LLM-Augmented Computational Phenotyping of Long Covid

• URL: http://arxiv.org/abs/2603.18115v1
• Date: Wed, 18 Mar 2026 15:02:05 GMT
• Title: LLM-Augmented Computational Phenotyping of Long Covid
• Abstract summary: The framework identifies three distinct clinical phenotypes, Protected, Responder, and Refractory, based on 13,511 Long Covid participants.<n>These phenotypes exhibit pronounced separation in peak symptom severity, baseline disease burden, and longitudinal dose-response patterns.<n>This study illustrates how large language models can be integrated into a principled, statistically grounded pipeline for phenotypic screening from complex longitudinal data.
• Score: 17.253602770455927
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling [0.5437050212139087]
  We use large language models (LLMs) as synthetic clinical experts to supervise a variational-autoencoder-based approach.<n>LLMs are queried offline on textual descriptions of patient observations to obtain judgments.
  arXiv  Detail & Related papers  (2026-08-17T12:47:18Z)
• CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association [22.78248640423072]
  CPAgents is an iterative phenotype-Composition framework for cardiovascular Phenome-wide association study (PheWAS)<n>Our system coordinates three agents: (i) an Analyst that identifies statistical pathologies and nominates candidate transformations; (ii) a Proposer that generates constrained, medically and statistically motivated expressions under numerical safety rules; and (iii) a Verifier that evaluates candidates using multi-stage criteria and produces transparent evidence trails.
  arXiv  Detail & Related papers  (2026-06-26T15:20:08Z)
• Multimodal Graph-based Classification of Esophageal Motility Disorders [73.90451172929117]
  Diagnosing esophageal motility disorders pose significant challenges due to the complexity of high-resolution impedance manometry data and variability in clinical interpretation.<n>This work explores the feasibility of a multimodal Machine Learning-based classification approach that combines HRIM recordings with patient-specific information and incorporates a graph-based modeling of esophageal physiology.
  arXiv  Detail & Related papers  (2026-05-13T14:52:12Z)
• LLM-MINE: Large Language Model based Alzheimer's Disease and Related Dementias Phenotypes Mining from Clinical Notes [13.189180222247337]
  We propose a Large Language Model-based phenotype mining framework for automatic extraction of Alzheimer's Disease and Related Dementias phenotypes from clinical notes.<n>Using two expert-defined phenotype lists, we evaluate the extracted phenotypes by examining their statistical significance across cohorts and their utility for unsupervised disease staging.<n>Our results demonstrate that LLM-based phenotype extraction is a promising tool for discovering clinically meaningful ADRD signals from unstructured notes.
  arXiv  Detail & Related papers  (2026-03-14T00:45:23Z)
• Causal Representation Learning from Multimodal Biomedical Observations [57.00712157758845]
  We develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biomedical datasets.<n>Key theoretical contribution is the structural sparsity of causal connections between modalities.<n>Results on a real-world human phenotype dataset are consistent with established biomedical research.
  arXiv  Detail & Related papers  (2024-11-10T16:40:27Z)
• Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling [53.7117640028211]
  We present a geometry-constrained probabilistic modeling treatment to resolve the identified issues. We incorporate a suite of critical geometric properties to impose proper constraints on the layout of constructed embedding space. A spectral graph-theoretic method is devised to estimate the number of potential novel classes.
  arXiv  Detail & Related papers  (2024-03-02T00:56:05Z)
• T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression [82.85825388788567]
  We develop a novel temporal clustering method, T-Phenotype, to discover phenotypes of predictive temporal patterns from labeled time-series data. We show that T-Phenotype achieves the best phenotype discovery performance over all the evaluated baselines.
  arXiv  Detail & Related papers  (2023-02-24T13:30:35Z)
• Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology [57.25098075813054]
  We propose a new framework for gene discovery entitled Un Phenotype Ensembles. It builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations.
  arXiv  Detail & Related papers  (2023-01-07T18:36:44Z)
• Bayesian Networks for the robust and unbiased prediction of depression and its symptoms utilizing speech and multimodal data [65.28160163774274]
  We apply a Bayesian framework to capture the relationships between depression, depression symptoms, and features derived from speech, facial expression and cognitive game data collected at thymia.
  arXiv  Detail & Related papers  (2022-11-09T14:48:13Z)
• A cost-based multi-layer network approach for the discovery of patient phenotypes [2.816539638885011]
  We propose a cost-based layer selector model for detecting phenotypes using a community detection approach. Our goal is to minimize the number of features used to build these phenotypes while preserving its quality. For some post-treatment variables, predictors using phenotypes from COBALT as features outperformed those using phenotypes detected by traditional clustering methods.
  arXiv  Detail & Related papers  (2022-09-19T14:07:10Z)
• Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions [0.6875312133832078]
  We provide a comprehensive review of low-rank approximation-based approaches for computational phenotyping. Recent developments have adapted low-rank data approximation methods by incorporating different constraints and regularizations that facilitate interpretability further.
  arXiv  Detail & Related papers  (2022-09-01T09:47:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.