TaMu / Artificial intelligence assisted fracture diagnostics

The project is exploring enhancing practices and divisions of work in the context of musculoskeletal fracture diagnostics (MSK). Artificial intelligence assisted systems are changing social and healthcare rapidly, and the new technology can support medical experts' diagnostics work. Previous study has focused on technologic solutions and technical maturities of AI. In this project, focus is shifted to cooperation between humans and AI. The aim is to seek understanding of enhancement of professional performance, diagnostic decision making, cognitive workload, and work fluency when professionals work with AI solutions. The knowledge of how to lead clinicians through developing diagnostic processes and integrating AI solutions successfully as part of everyday work in healthcare is especially needed. To address this issue, this project is discovering MSK-fracture diagnostics as operational and productive driven enhancement.  

The research is executed in close cooperation with TaMu  (Artificial intelligence assisted fracture diagnostics) development project. In TaMu the validated AI solution Gleamer BoneView is integrated and scaled step by step to primary healthcare. The AI assisting technology will be expanded to several different anatomic fracture diagnostics. The aim of the study is to produce systematic and measurable knowledge about the effects of AI-assisted diagnostics.  Interests especially are the speed of diagnostic processes, divisions of work, workflow, human resource allocation, cognitive workload, and expertise. In addition, the changing of requirements of training, and opportunities to scale AI solutions to different units of healthcare and other organizations are main interests of the study.  

The study produces multimodal information on how AI affects the clinicians' cognitive processes. The results of the study increase the understanding of the benefits and the risks of AI-assisted MSK-diagnostic processes. The results can be directly applied to the development of clinical work and specialist training of medical experts. The study is an essential part of implementing and scaling AI solutions in clinical practice.