Majority voting of doctors improves appropriateness of AI reliance in pathology

• Published in: International journal of human-computer studies 2024-10, Vol.190, p.103315, Article 103315
• Main Authors: Gu, Hongyan, Yang, Chunxu, Magaki, Shino, Zarrin-Khameh, Neda, Lakis, Nelli S., Cobos, Inma, Khanlou, Negar, Zhang, Xinhai R., Assi, Jasmeet, Byers, Joshua T., Hamza, Ameer, Han, Karam, Meyer, Anders, Mirbaha, Hilda, Mohila, Carrie A., Stevens, Todd M., Stone, Sara L., Yan, Wenzhong, Haeri, Mohammad, Chen, Xiang ‘Anthony’
• Format: Article
• Language: English
• Subjects: Appropriate reliance; Artificial intelligence; Majority voting; Pathology
• ISSN: 1071-5819; 1095-9300
• DOI: 10.1016/j.ijhcs.2024.103315

As Artificial Intelligence (AI) making advancements in medical decision-making, there is a growing need to ensure doctors develop appropriate reliance on AI to avoid adverse outcomes. However, existing methods in enabling appropriate AI reliance might encounter challenges while being applied in the medical domain. With this regard, this work employs and provides the validation of an alternative approach – majority voting – to facilitate appropriate reliance on AI in medical decision-making. This is achieved by a multi-institutional user study involving 32 medical professionals with various backgrounds, focusing on the pathology task of visually detecting a pattern, mitoses, in tumor images. Here, the majority voting process was conducted by synthesizing decisions under AI assistance from a group of pathology doctors (pathologists). Two metrics were used to evaluate the appropriateness of AI reliance: Relative AI Reliance (RAIR) and Relative Self-Reliance (RSR). Results showed that even with groups of three pathologists, majority-voted decisions significantly increased both RAIR and RSR – by approximately 9% and 31%, respectively – compared to decisions made by one pathologist collaborating with AI. This increased appropriateness resulted in better precision and recall in the detection of mitoses. While our study is centered on pathology, we believe these insights can be extended to general high-stakes decision-making processes involving similar visual tasks. •Multi-institutional user study with medical doctors from diverse backgrounds.•Two quantifiable metrics for evaluating appropriateness of AI reliance.•Majority voting improves appropriateness of AI reliance in pathology decisions.•Increased appropriateness elevates precision and recall.•Grouped pathologists improve qualities in visual decision-making.