Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach
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 (N = 1376) included individuals of European (EA) and African (AA) ancestry from the...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-03-01
|
Series: | Translational Psychiatry |
Online Access: | https://doi.org/10.1038/s41398-021-01281-2 |
id |
doaj-a4b99fa326444960a6af8f5bcbc55d5a |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sivan Kinreich Vivia V. McCutcheon Fazil Aliev Jacquelyn L. Meyers Chella Kamarajan Ashwini K. Pandey David B. Chorlian Jian Zhang Weipeng Kuang Gayathri Pandey Stacey Subbie-Saenz de. Viteri Meredith W. Francis Grace Chan Jessica L. Bourdon Danielle M. Dick Andrey P. Anokhin Lance Bauer Victor Hesselbrock Marc A. Schuckit John I. Nurnberger Tatiana M. Foroud Jessica E. Salvatore Kathleen K. Bucholz Bernice Porjesz |
spellingShingle |
Sivan Kinreich Vivia V. McCutcheon Fazil Aliev Jacquelyn L. Meyers Chella Kamarajan Ashwini K. Pandey David B. Chorlian Jian Zhang Weipeng Kuang Gayathri Pandey Stacey Subbie-Saenz de. Viteri Meredith W. Francis Grace Chan Jessica L. Bourdon Danielle M. Dick Andrey P. Anokhin Lance Bauer Victor Hesselbrock Marc A. Schuckit John I. Nurnberger Tatiana M. Foroud Jessica E. Salvatore Kathleen K. Bucholz Bernice Porjesz Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach Translational Psychiatry |
author_facet |
Sivan Kinreich Vivia V. McCutcheon Fazil Aliev Jacquelyn L. Meyers Chella Kamarajan Ashwini K. Pandey David B. Chorlian Jian Zhang Weipeng Kuang Gayathri Pandey Stacey Subbie-Saenz de. Viteri Meredith W. Francis Grace Chan Jessica L. Bourdon Danielle M. Dick Andrey P. Anokhin Lance Bauer Victor Hesselbrock Marc A. Schuckit John I. Nurnberger Tatiana M. Foroud Jessica E. Salvatore Kathleen K. Bucholz Bernice Porjesz |
author_sort |
Sivan Kinreich |
title |
Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach |
title_short |
Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach |
title_full |
Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach |
title_fullStr |
Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach |
title_full_unstemmed |
Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach |
title_sort |
predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach |
publisher |
Nature Publishing Group |
series |
Translational Psychiatry |
issn |
2158-3188 |
publishDate |
2021-03-01 |
description |
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 (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. |
url |
https://doi.org/10.1038/s41398-021-01281-2 |
work_keys_str_mv |
AT sivankinreich predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT viviavmccutcheon predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT fazilaliev predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT jacquelynlmeyers predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT chellakamarajan predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT ashwinikpandey predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT davidbchorlian predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT jianzhang predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT weipengkuang predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT gayathripandey predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT staceysubbiesaenzdeviteri predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT meredithwfrancis predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT gracechan predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT jessicalbourdon predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT daniellemdick predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT andreypanokhin predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT lancebauer predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT victorhesselbrock predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT marcaschuckit predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT johninurnberger predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT tatianamforoud predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT jessicaesalvatore predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT kathleenkbucholz predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach AT berniceporjesz predictingalcoholusedisorderremissionalongitudinalmultimodalmultifeaturedmachinelearningapproach |
_version_ |
1724210095390195712 |
spelling |
doaj-a4b99fa326444960a6af8f5bcbc55d5a2021-03-21T12:51:26ZengNature Publishing GroupTranslational Psychiatry2158-31882021-03-0111111010.1038/s41398-021-01281-2Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approachSivan Kinreich0Vivia V. McCutcheon1Fazil Aliev2Jacquelyn L. Meyers3Chella Kamarajan4Ashwini K. Pandey5David B. Chorlian6Jian Zhang7Weipeng Kuang8Gayathri Pandey9Stacey Subbie-Saenz de. Viteri10Meredith W. Francis11Grace Chan12Jessica L. Bourdon13Danielle M. Dick14Andrey P. Anokhin15Lance Bauer16Victor Hesselbrock17Marc A. Schuckit18John I. Nurnberger19Tatiana M. Foroud20Jessica E. Salvatore21Kathleen K. Bucholz22Bernice Porjesz23Department of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, Washington University School of Medicine in St LouisDepartment of Psychiatry, Virginia Commonwealth UniversityDepartment of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, State University of New York, Downstate Medical CenterDepartment of Psychiatry, State University of New York, Downstate Medical CenterBrown School of Social Work / Department of Psychiatry, Washington University in Saint LouisDepartment of Psychiatry, University of Connecticut School of MedicineDepartment of Psychiatry, Washington University School of Medicine in St LouisDepartment of Psychiatry, Virginia Commonwealth UniversityDepartment of Psychiatry, Washington University School of Medicine in St LouisDepartment of Psychiatry, University of Connecticut School of MedicineDepartment of Psychiatry, University of Connecticut School of MedicineDepartment of Psychiatry, University of California, San Diego School of MedicineDepartments of Psychiatry and Medical and Molecular Genetics, Indiana University School of MedicineDepartment of Medical and Molecular Genetics at Indiana University School of MedicineDepartment of Psychology, Virginia Commonwealth UniversityDepartment of Psychiatry, Washington University School of Medicine in St LouisDepartment of Psychiatry, State University of New York, Downstate Medical CenterAbstract 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.https://doi.org/10.1038/s41398-021-01281-2 |