· Contributors · Organizations ·
Machine Learning in Healthcare: Two Case Studies
SessionPoster Session 1
DescriptionDespite many demonstrated advantages of machine learning tools in healthcare their performance assessment remains partial at best. In particular, human interactions with machine learning tools in clinical settings remain poorly researched. This study examined machine learning tool in two important areas, sepsis diagnosis and suicide prediction. In our own study on the effects of ML models in predicting suicide we performed a meta-analytic review of relevant literature to assess the utility of ML in predicting suicide risk. Based on the results of the random effects, multi-level model, ML had a significant effect on the prediction of suicide as defined by suicide death or attempt. However, our literature reviews on the two major areas of ML use in healthcare turned up no thorough human factors analyses of provider interactions with their machine learning tools, suggesting a critical research gap waiting to be filled.