Structural differences in adolescent brains can predict alcohol misuse
Alcohol misuse during adolescence (AAM) has been associated with disruptive development of adolescent brains. In this longitudinal machine learning (ML) study, we could predict AAM significantly from brain structure (T1-weighted imaging and DTI) with accuracies of 73 -78% in the IMAGEN dataset (n∼11...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2022-05-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/77545 |
| _version_ | 1811203646372708352 |
|---|---|
| author | Roshan Prakash Rane Evert Ferdinand de Man JiHoon Kim Kai Görgen Mira Tschorn Michael A Rapp Tobias Banaschewski Arun LW Bokde Sylvane Desrivieres Herta Flor Antoine Grigis Hugh Garavan Penny A Gowland Rüdiger Brühl Jean-Luc Martinot Marie-Laure Paillere Martinot Eric Artiges Frauke Nees Dimitri Papadopoulos Orfanos Herve Lemaitre Tomas Paus Luise Poustka Juliane Fröhner Lauren Robinson Michael N Smolka Jeanne Winterer Robert Whelan Gunter Schumann Henrik Walter Andreas Heinz Kerstin Ritter IMAGEN consortium |
| author_facet | Roshan Prakash Rane Evert Ferdinand de Man JiHoon Kim Kai Görgen Mira Tschorn Michael A Rapp Tobias Banaschewski Arun LW Bokde Sylvane Desrivieres Herta Flor Antoine Grigis Hugh Garavan Penny A Gowland Rüdiger Brühl Jean-Luc Martinot Marie-Laure Paillere Martinot Eric Artiges Frauke Nees Dimitri Papadopoulos Orfanos Herve Lemaitre Tomas Paus Luise Poustka Juliane Fröhner Lauren Robinson Michael N Smolka Jeanne Winterer Robert Whelan Gunter Schumann Henrik Walter Andreas Heinz Kerstin Ritter IMAGEN consortium |
| author_sort | Roshan Prakash Rane |
| collection | DOAJ |
| description | Alcohol misuse during adolescence (AAM) has been associated with disruptive development of adolescent brains. In this longitudinal machine learning (ML) study, we could predict AAM significantly from brain structure (T1-weighted imaging and DTI) with accuracies of 73 -78% in the IMAGEN dataset (n∼1182). Our results not only show that structural differences in brain can predict AAM, but also suggests that such differences might precede AAM behavior in the data. We predicted 10 phenotypes of AAM at age 22 using brain MRI features at ages 14, 19, and 22. Binge drinking was found to be the most predictable phenotype. The most informative brain features were located in the ventricular CSF, and in white matter tracts of the corpus callosum, internal capsule, and brain stem. In the cortex, they were spread across the occipital, frontal, and temporal lobes and in the cingulate cortex. We also experimented with four different ML models and several confound control techniques. Support Vector Machine (SVM) with rbf kernel and Gradient Boosting consistently performed better than the linear models, linear SVM and Logistic Regression. Our study also demonstrates how the choice of the predicted phenotype, ML model, and confound correction technique are all crucial decisions in an explorative ML study analyzing psychiatric disorders with small effect sizes such as AAM. |
| first_indexed | 2024-04-12T02:58:45Z |
| format | Article |
| id | doaj.art-9739d305de394da7871dd02984b2c2a2 |
| institution | Directory Open Access Journal |
| issn | 2050-084X |
| language | English |
| last_indexed | 2024-04-12T02:58:45Z |
| publishDate | 2022-05-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj.art-9739d305de394da7871dd02984b2c2a22022-12-22T03:50:44ZengeLife Sciences Publications LtdeLife2050-084X2022-05-011110.7554/eLife.77545Structural differences in adolescent brains can predict alcohol misuseRoshan Prakash Rane0https://orcid.org/0000-0002-3996-2034Evert Ferdinand de Man1JiHoon Kim2https://orcid.org/0000-0002-3157-3472Kai Görgen3https://orcid.org/0000-0002-4711-9629Mira Tschorn4Michael A Rapp5Tobias Banaschewski6Arun LW Bokde7Sylvane Desrivieres8Herta Flor9Antoine Grigis10Hugh Garavan11Penny A Gowland12Rüdiger Brühl13https://orcid.org/0000-0003-0111-5996Jean-Luc Martinot14Marie-Laure Paillere Martinot15Eric Artiges16Frauke Nees17Dimitri Papadopoulos Orfanos18https://orcid.org/0000-0002-1242-8990Herve Lemaitre19Tomas Paus20Luise Poustka21Juliane Fröhner22Lauren Robinson23Michael N Smolka24https://orcid.org/0000-0001-5398-5569Jeanne Winterer25Robert Whelan26Gunter Schumann27Henrik Walter28Andreas Heinz29Kerstin Ritter30IMAGEN consortiumCharité – Universitätsmedizin Berlin (corporate member of Freie Universiät at Berlin, Humboldt-Universiät at zu Berlin, and Berlin Institute of Health), Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, GermanyFaculty IV – Electrical Engineering and Computer Science, Technische Universität Berlin, Berlin, GermanyDepartment of Education and Psychology, Freie Universität Berlin, Berlin, GermanyCharité – Universitätsmedizin Berlin (corporate member of Freie Universiät at Berlin, Humboldt-Universiät at zu Berlin, and Berlin Institute of Health), Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, Germany; Science of Intelligence, Research Cluster of Excellence, Berlin, GermanySocial and Preventive Medicine, Department of Sports and Health Sciences, Intra-faculty unit “Cognitive Sciences”, Faculty of Human Science, and Faculty of Health Sciences Brandenburg, Research Area Services Research and e-Health, University of Potsdam, Potsdam, GermanySocial and Preventive Medicine, Department of Sports and Health Sciences, Intra-faculty unit “Cognitive Sciences”, Faculty of Human Science, and Faculty of Health Sciences Brandenburg, Research Area Services Research and e-Health, University of Potsdam, Potsdam, GermanyDepartment of Child and Adolescent Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, GermanyDiscipline of Psychiatry, School of Medicine and Trinity College Institute of Neuroscience, Trinity College Dublin, Dublin, IrelandCentre for Population Neuroscience and Precision Medicine (PONS), Institute of Psychiatry, Psychology Neuroscience SGDP Centre, King’s College London, London, United KingdomInstitute of Cognitive and Clinical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany; Department of Psychology, School of Social Sciences, University of Mannheim, Mannheim, GermanyNeuroSpin, CEA, Université Paris-Saclay, Paris, FranceDepartments of Psychiatry and Psychology, University of Vermont, Burlington, United StatesSir Peter Mansfield Imaging Centre School of Physics and Astronomy, University of Nottingham, Nottingham, United KingdomPhysikalisch-Technische Bundesanstalt, Berlin, GermanyInstitut National de la Santé et de la Recherche Médicale, INSERM U A10 ”Trajectoires développementales en psychiatrie” Universite Paris-Saclay, Ecole Normale Supérieure Paris-Saclay, CNRS, Centre Borelli, Gif-sur-Yvette, FranceInstitut National de la Santé et de la Recherche Médicale, INSERM U A10 ”Trajectoires développementales en psychiatrie” Universite Paris-Saclay, Ecole Normale Supérieure Paris-Saclay, CNRS, Centre Borelli, Gif-sur-Yvette, France; AP-HP Sorbonne Université, Department of Child and Adolescent Psychiatry, Pitié-Salpêtrière Hospital, Paris, FranceInstitut National de la Santé et de la Recherche Médicale, INSERM U A10 ”Trajectoires développementales en psychiatrie” Universite Paris-Saclay, Ecole Normale Supérieure Paris-Saclay, CNRS, Centre Borelli, Gif-sur-Yvette, France; Psychiatry Department, EPS Barthélémy Durand, Etampes, FranceDepartment of Child and Adolescent Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; Institute of Cognitive and Clinical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany; PONS Research Group, Dept of Psychiatry and Psychotherapy, Campus Charite Mitte, Humboldt University, Berlin, GermanyNeuroSpin, CEA, Université Paris-Saclay, Paris, FranceNeuroSpin, CEA, Université Paris-Saclay, Paris, France; Institut des Maladies Neurodégénératives, UMR 5293, CNRS, CEA, University of Bordeaux, Bordeaux, FranceDepartment of Psychiatry, Faculty of Medicine and Centre Hospitalier Universitaire Sainte-Justine, University of Montreal, Montreal, Canada; Departments of Psychiatry and Psychology, University of Toronto, Toronto, CanadaDepartment of Child and Adolescent Psychiatry and Psychotherapy, University Medical Centre Göttingen, Göttingen, GermanyDepartment of Psychiatry and Neuroimaging Center, Technische Universität Dresden, Dresden, GermanyDepartment of Psychological Medicine, Section for Eating Disorders, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United KingdomDepartment of Psychiatry and Neuroimaging Center, Technische Universität Dresden, Dresden, GermanyCharité – Universitätsmedizin Berlin (corporate member of Freie Universiät at Berlin, Humboldt-Universiät at zu Berlin, and Berlin Institute of Health), Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, Germany; Department of Education and Psychology, Freie Universität Berlin, Berlin, GermanySchool of Psychology and Global Brain Health Institute, Trinity College Dublin, Dublin, IrelandPONS Research Group, Dept of Psychiatry and Psychotherapy, Campus Charite Mitte, Humboldt University, Berlin, GermanyCharité – Universitätsmedizin Berlin (corporate member of Freie Universiät at Berlin, Humboldt-Universiät at zu Berlin, and Berlin Institute of Health), Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, GermanyCharité – Universitätsmedizin Berlin (corporate member of Freie Universiät at Berlin, Humboldt-Universiät at zu Berlin, and Berlin Institute of Health), Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, GermanyCharité – Universitätsmedizin Berlin (corporate member of Freie Universiät at Berlin, Humboldt-Universiät at zu Berlin, and Berlin Institute of Health), Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, GermanyAlcohol misuse during adolescence (AAM) has been associated with disruptive development of adolescent brains. In this longitudinal machine learning (ML) study, we could predict AAM significantly from brain structure (T1-weighted imaging and DTI) with accuracies of 73 -78% in the IMAGEN dataset (n∼1182). Our results not only show that structural differences in brain can predict AAM, but also suggests that such differences might precede AAM behavior in the data. We predicted 10 phenotypes of AAM at age 22 using brain MRI features at ages 14, 19, and 22. Binge drinking was found to be the most predictable phenotype. The most informative brain features were located in the ventricular CSF, and in white matter tracts of the corpus callosum, internal capsule, and brain stem. In the cortex, they were spread across the occipital, frontal, and temporal lobes and in the cingulate cortex. We also experimented with four different ML models and several confound control techniques. Support Vector Machine (SVM) with rbf kernel and Gradient Boosting consistently performed better than the linear models, linear SVM and Logistic Regression. Our study also demonstrates how the choice of the predicted phenotype, ML model, and confound correction technique are all crucial decisions in an explorative ML study analyzing psychiatric disorders with small effect sizes such as AAM.https://elifesciences.org/articles/77545adolescence alcohol misusemachine learningdata science for psychiatryalcohol use disordermagnetic resonance imagingconfound control |
| spellingShingle | Roshan Prakash Rane Evert Ferdinand de Man JiHoon Kim Kai Görgen Mira Tschorn Michael A Rapp Tobias Banaschewski Arun LW Bokde Sylvane Desrivieres Herta Flor Antoine Grigis Hugh Garavan Penny A Gowland Rüdiger Brühl Jean-Luc Martinot Marie-Laure Paillere Martinot Eric Artiges Frauke Nees Dimitri Papadopoulos Orfanos Herve Lemaitre Tomas Paus Luise Poustka Juliane Fröhner Lauren Robinson Michael N Smolka Jeanne Winterer Robert Whelan Gunter Schumann Henrik Walter Andreas Heinz Kerstin Ritter IMAGEN consortium Structural differences in adolescent brains can predict alcohol misuse eLife adolescence alcohol misuse machine learning data science for psychiatry alcohol use disorder magnetic resonance imaging confound control |
| title | Structural differences in adolescent brains can predict alcohol misuse |
| title_full | Structural differences in adolescent brains can predict alcohol misuse |
| title_fullStr | Structural differences in adolescent brains can predict alcohol misuse |
| title_full_unstemmed | Structural differences in adolescent brains can predict alcohol misuse |
| title_short | Structural differences in adolescent brains can predict alcohol misuse |
| title_sort | structural differences in adolescent brains can predict alcohol misuse |
| topic | adolescence alcohol misuse machine learning data science for psychiatry alcohol use disorder magnetic resonance imaging confound control |
| url | https://elifesciences.org/articles/77545 |
| work_keys_str_mv | AT roshanprakashrane structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT evertferdinanddeman structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT jihoonkim structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT kaigorgen structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT miratschorn structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT michaelarapp structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT tobiasbanaschewski structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT arunlwbokde structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT sylvanedesrivieres structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT hertaflor structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT antoinegrigis structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT hughgaravan structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT pennyagowland structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT rudigerbruhl structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT jeanlucmartinot structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT marielaurepailleremartinot structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT ericartiges structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT fraukenees structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT dimitripapadopoulosorfanos structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT hervelemaitre structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT tomaspaus structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT luisepoustka structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT julianefrohner structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT laurenrobinson structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT michaelnsmolka structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT jeannewinterer structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT robertwhelan structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT gunterschumann structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT henrikwalter structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT andreasheinz structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT kerstinritter structuraldifferencesinadolescentbrainscanpredictalcoholmisuse AT imagenconsortium structuraldifferencesinadolescentbrainscanpredictalcoholmisuse |