Static Algorithm, Evolving Epidemic: Understanding the Potential of Human-AI Risk Assessment to Support Regional Overdose Prevention

2025-02-14

AI Summary

Local public health departments lack dynamic, evidence-based risk assessment to guide resource allocation during the opioid overdose epidemic. Method: This study proposes a “human-AI co-adaptation” framework, wherein AI-driven risk models are continuously calibrated in response to evolving regional epidemic dynamics. We developed an integrated machine learning prediction model and a multi-source data visualization interface, validated through expert interviews and usability assessments across three health departments. Contribution/Results: To our knowledge, this is the first empirical evaluation of static AI risk models within real-world, dynamically changing epidemic contexts. The study confirms the feasibility of human-AI collaboration in public health decision-making while identifying critical limitations—including poor model generalizability, insufficient data timeliness, and inadequate geographic representativeness. These findings establish a methodological foundation and actionable implementation pathway for deploying AI to enhance public health emergency response.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Drug overdose deaths, including those due to prescription opioids, represent a critical public health issue in the United States and worldwide. Artificial intelligence (AI) approaches have been developed and deployed to help prescribers assess a patient's risk for overdose-related death, but it is unknown whether public health experts can leverage similar predictions to make local resource allocation decisions more effectively. In this work, we evaluated how AI-based overdose risk assessment could be used to inform local public health decisions using a working prototype system. Experts from three health departments, of varying locations and sizes with respect to staff and population served, were receptive to the potential benefits of algorithmic risk prediction and of using AI-augmented visualization to connect across data sources. However, they also expressed concerns about whether the risk prediction model's formulation and underlying data would match the state of the overdose epidemic as it evolved in their specific locations. Our findings extend those of other studies on algorithmic systems in the public sector, and they present opportunities for future human-AI collaborative tools to support decision-making in local, time-varying contexts.

Problem

• AI-based overdose risk assessment
• Local public health decisions
• Time-varying epidemic contexts

Innovation

• AI-based overdose risk assessment
• AI-augmented visualization tools
• local public health decision support