[BibTeX] [RIS]
Making sense of radiomics: Insights on human-AI collaboration in medical interaction from an observational user study
Tipo de publicação: Artigo
Citação: MDP2024
Publication status: Published
Journal: Frontiers in Communication
Volume: 8
Ano: 2024
Mês: February
URL: https://www.frontiersin.org/ar...
DOI: 10.3389/fcomm.2023.1234987
Resumo: Technologies based on "artificial intelligence" (AI) are transforming our society, including healthcare and medical institutions. An example of this trend is the novel field in oncology and radiology called radiomics, extracting and mining large-scale quantitative features from medical imaging by machine-learning (ML) algorithms. This paper explores situated work with a radiomics software platform QuantImage (v2), and interaction around it, in educationally framed hands-on trial sessions where pairs of novice users (physicians and medical radiology technicians) work on a radiomics task consisting in developing of a predictive ML model with a co-present tutor. Informed by ethnomethodology and conversation analysis (EM/CA), the results show that learning about radiomics more generally and learning how to use the specific platform are deeply intertwined. Common-sense knowledge (e.g., about meanings of colors) can interfere with the ways of visual representation established in the professional domain. Participants' skills in using the platform and their knowledge of radiomics are routinely displayed in assessment of performance measures of the resulting ML models, in monitoring the platform's pace of operation for possible problems, and in ascribing independent actions (e.g., related to algorithms) to the platform. The findings are relevant to the current discussions about explainability of AI in medicine as well as issues of machinic agency.
Palavras-chave: AI, artificial intelligence, conversation analysis, ethnomethodology, oncology, radiomics, social interaction
Autores Mlynar, Jakub
Depeursinge, Adrien
Prior, John O.
Schaer, Roger
Martroye de Joly, Alexandre
Evéquoz, Florian
Adicionado por: []
Total mark: 0
Anexos
  • 2024--Mlynar&al_-_Making_sense...
Notas
    Tópicos