TY - JOUR

T1 - Deep learning-based integration of genetics with registry data for stratification of schizophrenia and depression

AU - Allesøe, Rosa Lundbye

AU - Nudel, Ron

AU - Thompson, Wesley K

AU - Wang, Yunpeng

AU - Nordentoft, Merete

AU - Børglum, Anders D

AU - Hougaard, David M

AU - Werge, Thomas

AU - Rasmussen, Simon

AU - Benros, Michael Eriksen

PY - 2022

Y1 - 2022

N2 - Currently, psychiatric diagnoses are, in contrast to most other medical fields, based on subjective symptoms and observable signs and call for new and improved diagnostics to provide the most optimal care. On the basis of a deep learning approach, we performed unsupervised patient stratification of 19,636 patients with depression [major depressive disorder (MDD)] and/or schizophrenia (SCZ) and 22,467 population controls from the iPSYCH2012 case cohort. We integrated data of disorder severity, history of mental disorders and disease comorbidities, genetics, and medical birth data. From this, we stratified the individuals in six and seven unique clusters for MDD and SCZ, respectively. When censoring data until diagnosis, we could predict MDD clusters with areas under the curve (AUCs) of 0.54 to 0.80 and SCZ clusters with AUCs of 0.71 to 0.86. Overall cases and controls could be predicted with an AUC of 0.81, illustrating the utility of data-driven subgrouping in psychiatry.

AB - Currently, psychiatric diagnoses are, in contrast to most other medical fields, based on subjective symptoms and observable signs and call for new and improved diagnostics to provide the most optimal care. On the basis of a deep learning approach, we performed unsupervised patient stratification of 19,636 patients with depression [major depressive disorder (MDD)] and/or schizophrenia (SCZ) and 22,467 population controls from the iPSYCH2012 case cohort. We integrated data of disorder severity, history of mental disorders and disease comorbidities, genetics, and medical birth data. From this, we stratified the individuals in six and seven unique clusters for MDD and SCZ, respectively. When censoring data until diagnosis, we could predict MDD clusters with areas under the curve (AUCs) of 0.54 to 0.80 and SCZ clusters with AUCs of 0.71 to 0.86. Overall cases and controls could be predicted with an AUC of 0.81, illustrating the utility of data-driven subgrouping in psychiatry.

KW - Deep Learning

KW - Depression/genetics

KW - Depressive Disorder, Major/diagnosis

KW - Humans

KW - Registries

KW - Schizophrenia/diagnosis

U2 - 10.1126/sciadv.abi7293

DO - 10.1126/sciadv.abi7293

M3 - Journal article

C2 - 35767618

VL - 8

JO - Science advances

JF - Science advances

SN - 2375-2548

IS - 26

M1 - eabi7293

ER -