Soc Sci Med. 2024 Sep 6;359:117298. doi: 10.1016/j.socscimed.2024.117298. Online ahead of print.

ABSTRACT

The promise behind many advanced digital technologies in healthcare is to provide novel and accurate information, aiding medical experts to navigate and, ultimately, decrease uncertainty in their clinical work. However, sociological studies have started to show that these technologies are not producing straightforward objective knowledge, but instead often become associated with new uncertainties arising in unanticipated places and situations. This study contributes to the body of work by presenting a qualitative study of an Artificial Intelligence (AI) algorithm designed to predict the risk of mortality in patients discharged to home from the emergency department (ED). Through in-depth interviews with physicians working at the ED of a Swedish hospital, we demonstrate that while the AI algorithm can reduce targeted uncertainty, it simultaneously introduces three new forms of uncertainty into clinical practice: epistemic uncertainty, actionable uncertainty and ethical uncertainty. These new uncertainties require deliberate management and control, marking a shift from the physicians’ accustomed comfort with uncertainty in mortality prediction. Our study advances the understanding of the recursive nature and temporal dynamics of uncertainty in medical work, showing how new uncertainties emerge from attempts to manage existing ones. It also reveals that physicians’ attitudes towards, and management of, uncertainty vary depending on its form and underscores the intertwined role of digital technology in this process. By examining AI in emergency care, we provide valuable insights into how this epistemic technology reconfigures clinical uncertainty, offering significant theoretical and practical implications for the integration of AI in healthcare.

PMID:39260029 | DOI:10.1016/j.socscimed.2024.117298