Author:
Reverberi Carlo,Rigon Tommaso,Solari Aldo,Hassan Cesare,Cherubini Paolo,Antonelli Giulio,Awadie Halim,Bernhofer Sebastian,Carballal Sabela,Dinis-Ribeiro Mário,Fernández-Clotett Agnès,Esparrach Glòria Fernández,Gralnek Ian,Higasa Yuta,Hirabayashi Taku,Hirai Tatsuki,Iwatate Mineo,Kawano Miki,Mader Markus,Maieron Andreas,Mattes Sebastian,Nakai Tastuya,Ordas Ingrid,Ortigão Raquel,Zúñiga Oswaldo Ortiz,Pellisé Maria,Pinto Cláudia,Riedl Florian,Sánchez Ariadna,Steiner Emanuel,Tanaka Yukari,Cherubini Andrea,
Abstract
AbstractArtificial Intelligence (ai) systems are precious support for decision-making, with many applications also in the medical domain. The interaction betweenmds andaienjoys a renewed interest following the increased possibilities of deep learning devices. However, we still have limited evidence-based knowledge of the context, design, and psychological mechanisms that craft an optimal human–aicollaboration. In this multicentric study, 21 endoscopists reviewed 504 videos of lesions prospectively acquired from real colonoscopies. They were asked to provide an optical diagnosis with and without the assistance of anaisupport system. Endoscopists were influenced byai($$\textsc {or}=3.05$$OR=3.05), but not erratically: they followed theaiadvice more when it was correct ($$\textsc {or}=3.48$$OR=3.48) than incorrect ($$\textsc {or}=1.85$$OR=1.85). Endoscopists achieved this outcome through a weighted integration of their and theaiopinions, considering the case-by-case estimations of the two reliabilities. This Bayesian-like rational behavior allowed the human–aihybrid team to outperform both agents taken alone. We discuss the features of the human–aiinteraction that determined this favorable outcome.
Publisher
Springer Science and Business Media LLC
Cited by
59 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献