Lessons Learned from Designing an AI-Enabled Diagnosis Tool for Pathologists

TL;DR

This paper discusses the development and evaluation of Impetus, an AI-assisted diagnostic tool for pathologists, highlighting lessons learned from a study involving eight professionals to improve human-AI collaboration in pathology.

Contribution

It introduces collaborative techniques and a prototype AI tool for pathology diagnosis, providing insights into effective human-AI integration in medical workflows.

Findings

AI can assist pathologists in tumor detection from histological slides.

Human-AI collaboration requires careful design to account for AI limitations.

Lessons learned inform future development of human-centered medical AI systems.

Abstract

Despite the promises of data-driven artificial intelligence (AI), little is known about how we can bridge the gulf between traditional physician-driven diagnosis and a plausible future of medicine automated by AI. Specifically, how can we involve AI usefully in physicians' diagnosis workflow given that most AI is still nascent and error-prone (e.g., in digital pathology)? To explore this question, we first propose a series of collaborative techniques to engage human pathologists with AI given AI's capabilities and limitations, based on which we prototype Impetus - a tool where an AI takes various degrees of initiatives to provide various forms of assistance to a pathologist in detecting tumors from histological slides. We summarize observations and lessons learned from a study with eight pathologists and discuss recommendations for future work on human-centered medical AI systems.