Modeling Bounded Rationality in Drug Shortage Pharmacists Using Attention-Guided Dynamic Decomposition

2026-05-13

AI Summary

This study addresses the challenge hospital pharmacists face in achieving globally optimal decisions under high-risk, uncertain, and time-constrained conditions caused by drug shortages. The authors propose a bounded rationality decision-making framework inspired by pharmacists’ attention mechanisms, which innovatively partitions pharmaceuticals dynamically into a high-cost reasoning subset and a low-cost monitoring subset. Rather than optimizing specific actions, the framework prioritizes the allocation of cognitive resources. It integrates expert-derived attention weights with a reinforcement learning–driven adaptive mechanism through a collaborative simulation involving an Expert Agent and a Learner Agent. Experimental results demonstrate that the approach maintains stable performance across varying time horizons without requiring full state-space reasoning, significantly reducing decision complexity and offering a lightweight satisficing paradigm suitable for resource-constrained environments.

Abstract

Hospital pharmacists make high-stakes decisions to mitigate drug shortages under uncertainty, time pressure, and patient risk. Interviews revealed that pharmacists focus attention on a small subset of drugs, limiting cognitive effort to the most urgent cases. Motivated by these findings, we formalize a bounded-rational, attention-guided decision framework that dynamically decomposes drugs into a subset for high-cost reasoning and a complementary subset for low-cost monitoring. We develop two agents: an Expert Agent that applies attention weights derived from pharmacist interviews, and a Learner Agent that adapts attention allocation over time through experience. Across simulated scenarios spanning short to long horizons, we show that attention-guided planning supports stable decision-making without complete state reasoning. These results suggest that a primary decision is not what action to take, but where to allocate cognitive effort, and that attention-guided, satisficing strategies can reduce problem complexity while maintaining stable performance.

Problem

• bounded rationality
• drug shortage
• attention allocation
• cognitive effort
• decision-making

Innovation

• bounded rationality
• attention-guided decomposition
• dynamic decision-making
• cognitive effort allocation
• satisficing strategy