Can Domain Experts Rely on AI Appropriately? A Case Study on AI-Assisted Prostate Cancer MRI Diagnosis

TL;DR

This study investigates how radiologists interact with AI in prostate cancer MRI diagnosis, revealing that human-AI teams outperform humans alone but still underperform compared to AI, with feedback having limited impact on reliance.

Contribution

The paper provides an in-depth experimental analysis of human-AI collaboration in medical diagnosis, highlighting the effects of performance feedback and decision workflows on trust and reliance.

Findings

Human-AI teams outperform humans alone in diagnosis accuracy.

Clinicians tend to under-rely on AI predictions, limiting team performance.

Performance feedback does not significantly enhance human-AI team accuracy.

Abstract

Despite the growing interest in human-AI decision making, experimental studies with domain experts remain rare, largely due to the complexity of working with domain experts and the challenges in setting up realistic experiments. In this work, we conduct an in-depth collaboration with radiologists in prostate cancer diagnosis based on MRI images. Building on existing tools for teaching prostate cancer diagnosis, we develop an interface and conduct two experiments to study how AI assistance and performance feedback shape the decision making of domain experts. In Study 1, clinicians were asked to provide an initial diagnosis (human), then view the AI's prediction, and subsequently finalize their decision (human-AI team). In Study 2 (after a memory wash-out period), the same participants first received aggregated performance statistics from Study 1, specifically their own performance, the AI's performance, and their human-AI team performance, and then directly viewed the AI's prediction before making their diagnosis (i.e., no independent initial diagnosis). These two workflows represent realistic ways that clinical AI tools might be used in practice, where the second study simulates a scenario where doctors can adjust their reliance and trust on AI based on prior performance feedback. Our findings show that, while human-AI teams consistently outperform humans alone, they still underperform the AI due to under-reliance, similar to prior studies with crowdworkers. Providing clinicians with performance feedback did not significantly improve the performance of human-AI teams, although showing AI decisions in advance nudges people to follow AI more. Meanwhile, we observe that the ensemble of human-AI teams can outperform AI alone, suggesting promising directions for human-AI collaboration.