A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure

Abstract

For many complex diseases, there is a wide variety of ways in which an individual can manifest the disease. The challenge of personalized medicine is to develop tools that can accurately predict the trajectory of an individual's disease, which can in turn enable clinicians to optimize treatments. We represent an individual's disease trajectory as a continuous-valued continuous-time function describing the severity of the disease over time. We propose a hierarchical latent variable model that individualizes predictions of disease trajectories. This model shares statistical strength across observations at different resolutions--the population, subpopulation and the individual level. We describe an algorithm for learning population and subpopulation parameters offline, and an online procedure for dynamically learning individual-specific parameters. Finally, we validate our model on the task of predicting the course of interstitial lung disease, a leading cause of death among patients with the autoimmune disease scleroderma. We compare our approach against state-of-the-art and demonstrate significant improvements in predictive accuracy.

Appeared in Neural Information Processing Systems (NIPS) 2015

Cited by in corpus (25)

• A Review of Challenges and Opportunities in Machine Learning for Health
• Artificial Intelligence for Social Good
• Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
• DPVis: Visual Analytics with Hidden Markov Models for Disease Progression Pathways
• Product Kernel Interpolation for Scalable Gaussian Processes
• Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care
• Differentially Private Data Generative Models
• A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves
• Interpretable machine learning for high-dimensional trajectories of aging health
• Sparse Multi-Output Gaussian Processes for Medical Time Series Prediction
• The potential for complex computational models of aging
• A Hidden Absorbing Semi-Markov Model for Informatively Censored Temporal Data: Learning and Inference
• Personalized Risk Scoring for Critical Care Patients using Mixtures of Gaussian Process Experts
• Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization
• Forecasting Individualized Disease Trajectories using Interpretable Deep Learning
• A Comprehensive Evaluation of Multi-task Learning and Multi-task Pre-training on EHR Time-series Data
• Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics
• Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare
• Disease Trajectory Maps
• Personalized Risk Scoring for Critical Care Prognosis using Mixtures of Gaussian Processes
• A latent topic model for mining heterogenous non-randomly missing electronic health records data
• Modeling Treatment Delays for Patients using Feature Label Pairs in a Time Series
• Errors-in-variables Modeling of Personalized Treatment-Response Trajectories
• Modeling trajectories of mental health: challenges and opportunities
• Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation