According to a study published online on December 7 at JAMA Psychiatry.
Rosa Lundbye Allesøe, from Copenhagen University Hospital in Denmark, and colleagues developed deep learning models to predict the diagnosis and severity of mental disorder. The development was based on 63,535 individuals with mental disorders (attention-deficit/hyperactivity disorder [ADHD]autism spectrum disorder [ASD]major depressive disorder [MDD]bipolar disorder [BD]and schizophrenia spectrum disorders [SCZ]) and population controls.
The researchers reported that the specific diagnosis was predicted in a multidiagnostic prediction model (including the background population) with an overall area under the receiver operating characteristic curve (AUC) of 0.81 and Matthews correlation coefficient (MCC) of 0.28. Single-disorder models yielded AUC/MCC of 0.84/0.54 for SCZ, 0.79/0.41 for BD, 0.77/0.39 for ASD, 0.74/0.38 for ADHD, and 0. .74/0.38 for MDD.
Previous mental disorders and age (11 to 23 percent reduction in predictive accuracy when omitted) were the most important cues for multidiagnostic prediction, followed by family diagnoses, birth-related measurements, and genetic data (3 to 5 percent decrease in prediction accuracy when ) is removed. More severe cases were the most predictive when predicting disease trajectories, with an AUC of 0.72.
“The results suggest that the multidiagnostic model that resembles a clinical setting before screening can predict the diagnosis of mental disorder with high accuracy based only on registry data and genetic information,” the authors write.
Rosa Lundbye Allesøe et al, Deep learning for cross-diagnostic prediction of diagnosis and prognosis of mental disorders using Danish national registry and genetic data, JAMA Psychiatry (2022). DOI: 10.1001/jamapsychiatry.2022.4076
Copyright © 2022 HealthDay. All rights reserved.
citation: Genetic data + registry AI model can predict diagnosis of mental disorders (2022, December 21) retrieved on December 21, 2022 from https://medicalxpress.com/news/2022-12-genetic-registry-ai-mental -disorder.html
This document is subject to copyright. Except for any fair agreement for study or private research purposes, no part may be reproduced without written permission. The content is provided for informational purposes only.
