Timely Clinical Diagnosis through Active Test Selection

2025-10-21

AI Summary

Current clinical diagnostic methods rely on static, fully observed data, failing to model the sequential, resource-constrained, and dynamic reasoning inherent in real-world practice. To address this, we propose ACTMED—a novel framework that integrates Bayesian experimental design (BED) with large language models (LLMs) for diagnostic decision-making. Unlike conventional approaches, ACTMED requires no structured training: LLMs implicitly model patient state distributions and perform belief updates, while BED actively selects the next most informative diagnostic test based on expected information gain. This enables interpretable, adaptive diagnosis with continuous clinician oversight. Evaluated on real-world datasets, ACTMED achieves significant improvements—+8.2% in diagnostic accuracy and −31.5% reduction in average tests performed—while enhancing interpretability and cross-scenario generalization. ACTMED establishes a new paradigm for efficient, trustworthy, AI-augmented diagnosis in resource-limited settings.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Active Learning
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

There is growing interest in using machine learning (ML) to support clinical diag- nosis, but most approaches rely on static, fully observed datasets and fail to reflect the sequential, resource-aware reasoning clinicians use in practice. Diagnosis remains complex and error prone, especially in high-pressure or resource-limited settings, underscoring the need for frameworks that help clinicians make timely and cost-effective decisions. We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design), a diagnostic framework that integrates Bayesian Experimental Design (BED) with large language models (LLMs) to better emulate real-world diagnostic reasoning. At each step, ACTMED selects the test expected to yield the greatest reduction in diagnostic uncertainty for a given patient. LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data. Clinicians can remain in the loop; reviewing test suggestions, interpreting intermediate outputs, and applying clinical judgment throughout. We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use. This represents a step to- ward transparent, adaptive, and clinician-aligned diagnostic systems that generalize across settings with reduced reliance on domain-specific data.

Problem

• Optimizing sequential test selection for clinical diagnosis
• Reducing diagnostic uncertainty with adaptive AI frameworks
• Improving resource efficiency in clinical decision-making processes

Innovation

• Integrates Bayesian design with large language models
• Selects tests to reduce diagnostic uncertainty adaptively
• Uses LLMs as flexible simulators without structured data