Evaluating representation embeddings from LLMs and time-series foundation models for wearable accelerometer-based health prediction

On NHANES accelerometer data, compares entropy-based features, pretrained LLM embeddings and TSFM embeddings for overweight, lipids, glucose, arthritis and cancers. Simple entropy features match or slightly beat embeddings on all endpoints; LLM embeddings add only ΔAUC ≈0.01–0.05; TSFM embeddings add minimal value across sequence lengths; prompt-based LLM reasoning is worst (AUC ≈0.56–0.65).

• Form factor: wrist (NHANES)

Wearable accelerometer data capture rich behavioral signals relevant for personalized health, yet the comparative evidence on modern representation-learning approaches remains limited. Using accelerometer data from the National Health and Nutrition Examination Survey (NHANES), we evaluated three representation families for predicting multiple clinical outcomes: simple entropy-based features, pretrained large-language-model (LLM) embeddings, and time-series foundation model embeddings. Outcomes included overweight status, lipid biomarkers, glucose, arthritis, and cancers. Across all endpoints, entropy-based features consistently performed comparably to, and often slightly better than, embedding approaches. LLM-derived embeddings offered only marginal improvements (ΔAUC≈0.01-0.05), and time-series foundation model embeddings provided minimal value across varying sequence lengths. Prompt-based LLM reasoning performed worst (AUC≈0.56-0.65), demonstrating limited ability to infer quantitative physiological states from structured text. These results highlight the strength of simple variability features and underscore the need for domain-aligned pretraining in future time-series foundation models for health sensing.

Verbatim from Europe PMC (opens in a new tab) · Abstract via Europe PMC; © the authors/publisher

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.