Related Experiment Video
Updated: May 15, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Predicting onset of major depression in general practice attendees in Europe: extending the application of the
M King1, C Bottomley, J Bellón-Saameño
1Mental Health Sciences Unit, Faculty of Brain Sciences, University College London Medical School, London, UK. michael.king@ucl.ac.uk
Background:
PredictD is a risk algorithm that was developed to predict risk of onset of major depression over 12 months in general practice attendees in Europe and validated in a similar population in Chile. It was the first risk algorithm to be developed in the field of mental disorders. Our objective was to extend predictD as an algorithm to detect people at risk of major depression over 24 months. Method Participants were 4190 adult attendees to general practices in the UK, Spain, Slovenia and Portugal, who were not depressed at baseline and were followed up for 24 months. The original predictD risk algorithm for onset of DSM-IV major depression had already been developed in data arising from the first 12 months of follow-up. In this analysis we fitted predictD to the longer period of follow-up, first by examining only the second year (12-24 months) and then the whole period of follow-up (0-24 months).
Results:
The instrument performed well for prediction of major depression from 12 to 24 months [c-index 0.728, 95% confidence interval (CI) 0.675-0.781], or over the whole 24 months (c-index 0.783, 95% CI 0.757-0.809).
Conclusions:
The predictD risk algorithm for major depression is accurate over 24 months, extending it current use of prediction over 12 months. This strengthens its use in prevention efforts in general medical settings.
