When it comes to mental health outcomes, a new study shows A.I. may perform better than doctors.
A recent study published in the journal for the American Medical Association, JAMA Psychiatry - found that algorithms performed better than humans in predicting the outcomes of patients futures for things like their ability to maintain relationships or their ability to find employment. A.I. predicted what the social outcomes would be for patients one year later with an accuracy of 83%, which was significantly better than the human clinicians.
The study was conducted in five different European countries and followed 236 patients who were at a high risk for psychosis and depression. It was lead by professor Nikolaos Koutsouleris of Ludwig-Mazimilian University in Munich.
The machine learning models where trained on functional neuroimaging and baseline data. The study also states...
There was 1.9-fold increase of prognostic certainty in uncertain cases of patients in CHR states, and a 10.5-fold increase of prognostic certainty for patients with ROD.
Will Machines Replace Doctors?
Doctors will not be replaced by algorithms any time soon. Predictive tools such as the ones used in this experiment will just make them more effective.
Author John Wojewoda
