A deep learning model that combines genetics and registry data can predict both mental disorder diagnosis and disorder progression in a clinically relevant, cross-diagnostic manner prior to clinical assessment, according to a study published online Dec. 7 in JAMA Psychiatry.
The development was based upon 63,535 individuals with attention-deficit/hyperactivity disorder [ADHD], autism spectrum disorder [ASD], major depressive disorder [MDD], bipolar disorder [BD], and schizophrenia spectrum disorders [SCZ] as well as a control population.
The researchers reported that 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 gave AUCs/MCCs 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.
Will this become another diagnostic tool, or will it replace medical professionals in the screening and diagnosis of autism and the other listed issues? What if these predictions are performed without your knowledge or permission? What do you think?
Can be a first step to influence public policies to allocate resources to assist groups under this diagnostic.