Loading...
Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach.
Kinreich, Sivan; McCutcheon, Vivia V; Aliev, Fazil; Meyers, Jacquelyn L; Kamarajan, Chella; Pandey, Ashwini K; Chorlian, David B; Zhang, Jian; Kuang, Weipeng; Pandey, Gayathri; Viteri, Stacey Subbie-Saenz de; Francis, Meredith W; Chan, Grace; Bourdon, Jessica L; Dick, Danielle M; Anokhin, Andrey P; Bauer, Lance; Hesselbrock, Victor; Schuckit, Marc A; Nurnberger, John I; Foroud, Tatiana M; Salvatore, Jessica E; Bucholz, Kathleen K; Porjesz, Bernice
Journal Title
Translational psychiatry
Keywords
Readers/Advisors
Journal Title
Term and Year
Publication Date
2021-03-15
Book Title
Publication Volume
11
Publication Issue
1
Publication Begin
166
Publication End
Number of pages
Collections
Files
Loading...
s41398-021-01281-2.pdf
Adobe PDF, 845.37 KB
Research Projects
Organizational Units
Journal Issue
Abstract
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 (Nā=ā1376) 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.
Citation
Kinreich S, McCutcheon VV, Aliev F, Meyers JL, Kamarajan C, Pandey AK, Chorlian DB, Zhang J, Kuang W, Pandey G, Viteri SS, Francis MW, Chan G, Bourdon JL, Dick DM, Anokhin AP, Bauer L, Hesselbrock V, Schuckit MA, Nurnberger JI Jr, Foroud TM, Salvatore JE, Bucholz KK, Porjesz B. Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach. Transl Psychiatry. 2021 Mar 15;11(1):166. doi: 10.1038/s41398-021-01281-2. PMID: 33723218; PMCID: PMC7960734.