TY - JOUR
T1 - Predicting alcohol use disorder remission
T2 - a longitudinal multimodal multi-featured machine learning approach
AU - Kinreich, Sivan
AU - McCutcheon, Vivia V.
AU - Aliev, Fazil
AU - Meyers, Jacquelyn L.
AU - Kamarajan, Chella
AU - Pandey, Ashwini K.
AU - Chorlian, David B.
AU - Zhang, Jian
AU - Kuang, Weipeng
AU - Pandey, Gayathri
AU - Viteri, Stacey Subbie Saenz de
AU - Francis, Meredith W.
AU - Chan, Grace
AU - Bourdon, Jessica L.
AU - Dick, Danielle M.
AU - Anokhin, Andrey P.
AU - Bauer, Lance
AU - Hesselbrock, Victor
AU - Schuckit, Marc A.
AU - Nurnberger, John I.
AU - Foroud, Tatiana M.
AU - Salvatore, Jessica E.
AU - Bucholz, Kathleen K.
AU - Porjesz, Bernice
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/6
Y1 - 2021/6
N2 - Predictive models for recovering from alcohol use disorder (AUD) and identifying related predisposition biomarkers can have a tremendous impact on addiction treatment outcomes and cost reduction. Our sample (N = 1376) included individuals of European (EA) and African (AA) ancestry from the Collaborative Study on the Genetics of Alcoholism (COGA) who were initially assessed as having AUD (DSM-5) and reassessed years later as either having AUD or in remission. To predict this difference in AUD recovery status, we analyzed the initial data using multimodal, multi-features machine learning applications including EEG source-level functional brain connectivity, Polygenic Risk Scores (PRS), medications, and demographic information. Sex and ancestry age-matched stratified analyses were performed with supervised linear Support Vector Machine application and were calculated twice, once when the ancestry was defined by self-report and once defined by genetic data. Multifeatured prediction models achieved higher accuracy scores than models based on a single domain and higher scores in male models when the ancestry was based on genetic data. The AA male group model with PRS, EEG functional connectivity, marital and employment status features achieved the highest accuracy of 86.04%. Several discriminative features were identified, including collections of PRS related to neuroticism, depression, aggression, years of education, and alcohol consumption phenotypes. Other discriminated features included being married, employed, medication, lower default mode network and fusiform connectivity, and higher insula connectivity. Results highlight the importance of increasing genetic homogeneity of analyzed groups, identifying sex, and ancestry-specific features to increase prediction scores revealing biomarkers related to AUD remission.
AB - Predictive models for recovering from alcohol use disorder (AUD) and identifying related predisposition biomarkers can have a tremendous impact on addiction treatment outcomes and cost reduction. Our sample (N = 1376) included individuals of European (EA) and African (AA) ancestry from the Collaborative Study on the Genetics of Alcoholism (COGA) who were initially assessed as having AUD (DSM-5) and reassessed years later as either having AUD or in remission. To predict this difference in AUD recovery status, we analyzed the initial data using multimodal, multi-features machine learning applications including EEG source-level functional brain connectivity, Polygenic Risk Scores (PRS), medications, and demographic information. Sex and ancestry age-matched stratified analyses were performed with supervised linear Support Vector Machine application and were calculated twice, once when the ancestry was defined by self-report and once defined by genetic data. Multifeatured prediction models achieved higher accuracy scores than models based on a single domain and higher scores in male models when the ancestry was based on genetic data. The AA male group model with PRS, EEG functional connectivity, marital and employment status features achieved the highest accuracy of 86.04%. Several discriminative features were identified, including collections of PRS related to neuroticism, depression, aggression, years of education, and alcohol consumption phenotypes. Other discriminated features included being married, employed, medication, lower default mode network and fusiform connectivity, and higher insula connectivity. Results highlight the importance of increasing genetic homogeneity of analyzed groups, identifying sex, and ancestry-specific features to increase prediction scores revealing biomarkers related to AUD remission.
UR - http://www.scopus.com/inward/record.url?scp=85102578415&partnerID=8YFLogxK
U2 - 10.1038/s41398-021-01281-2
DO - 10.1038/s41398-021-01281-2
M3 - Article
C2 - 33723218
AN - SCOPUS:85102578415
SN - 2158-3188
VL - 11
JO - Translational psychiatry
JF - Translational psychiatry
IS - 1
M1 - 166
ER -