AI failed to detect critical health conditions: study

Artificial Intelligence systems designed to predict the likelihood of a hospitalized patient dying largely aren't detecting worsening health conditions, according to a new study. Some machine learning models trained exclusively on existing patient data didn't recognize about 66 percent of injuries that could lead to patient death in the hospital, according to the research published in Nature's Communications Medicine journal. Researchers looked at several machine learning models commonly cited in medical literature for use in predicting patient deterioration and fed them publicly available sets of data about the health and metrics of patients in ICUs or with cancer. The researchers then created test cases for the models to predict potential health issues and risk scores if some patient metrics were altered from the initial data set. The models for in-hospital mortality prediction could only recognize an average of 34 percent of patient injuries, the study found.