Rams, hounds and white boxes: Investigating human–AI collaboration protocols in medical diagnosis
Year: 2023
Type: article
Abstract: In this paper, we study human-AI collaboration protocols, a design-oriented construct aimed at establishing and evaluating how humans and AI can collaborate in cognitive tasks. We applied this construct in two user studies involving 12 specialist radiologists (the knee MRI study) and 44 ECG readers of varying expertise (the ECG study), who evaluated 240 and 20 cases, respectively, in different collaboration configurations. We confirm the utility of AI support but find that XAI can be associated with a "white-box paradox", producing a null or detrimental effect. We also find that the order of presentation matters: AI-first protocols are associated with higher diagnostic accuracy than human-first protocols, and with higher accuracy than both humans and AI alone. Our findings identify the best conditions for AI to augment human diagnostic skills, rather than trigger dysfunctional responses and cognitive biases that can undermine decision effectiveness.
Institutions: IRCCS Ospedale Galeazzi - Sant'Ambrogio, University of Milano-Bicocca, IRCCS Ospedale San Raffaele, University of Siena, Azienda Ospedaliero Universitaria Maggiore della Carita, University of Milan, Fraunhofer Portugal Research, Laboratório de Instrumentação Engenharia Biomédica e Física da Radiação, Laboratório de Instrumentação Engenharia Biomédica e Física da Radiação, Fundação para a Ciência e Tecnologia, Universidade Nova de Lisboa
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $3,230
Funder: Ministero della Salute
OpenAlex ID: W4319339070