Self-fulfilling prophecies and machine learning in resuscitation science
Authors' conclusion
There is a need for broad recognition of SFPs as ML is increasingly applied in resuscitation science and across medicine.
Study context
- Population
- Studies and review articles on machine learning (ML), algorithmic fairness and bias (PubMed, ArXiv)
- Outcome
- Mechanisms through which ML may reproduce or compound SFPs
Methodological detailsManuscripts selected by expert opinion of well-designed or key studies and review articles
- Manuscripts selected by expert opinion of well-designed or key studies and review articles
Main finding
As reported in the abstract
- 4 key mechanisms identified
- Imperfect human beliefs and behaviour encoded as self-fulfilling prophecies (SFPs) when treatment decisions are not accounted for (common)
- Human-machine interaction may compound SFPs through mutual reinforcement
- ML may introduce new SFPs from incorrect predictions
- Historically correct clinical choices may become SFPs as medicine progresses
Original publication
Self-fulfilling prophecies and machine learning in resuscitation science. Resuscitation. Published 25 October 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →