CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association

2026-06-26

AI Summary

Existing studies linking cardiac imaging phenotypes to disease predominantly rely on predefined univariate or handcrafted features, which struggle to capture nonlinear effects and cross-phenotype interactions. To address this limitation, this work proposes CPAgents, a novel framework that introduces a multi-agent collaborative mechanism to automatically construct composite phenotypes—such as ratios and interaction terms—that are both clinically meaningful and statistically robust. The framework employs rule-constrained expression generation, multi-stage validation, numerical safety strategies, and interpretability assessment. Evaluated on a large-scale cardiac imaging cohort, the discovered phenotypes achieved top performance in 56 out of 72 disease discrimination tasks, significantly outperforming baseline methods across all nine clinical disease categories, thereby transcending the constraints of traditional expert-driven paradigms.

Abstract

Identifying robust associations between cardiac imaging phenotypes and clinical diseases is fundamental to population-scale cardiovascular research and reliable risk stratification. However, current phenome-wide association studies rely on pre-defined, single-variable phenotypes or expert-crafted features, which limits their ability to capture clinically meaningful non-linear effects and cross-phenotype interactions. To address this, we propose CPAgents, an iterative phenotype-Composition framework for cardiovascular Phenome-wide association study (PheWAS) that automatically constructs and validates interpretable composite phenotypes (e.g., polynomial, ratio, and interaction forms) from base imaging features. Specifically, 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 for accepted phenotypes. Evaluated on a population-scale cardiac imaging cohort, the discovered composite phenotypes markedly improve disease discrimination: across 72 classifier-disease-metric combinations, our variants achieve the top rank in 56 cases versus 18 for baselines, with gains observed across all nine clinical disease categories. Our framework yields compact, clinically interpretable phenotype formulas with transparent evidence trails, enabling scalable discovery of stronger phenotype-disease associations beyond expert-driven feature selection.

Problem

• cardiac imaging phenotypes
• phenome-wide association studies
• composite phenotypes
• non-linear effects
• cross-phenotype interactions

Innovation

• agentic framework
• composite phenotype
• cardiovascular PheWAS
• interpretable AI
• automated feature construction