Forecasting Disease Trajectories in Alzheimer's Disease Using Deep\n Learning

2018/07/06 by Bryan Lim, Mihaela van der Schaar, Lim, Bryan +1
Computer Science · Environmental Science · Medicine · #Dementia and Cognitive Impairment Research #FOS: Computer and information sciences #Health, Environment, Cognitive Aging #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.1807.03159

openalex publication_date 2018/07/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Joint models for longitudinal and time-to-event data are commonly used in\nlongitudinal studies to forecast disease trajectories over time. Despite the\nmany advantages of joint modeling, the standard forms suffer from limitations\nthat arise from a fixed model specification and computational difficulties when\napplied to large datasets. We adopt a deep learning approach to address these\nlimitations, enhancing existing methods with the flexibility and scalability of\ndeep neural networks while retaining the benefits of joint modeling. Using data\nfrom the Alzheimer's Disease Neuroimaging Institute, we show improvements in\nperformance and scalability compared to traditional methods.\n

Related

• DeepAD: A Robust Deep Learning Model of Alzheimer's Disease Progression for Real-World Clinical Applications
• Deep Recurrent Model for Individualized Prediction of Alzheimer's\n Disease Progression
• Artificial Intelligence for Personalized Prediction of Alzheimer's Disease Progression: A Survey of Methods, Data Challenges, and Future Directions
• Generative forecasting of brain activity enhances Alzheimer's classification and interpretation
• FLARe: Forecasting by Learning Anticipated Representations