Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis

arXiv:2309.12368v2 Announce Type: replace-cross
Abstract: Today's AI systems for medical decision support often succeed on benchmark datasets in research papers but fail in real-world deployment. This work focuses on the decision making of sepsis, an acute life-threatening systematic infection that requires an early diagnosis with high uncertainty from the clinician. Our aim is to explore the design requirements for AI systems that can support clinical experts in making better decisions for the early diagnosis of sepsis. The study begins with …

abstract ai collaboration ai systems arxiv benchmark case case study collaboration cs.ai cs.hc cs.lg datasets decision decision making decision support deployment diagnosis human infection life making medical papers research research papers study support systems type work world