Patient foundation model for risk stratification in low-risk overweight patients

TL;DR

This paper introduces PatientTPP, a neural temporal point process model trained on extensive clinical data to improve risk stratification and outcome prediction in overweight patients, aiding personalized care and cost management.

Contribution

The paper presents PatientTPP, a novel TPP-based model that incorporates static and numeric features with clinical knowledge, enhancing risk prediction in overweight individuals.

Findings

Outperformed BMI in predicting future cardiovascular costs.

Supported classification of obesity-related outcomes in low-risk patients.

Provided interpretable patient representations for risk modeling.

Abstract

Accurate risk stratification in patients with overweight or obesity is critical for guiding preventive care and allocating high-cost therapies such as GLP-1 receptor agonists. We present PatientTPP, a neural temporal point process (TPP) model trained on over 500,000 real-world clinical trajectories to learn patient representations from sequences of diagnoses, labs, and medications. We extend existing TPP modeling approaches to include static and numeric features and incorporate clinical knowledge for event encoding. PatientTPP representations support downstream prediction tasks, including classification of obesity-associated outcomes in low-risk individuals, even for events not explicitly modeled during training. In health economic evaluation, PatientTPP outperformed body mass index in stratifying patients by future cardiovascular-related healthcare costs, identifying higher-risk patients more efficiently. By modeling both the type and timing of clinical events, PatientTPP offers an interpretable, general-purpose foundation for patient risk modeling with direct applications to obesity-related care and cost targeting.