LLM agent teams show strengths and limits for healthcare decision optimization
On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management
Artificial IntelligenceMultiagent Systems
Summary
Healthcare decisions often weigh factors like patient wait times, staff workload, and costs, but figuring out how much each matters is hard. The authors studied how teams of AI language agents can represent different viewpoints to provide these weights. They found that the agents’ opinions change depending on how they interact and what information they get, and that the method of combining opinions affects results. Their work shows that AI-generated preferences need careful checking before using them to make healthcare scheduling decisions.
What this means in practice
- •For hospital operations teams: Use LLM agent teams to generate and audit stakeholder preferences for scheduling decisions that balance wait times, workloads, and costs.
- •For healthcare software developers: Incorporate models that account for uncertainty in AI-generated preferences to improve reliability of multi-criteria optimization tools.
Tested on simulated data.
Authors
Marco Boresta, Tommaso Giovannelli, Sepehr Namirad, Giulia Riccardi
Abstract
Multi-criteria models for healthcare operations need weights that express how stakeholders trade off patient waiting time, provider workload, and operating cost, but these weights are difficult to quantify. Teams of large language model (LLM) agents, each prompted to represent a stakeholder, have been used to supply them. We propose a framework for assessing the reliability of LLM-generated preferences as inputs to multi-objective optimization and quantifying how their uncertainty affects decisions. We study explicit preferences by asking agents to rate the importance of the criteria in an outpatient appointment scheduling problem, and implicit preferences by inferring trade-offs from the agents' pairwise choices between emergency department configurations. The computational experiments show that the explicit preferences respond to the clinic's operating conditions and differ across roles, but deliberation among the agents can erase these differences, whereas simple averaging preserves them. The pairwise choices used to reveal the agents' implicit preferences depend largely on which option is presented first, and we find limited evidence that a statistical model using contextual information alongside presentation order predicts the agents' choices on new comparison pairs better than a model using presentation order alone. We then formulate robust weighted-sum optimization models to account for preference uncertainty. In most cases, these models select different schedules or configurations from those obtained using average preference weights. These results indicate that LLM-generated preferences need an audit of this kind before they are used as optimization weights in healthcare decision support.