Interpretable machine learning for high-dimensional trajectories of aging health

TL;DR

This paper introduces DJIN, an interpretable, scalable machine learning model that predicts individual aging health trajectories and survival, revealing physiological connections and enabling realistic simulations from high-dimensional longitudinal data.

Contribution

The paper presents DJIN, a novel interpretable interaction network model that accurately predicts aging health trajectories and survival, and uncovers physiological relationships in high-dimensional data.

Findings

DJIN outperforms linear models in predicting health outcomes and survival.

The model identifies plausible physiological connections between health variables.

It can generate realistic aging simulations and impute missing data.

Abstract

We have built a computational model for individual aging trajectories of health and survival, which contains physical, functional, and biological variables, and is conditioned on demographic, lifestyle, and medical background information. We combine techniques of modern machine learning with an interpretable interaction network, where health variables are coupled by explicit pair-wise interactions within a stochastic dynamical system. Our dynamic joint interpretable network (DJIN) model is scalable to large longitudinal data sets, is predictive of individual high-dimensional health trajectories and survival from baseline health states, and infers an interpretable network of directed interactions between the health variables. The network identifies plausible physiological connections between health variables as well as clusters of strongly connected health variables. We use English Longitudinal Study of Aging (ELSA) data to train our model and show that it performs better than multiple dedicated linear models for health outcomes and survival. We compare our model with flexible lower-dimensional latent-space models to explore the dimensionality required to accurately model aging health outcomes. Our DJIN model can be used to generate synthetic individuals that age realistically, to impute missing data, and to simulate future aging outcomes given arbitrary initial health states.