AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents

TL;DR

AutoCT is a novel framework that combines large language models with classical machine learning to predict clinical trial outcomes accurately, interpretably, and efficiently without human intervention.

Contribution

It introduces AutoCT, which autonomously generates and refines features using LLMs and Monte Carlo Tree Search, improving prediction performance and interpretability in clinical trial prediction.

Findings

AutoCT matches or exceeds state-of-the-art performance.

AutoCT requires fewer self-refinement iterations.

AutoCT offers scalable and interpretable predictions.

Abstract

Clinical trials are critical for advancing medical treatments but remain prohibitively expensive and time-consuming. Accurate prediction of clinical trial outcomes can significantly reduce research and development costs and accelerate drug discovery. While recent deep learning models have shown promise by leveraging unstructured data, their black-box nature, lack of interpretability, and vulnerability to label leakage limit their practical use in high-stakes biomedical contexts. In this work, we propose AutoCT, a novel framework that combines the reasoning capabilities of large language models with the explainability of classical machine learning. AutoCT autonomously generates, evaluates, and refines tabular features based on public information without human input. Our method uses Monte Carlo Tree Search to iteratively optimize predictive performance. Experimental results show that AutoCT performs on par with or better than SOTA methods on clinical trial prediction tasks within only a limited number of self-refinement iterations, establishing a new paradigm for scalable, interpretable, and cost-efficient clinical trial prediction.