Improving Workflow Integration with xPath: Design and Evaluation of a Human-AI Diagnosis System in Pathology

Recent developments in AI have provided assisting tools to support pathologists’ diagnoses. However, it remains challenging incorporate such into practice; one main concern is AI’s insufficient workflow integration with medical decisions. We observed examination and discovered that the hindering factor integrate its incompatibility workflow. To bridge gap between pathologists AI, we developed a human-AI collaborative diagnosis tool— xPath —that shares similar process of pathologists, which can improve their routine examination. The viability confirmed by technical evaluation work sessions 12 professionals pathology. This identifies addresses challenge incorporating models pathology, offer first-hand knowledge about how HCI researchers side-by-side bring technological advances tasks towards practical applications.