Lessons Learned from Designing an AI-Enabled Diagnosis Tool for Pathologists
This work addresses the problem of bridging AI and physician workflows in digital pathology, but it is incremental as it focuses on prototyping and lessons learned rather than a full-scale solution.
The study tackled the challenge of integrating AI into pathologists' diagnostic workflows by prototyping Impetus, a tool that uses AI to assist in tumor detection from histological slides, based on observations from a study with eight pathologists.
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.