LLM-Augmented Computational Phenotyping of Long Covid

TL;DR

This paper introduces 'Grace Cycle,' an LLM-augmented framework for identifying meaningful subphenotypes in Long Covid patients using longitudinal data, revealing three distinct clinical phenotypes with strong statistical support.

Contribution

The study presents a novel, disease-agnostic framework integrating large language models into phenotypic discovery from complex longitudinal data.

Findings

Identified three distinct Long Covid phenotypes: Protected, Responder, Refractory.

Demonstrated significant separation in symptom severity and disease burden among phenotypes.

Framework is generalizable to other complex diseases.

Abstract

Phenotypic characterization is essential for understanding heterogeneity in chronic diseases and for guiding personalized interventions. Long COVID, a complex and persistent condition, yet its clinical subphenotypes remain poorly understood. In this work, we propose an LLM-augmented computational phenotyping framework ``Grace Cycle'' that iteratively integrates hypothesis generation, evidence extraction, and feature refinement to discover clinically meaningful subgroups from longitudinal patient data. The framework identifies three distinct clinical phenotypes, Protected, Responder, and Refractory, based on 13,511 Long Covid participants. These phenotypes exhibit pronounced separation in peak symptom severity, baseline disease burden, and longitudinal dose-response patterns, with strong statistical support across multiple independent dimensions. This study illustrates how large language models can be integrated into a principled, statistically grounded pipeline for phenotypic screening from complex longitudinal data. Note that the proposed framework is disease-agnostic and offers a general approach for discovering clinically interpretable subphenotypes.