The new 87% accuracy finding, which was published in the journal NPJ Schizophrenia, improves on a 2017 study on other machine learning models built for the same purpose, which returned a 74% accuracy result.
Quite an improvement from only 2 years ago.
“The next step in this line of research is to develop models for predictions on the course of the disease and responses to treatment.
“For instance, patients can greatly benefit from models that have learned to predict optimal treatment strategy that is individualised for them.”
Explains accuracy, sensitivity and specificity
Well, this sounds atleast alittle hopeful!
My concern is, once a doc thinks you have kind of psychosis they then automatically throw ap’s at you. So for people like us, we are already medicated through the gills and would not be able to do these scans. So who would these subjects be? Is there a certain amount of time after you come off aps that you could then do a scan?
@Priscillame. Most schizophrenia research is done with medicated patients (easier to find). “Anti-psychotic naïve” patients are generally used when studying ap’s themselves or when researchers want extra rigor in their results.
I don’t think this technology would have gotten to a reported 87% accuracy without taking into account such a well known variable as medication.