Managing the collaboration between domain experts and Artificial Intelligence. 

Two case studies in the healthcare system.

Directed by Etienne Minvielle

defence scheduled for Friday 6 September at 3 p.m IN Amphithéâtre Lagarigue 

Ecole polytechnique,  Avenue Fresnel, 91120 Palaiseau

If you would like to come, please let us know by email:  Nous contacter

Abstract:

Artificial Intelligence (AI) leverages machine learning methods to automate the creation of complex statistical models. These AI tools can perform tasks with expert-level proficiency, yet the precise way results are generated often remains opaque, posing challenges for their integration into organizations. This thesis explores the collaboration between domain experts and AI tools within the healthcare system. In the healthcare system, human-AI collaboration is particularly critical due to the professional and moral responsibilities inherent in medical decisions and their inherent uncertainty. While AI tools promise to address the tensions in this system by offering increased personalization of care at lower costs, they also raise concerns, and their real-world adoption remains to be fully realized. Our empirical approach includes two case studies, illustrating these dynamics. RADO focuses on the use of an AI tool by radiologists for mammographic analysis, aiming to enhance their activities. KOVAK, examines how a medical research team uses AI tools to analyze patient cohort data.

A first analytical framework observes how experts leverage their knowledge to incorporate AI results, thereby demonstrating an engaged collaboration. A second one identifies the dual nature of the AI tool use, between a way to optimize an activity or generate learning. A third one, based on Peirce’s work on pragmatic inquiry, considers the AI tool as a partner in the knowledge construction process. We propose our collaboration model, EMC2 (Expert Machine Collaborative Community). It integrates various modes of managing expert-AI collaboration, thus facilitating better integration of this collaboration within organizations. This thesis contributes to the literature on human-AI collaboration models by defining management modes derived from an empirical approach. It also contributes to the literature on AI tool usage by specifying interrogative practices and by applying the concept of pragmatic inquiry

Key words: collaboration, humain-IA, Artificial Intelligence ; domain expert ; healthcare system

Composition du jury :