LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data

2026-07-01

AI Summary

This work addresses the challenge of jointly inferring the structure and parameter distribution of ordinary differential equations (ODEs) in small-sample settings such as rare diseases, where individual-level data are scarce, noisy, and subject to privacy constraints. The authors propose AgentODE, a novel framework that, for the first time, operates solely on population-level summary statistics. It leverages a large language model to generate candidate ODE structures and integrates tool-augmented reasoning agents with Bayesian inference to iteratively refine parameter distributions within a diagnose-and-update loop. The approach balances mechanistic interpretability with privacy preservation, successfully recovering functionally consistent ODE structures across multiple benchmarks and real-world RDEB clinical data (46 patients, 231 observations), outperforming baseline methods that rely on individual patient data.

Abstract

Mechanistic modeling via ordinary differential equations (ODEs) provides interpretable descriptions of complex dynamics and enables inference of underlying mechanisms, which is particularly valuable in clinical settings. However, in rare diseases, both the structure and parameters of the model are typically unknown, while individual-level data is scarce, noisy, heterogeneous, and subject to privacy constraints. In such settings, population-level summary statistics provide a practical privacy-preserving data representation, while capturing heterogeneity further requires modeling parameters as distributions rather than fixed values. Yet no existing method jointly discovers ODE structure and refines parameter distributions solely from summary statistics. We present AgentODE, an end-to-end framework that addresses this gap. An LLM proposes candidate ODE structures, while a tool-augmented inference agent iteratively refines parameter distributions through a diagnosis--update loop, operating on population-level summary statistics alone. We evaluate AgentODE on three benchmark problems across different fields and two clinical datasets, including the rare disease recessive dystrophic epidermolysis bullosa (RDEB), with only 231 observations across 46 patients. AgentODE recovers functionally consistent ODE structures across all settings, and experiments on RDEB demonstrates that in sparse and noisy data settings reasoning from summary statistics promotes mechanistically principled structure discovery, whereas baselines with individual-level data access recover implausible structures despite better predictive performance. AgentODE opens new possibilities for mechanistic modeling of rare diseases directly from population-level summary statistics, where data scarcity and privacy constraints have traditionally limited such analyses.

Problem

• ODE discovery
• parameter inference
• rare diseases
• summary statistics
• mechanistic modeling

Innovation

• LLM-guided discovery
• ODE structure identification
• parameter distribution inference
• summary statistics
• rare disease modeling