Subject-Adaptive Sparse Linear Models for Interpretable Personalized Health Prediction from Multimodal Lifelog Data
This work addresses the need for interpretable and personalized health prediction models for clinicians and practitioners, though it is incremental as it builds on existing linear and ensemble methods.
The paper tackled the problem of predicting personalized health outcomes from multimodal lifelog data by proposing the Subject-Adaptive Sparse Linear (SASL) framework, which achieved predictive performance comparable to black-box methods with significantly fewer parameters and greater interpretability on the CH-2025 dataset with about 450 daily observations from ten subjects.
Improved prediction of personalized health outcomes -- such as sleep quality and stress -- from multimodal lifelog data could have meaningful clinical and practical implications. However, state-of-the-art models, primarily deep neural networks and gradient-boosted ensembles, sacrifice interpretability and fail to adequately address the significant inter-individual variability inherent in lifelog data. To overcome these challenges, we propose the Subject-Adaptive Sparse Linear (SASL) framework, an interpretable modeling approach explicitly designed for personalized health prediction. SASL integrates ordinary least squares regression with subject-specific interactions, systematically distinguishing global from individual-level effects. We employ an iterative backward feature elimination method based on nested $F$-tests to construct a sparse and statistically robust model. Additionally, recognizing that health outcomes often represent discretized versions of continuous processes, we develop a regression-then-thresholding approach specifically designed to maximize macro-averaged F1 scores for ordinal targets. For intrinsically challenging predictions, SASL selectively incorporates outputs from compact LightGBM models through confidence-based gating, enhancing accuracy without compromising interpretability. Evaluations conducted on the CH-2025 dataset -- which comprises roughly 450 daily observations from ten subjects -- demonstrate that the hybrid SASL-LightGBM framework achieves predictive performance comparable to that of sophisticated black-box methods, but with significantly fewer parameters and substantially greater transparency, thus providing clear and actionable insights for clinicians and practitioners.