multimodal modeling of cognitive and brain health trajectories for early dementia prediction

• Published in: Scientific reports 2024-05, Vol.14 (1), p.10755-10755, Article 10755
• Main Authors: Burkhart, Michael C., Lee, Liz Y., Vaghari, Delshad, Toh, An Qi, Chong, Eddie, Chen, Christopher, Tiňo, Peter, Kourtzi, Zoe
• Format: Article
• Language: English
• Subjects: 631/378/2612; 639/705/1042; 692/53; 692/699/375/132; Aged; Aged, 80 and over; Alzheimer Disease - diagnosis; Alzheimer Disease - diagnostic imaging; Amyloid beta-Peptides - metabolism; Biomarkers; Brain - diagnostic imaging; Brain - pathology; Cognition - physiology; Dementia; Dementia - diagnosis; Dementia - diagnostic imaging; Dementia disorders; Diagnosis; Disease Progression; Female; Humanities and Social Sciences; Humans; Magnetic Resonance Imaging - methods; Male; Missing data; multidisciplinary; Neurodegenerative diseases; Predictions; Science; Science (multidisciplinary); Substantia grisea; Training; β-Amyloid
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-60914-w

Predicting the course of neurodegenerative disorders early has potential to greatly improve clinical management and patient outcomes. A key challenge for early prediction in real-world clinical settings is the lack of labeled data (i.e., clinical diagnosis). In contrast to supervised classification approaches that require labeled data, we propose an unsupervised multimodal trajectory modeling (MTM) approach based on a mixture of state space models that captures changes in longitudinal data (i.e., trajectories) and stratifies individuals without using clinical diagnosis for model training. MTM learns the relationship between states comprising expensive, invasive biomarkers (β-amyloid, grey matter density) and readily obtainable cognitive observations. MTM training on trajectories stratifies individuals into clinically meaningful clusters more reliably than MTM training on baseline data alone and is robust to missing data (i.e., cognitive data alone or single assessments). Extracting an individualized cognitive health index (i.e., MTM-derived cluster membership index) allows us to predict progression to AD more precisely than standard clinical assessments (i.e., cognitive tests or MRI scans alone). Importantly, MTM generalizes successfully from research cohort to real-world clinical data from memory clinic patients with missing data, enhancing the clinical utility of our approach. Thus, our multimodal trajectory modeling approach provides a cost-effective and non-invasive tool for early dementia prediction without labeled data (i.e., clinical diagnosis) with strong potential for translation to clinical practice.