ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders

2025-04-24

AI Summary

Excessive laboratory test ordering in intensive care units (ICUs) leads to resource waste and increased clinical burden. Method: This paper proposes an interpretable offline causal bandit policy learning framework. It innovatively incorporates predictive clinical states as privileged information into offline reinforcement learning, jointly leveraging real-time observations and future state predictions; the reward function is designed in accordance with clinical guidelines. Policy optimization is achieved via privileged information distillation and interpretable policy function modeling, enabling knowledge-driven decision-making. Contributions: (1) First integration of privileged information into offline causal bandit learning; (2) Simultaneous emphasis on policy interpretability and clinical adoptability. Results: Evaluated on real-world offline ICU data, the method significantly reduces testing frequency and associated costs while achieving zero critical missed detections—outperforming both clinicians’ actual ordering practices and existing baseline methods.

Technology Category

• Machine Learning: Online Learning & Bandits
• Reasoning under Uncertainty: Causality
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• 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

Ordering a minimal subset of lab tests for patients in the intensive care unit (ICU) can be challenging. Care teams must balance between ensuring the availability of the right information and reducing the clinical burden and costs associated with each lab test order. Most in-patient settings experience frequent over-ordering of lab tests, but are now aiming to reduce this burden on both hospital resources and the environment. This paper develops a novel method that combines off-policy learning with privileged information to identify the optimal set of ICU lab tests to order. Our approach, EXplainable Off-policy learning with Side Information for ICU blood Test Orders (ExOSITO) creates an interpretable assistive tool for clinicians to order lab tests by considering both the observed and predicted future status of each patient. We pose this problem as a causal bandit trained using offline data and a reward function derived from clinically-approved rules; we introduce a novel learning framework that integrates clinical knowledge with observational data to bridge the gap between the optimal and logging policies. The learned policy function provides interpretable clinical information and reduces costs without omitting any vital lab orders, outperforming both a physician's policy and prior approaches to this practical problem.

Problem

• Optimizing ICU lab test orders to reduce costs and clinical burden
• Balancing information needs with over-ordering of lab tests
• Developing interpretable AI for clinical decision-making in test ordering

Innovation

• Combines off-policy learning with privileged information
• Uses causal bandit trained with offline clinical data
• Provides interpretable clinical decision support tool