Introduction
Clinical machine learning (ML) has the potential to support high-stakes medical decision-making, but its reliability is often constrained by scarce, heterogeneous, and temporal complexity. Developing effective ML pipelines for such data remains time-consuming and error-prone, while existing automated machine learning (AutoML) systems only partially address this challenge because they largely rely on brute-force search over predefined spaces and lack explicit reasoning and memory. We propose DoctorAgents, an agentic AI framework that autonomously constructs and optimizes end-to-end ML pipelines through specialized large language model (LLM) agents for generation, validation, and refinement. DoctorAgents backpropagates natural-language feedback through textual gradient descent to perform targeted updates without exhaustive search.
Experimental Results
Experiments across diverse clinical tasks show that DoctorAgents consistently outperforms established AutoML baselines while producing more interpretable task-specific representations. Blogger's Review: DoctorAgents framework significantly improves the efficiency and interpretability of AutoML on small clinical temporal data by introducing large language model agents, which is expected to accelerate the application of clinical machine learning.