This site is optimised for modern browsers. For the best experience, please use Google Chrome, Mozilla Firefox, or Microsoft Edge.


We welcome your feedback, which will help improve this site.

Feedback form

Computers can ‘spot the difference’ between healthy brains and the brains of people with dissociative identity disorder


Machine learning has been used to accurately distinguish between people with dissociative identity disorder (DID), formerly known as ‘multiple personality disorder’, and healthy individuals on the basis of their brain structure.

The research, funded by the NIHR Maudsley Biomedical Research Centre, used machine-learning techniques to recognise patterns in brain scans.

DID, formerly known as ‘multiple personality disorder’, is one of the most disputed and controversial mental health disorders, with serious problems around under diagnosis and misdiagnosis. It is the most severe of all dissociative disorders, involving multiple identity states and recurrent amnesia.

This NIHR funded research, published in the British Journal of Psychiatry, used the largest ever sample of individuals with DID in a brain imaging study.

Using machine-learning analyses of MRI scans, the researchers were able to discriminate between people with a confirmed diagnosis of DID and healthy controls with an overall accuracy of 73%, significantly higher than the level of accuracy you would expect by chance.

Corresponding author Dr Simone Reinders, Senior Research Associate at the Department of Psychological Medicine, Institute of Psychiatry, Psychology & Neuroscience, King’s College London, said: “From the moment of seeking treatment for symptoms, to the time of an accurate diagnosis of DID, individuals receive an average of four misdiagnoses and spend seven years in mental health services.

“These findings are important because they provide the first evidence of a biological basis for distinguishing between individuals with DID and healthy individuals. Ultimately, the application of pattern recognition techniques could prevent unnecessary suffering through earlier and more accurate diagnosis, facilitating faster and more targeted therapeutic interventions.”

Read more