Predicting time-to-conversion for dementia of Alzheimer's type using multi-modal deep survival analysis

• Published in: Neurobiology of aging Vol. 121; pp. 139 - 156
• Main Authors: Mirabnahrazam, Ghazal, Ma, Da, Beaulac, Cédric, Lee, Sieun, Popuri, Karteek, Lee, Hyunwoo, Cao, Jiguo, Galvin, James E, Wang, Lei, Beg, Mirza Faisal
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.01.2023
• Subjects: Alzheimer Disease - diagnostic imaging; Alzheimer Disease - genetics; Alzheimer's disease; Cognitive Dysfunction - diagnosis; Cognitive Dysfunction - genetics; Deep learning; Disease Progression; Early detection; Humans; Magnetic Resonance Imaging - methods; Multi-modal data; Neuroimage genomics; Neuroimaging - methods; Survival Analysis; Deep learning; Survival analysis; Multi-modal data; Neuroimage genomics; Alzheimer's disease; Early detection
• ISSN: 0197-4580; 1558-1497; 1558-1497
• DOI: 10.1016/j.neurobiolaging.2022.10.005

Dementia of Alzheimer's Type (DAT) is a complex disorder influenced by numerous factors, and it is difficult to predict individual progression trajectory from normal or mildly impaired cognition to DAT. An in-depth examination of multiple modalities of data may yield an accurate estimate of time-to-conversion to DAT for preclinical subjects at various stages of disease development. We used a deep-learning model designed for survival analyses to predict subjects’ time-to-conversion to DAT using the baseline data of 401 subjects with 63 features from MRI, genetic, and CDC (Cognitive tests, Demographic, and CSF) data in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our study demonstrated that CDC data outperform genetic or MRI data in predicting DAT time-to-conversion for subjects with Mild Cognitive Impairment (MCI). On the other hand, genetic data provided the most predictive power for subjects with Normal Cognition (NC) at the time of the visit. Furthermore, combining MRI and genetic features improved the time-to-event prediction over using either modality alone. Finally, adding CDC to any combination of features only worked as well as using only the CDC features.