Combination of machine learning and brain imaging create better diagnostics for mental illness
2020
Hamamutsu University School of Medicine, Hamamatsu City, Japan(1)
The University of Tokyo, Tokyo, Japan(2)
The University of Tokyo, Tokyo, Japan(2)
A computer algorithm was trained on MRI brain scans (magnetic resonance imaging) of 206 autism, schizophrenia and psychosis patients as well as people with no mental health concerns. A total of six different algorithms were used to discriminate between the different MRI images of the patient groups. This allowed associating different psychiatric diagnoses with variations in the thickness, surface or volume of areas of the brain on the MRI images. After a training period, the algorithm was tested with brain scans of another 43 patients. The machine's diagnosis matched the psychiatrists' assessments with high reliability and up to 85 per cent accuracy.
Machine-learning classification using neuroimaging data in schizophrenia, autism, ultra-high risk and first-episode psychosis
Hidenori Yamasue(1), Shinsuke Koike(2)
Added on: 09-22-2020
[1] https://www.nature.com/articles/s41398-020-00965-5[2] https://www.technologynetworks.com/neuroscience/news/can-machine-learning-and-brain-imaging-create-better-diagnostics-for-mental-illness-338710
