Dynamic Classification of Latent Disease Progression with Auxiliary Surrogate Labels

TL;DR

This paper introduces a novel hybrid model combining generative and discriminative approaches to improve disease progression prediction using surrogate labels and health markers, especially when true disease states are unknown.

Contribution

It develops an adaptive algorithm integrating hidden Markov models with classification models, eliminating the need to model marker distributions, and demonstrates improved accuracy in distinguishing neurological diseases.

Findings

Enhanced prediction accuracy for disease progression.

Effective handling of surrogate labels and missing true states.

Validated improvements on Alzheimer's disease dataset.

Abstract

Disease progression prediction based on patients' evolving health information is challenging when true disease states are unknown due to diagnostic capabilities or high costs. For example, the absence of gold-standard neurological diagnoses hinders distinguishing Alzheimer's disease (AD) from related conditions such as AD-related dementias (ADRDs), including Lewy body dementia (LBD). Combining temporally dependent surrogate labels and health markers may improve disease prediction. However, existing literature models informative surrogate labels and observed variables that reflect the underlying states using purely generative approaches, limiting the ability to predict future states. We propose integrating the conventional hidden Markov model as a generative model with a time-varying discriminative classification model to simultaneously handle potentially misspecified surrogate labels and incorporate important markers of disease progression. We develop an adaptive forward-backward algorithm with subjective labels for estimation, and utilize the modified posterior and Viterbi algorithms to predict the progression of future states or new patients based on objective markers only. Importantly, the adaptation eliminates the need to model the marginal distribution of longitudinal markers, a requirement in traditional algorithms. Asymptotic properties are established, and significant improvement with finite samples is demonstrated via simulation studies. Analysis of the neuropathological dataset of the National Alzheimer's Coordinating Center (NACC) shows much improved accuracy in distinguishing LBD from AD.