Interpretable machine learning for high-dimensional trajectories of aging health

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. Author summaryAging is the process of age-dependent functional decline of biological organisms. This process is high-dimensional, involving changes in all aspects of organism functioning. The progression of aging is often simplified with low-dimensional summary measures to describe the overall health state. While these summary measures of aging can be used predict mortality and are correlated with adverse health outcomes, we demonstrate that the prediction of individual aging health outcomes cannot be done accurately with these low-dimensional measures, and requires a high-dimensional model. This work presents a machine learning approach to model high-dimensional aging health trajectories and mortality. This approach is made interpretable by inferring a network of pairwise interactions between the health variables, describing the interactions used by the model to make predictions and suggesting plausible biological mechanisms.