Cohort-Aware Agents for Individualized Lung Cancer Risk Prediction Using a Retrieval-Augmented Model Selection Framework

TL;DR

This paper introduces a personalized lung cancer risk prediction system that dynamically selects the best model for each patient by combining cohort retrieval with reasoning via large language models, improving individual risk assessment accuracy.

Contribution

It presents a novel retrieval-augmented framework that enables cohort-aware, individualized model selection for lung cancer risk prediction using multi-modal data and LLM reasoning.

Findings

Effective cohort retrieval using FAISS improves model relevance.

LLM-based reasoning enhances personalized model selection.

Framework demonstrates potential for real-world clinical application.

Abstract

Accurate lung cancer risk prediction remains challenging due to substantial variability across patient populations and clinical settings -- no single model performs best for all cohorts. To address this, we propose a personalized lung cancer risk prediction agent that dynamically selects the most appropriate model for each patient by combining cohort-specific knowledge with modern retrieval and reasoning techniques. Given a patient's CT scan and structured metadata -- including demographic, clinical, and nodule-level features -- the agent first performs cohort retrieval using FAISS-based similarity search across nine diverse real-world cohorts to identify the most relevant patient population from a multi-institutional database. Second, a Large Language Model (LLM) is prompted with the retrieved cohort and its associated performance metrics to recommend the optimal prediction algorithm from a pool of eight representative models, including classical linear risk models (e.g., Mayo, Brock), temporally-aware models (e.g., TD-VIT, DLSTM), and multi-modal computer vision-based approaches (e.g., Liao, Sybil, DLS, DLI). This two-stage agent pipeline -- retrieval via FAISS and reasoning via LLM -- enables dynamic, cohort-aware risk prediction personalized to each patient's profile. Building on this architecture, the agent supports flexible and cohort-driven model selection across diverse clinical populations, offering a practical path toward individualized risk assessment in real-world lung cancer screening.