Anxiety onset in adolescents: a machine-learning prediction

IMAGEN Consortium

doi:10.1038/s41380-022-01840-z

Anxiety onset in adolescents: a machine-learning prediction

IMAGEN Consortium

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

62 Downloads (Pure)

Abstract

Recent longitudinal studies in youth have reported MRI correlates of prospective anxiety symptoms during adolescence, a vulnerable period for the onset of anxiety disorders. However, their predictive value has not been established. Individual prediction through machine-learning algorithms might help bridge the gap to clinical relevance. A voting classifier with Random Forest, Support Vector Machine and Logistic Regression algorithms was used to evaluate the predictive pertinence of gray matter volumes of interest and psychometric scores in the detection of prospective clinical anxiety. Participants with clinical anxiety at age 18–23 (N = 156) were investigated at age 14 along with healthy controls (N = 424). Shapley values were extracted for in-depth interpretation of feature importance. Prospective prediction of pooled anxiety disorders relied mostly on psychometric features and achieved moderate performance (area under the receiver operating curve = 0.68), while generalized anxiety disorder (GAD) prediction achieved similar performance. MRI regional volumes did not improve the prediction performance of prospective pooled anxiety disorders with respect to psychometric features alone, but they improved the prediction performance of GAD, with the caudate and pallidum volumes being among the most contributing features. To conclude, in non-anxious 14 year old adolescents, future clinical anxiety onset 4–8 years later could be individually predicted. Psychometric features such as neuroticism, hopelessness and emotional symptoms were the main contributors to pooled anxiety disorders prediction. Neuroanatomical data, such as caudate and pallidum volume, proved valuable for GAD and should be included in prospective clinical anxiety prediction in adolescents.

Original language	English
Journal	Molecular Psychiatry
DOIs	https://doi.org/10.1038/s41380-022-01840-z
Publication status	Accepted/In press - 8 Dec 2022

Access to Document

10.1038/s41380-022-01840-z

s41380-022-01840-z
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Final published version, 1.85 MBLicence: CC BY

Cite this

@article{4fad30421bb646a8bcf17aef0ef6987a,

title = "Anxiety onset in adolescents: a machine-learning prediction",

abstract = "Recent longitudinal studies in youth have reported MRI correlates of prospective anxiety symptoms during adolescence, a vulnerable period for the onset of anxiety disorders. However, their predictive value has not been established. Individual prediction through machine-learning algorithms might help bridge the gap to clinical relevance. A voting classifier with Random Forest, Support Vector Machine and Logistic Regression algorithms was used to evaluate the predictive pertinence of gray matter volumes of interest and psychometric scores in the detection of prospective clinical anxiety. Participants with clinical anxiety at age 18–23 (N = 156) were investigated at age 14 along with healthy controls (N = 424). Shapley values were extracted for in-depth interpretation of feature importance. Prospective prediction of pooled anxiety disorders relied mostly on psychometric features and achieved moderate performance (area under the receiver operating curve = 0.68), while generalized anxiety disorder (GAD) prediction achieved similar performance. MRI regional volumes did not improve the prediction performance of prospective pooled anxiety disorders with respect to psychometric features alone, but they improved the prediction performance of GAD, with the caudate and pallidum volumes being among the most contributing features. To conclude, in non-anxious 14 year old adolescents, future clinical anxiety onset 4–8 years later could be individually predicted. Psychometric features such as neuroticism, hopelessness and emotional symptoms were the main contributors to pooled anxiety disorders prediction. Neuroanatomical data, such as caudate and pallidum volume, proved valuable for GAD and should be included in prospective clinical anxiety prediction in adolescents.",

author = "{IMAGEN Consortium} and Chavanne, {Alice V.} and {Paill{\`e}re Martinot}, {Marie Laure} and Jani Penttil{\"a} and Yvonne Grimmer and Patricia Conrod and Argyris Stringaris and {van Noort}, Betteke and Corinna Isensee and Andreas Becker and Tobias Banaschewski and Bokde, {Arun L.W.} and Sylvane Desrivi{\`e}res and Herta Flor and Antoine Grigis and Hugh Garavan and Penny Gowland and Andreas Heinz and Ruediger Bruehl and Frauke Nees and {Papadopoulos Orfanos}, Dimitri and Tom{\'a}{\v s} Paus and Luise Poustka and Sarah Hohmann and Sabina Millenet and Fr{\"o}hner, {Juliane H.} and Smolka, {Michael N.} and Henrik Walter and Robert Whelan and Gunter Schumann and Martinot, {Jean Luc} and Eric Artiges and Eric Artiges and Semiha Aydin and Christine Bach and Tobias Banaschewski and Alexis Barbot and Gareth Barker and Arun Bokde and Nad{\`e}ge Bordas and Zuleima Bricaud and Uli Bromberg and Ruediger Bruehl and Christian B{\"u}chel and Anna Cattrell and Patricia Conrod and Tianye Jia and Charlotte Nymberg and Jan Reuter and Barbara Ruggeri and Gunter Schumann",

note = "Funding Information: This work received support from the following sources: the European Union-funded FP6 Integrated Project IMAGEN (Reinforcement-related behavior in normal brain function and psychopathology) (LSHM-CT-2007-037286), the Horizon 2020 funded ERC Advanced Grant “STRATIFY” (Brain network based stratification of reinforcement-related disorders) (695313), Human Brain Project (HBP SGA 2, 785907, and HBP SGA 3, 945539), the Medical Research Council Grant 'c-VEDA{\textquoteright} (Consortium on Vulnerability to Externalizing Disorders and Addictions) (MR/N000390/1), the National Institute of Health (NIH) (R01DA049238, A decentralized macro and micro gene-by-environment interaction analysis of substance use behavior and its brain biomarkers), the National Institute for Health Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King{\textquoteright}s College London, the Bundesministerium f{\"u}r Bildung und Forschung (BMBF grants 01GS08152; 01EV0711; Forschungsnetz AERIAL 01EE1406A, 01EE1406B; Forschungsnetz IMAC- Mind 01GL1745B), the Deutsche Forschungsgemeinschaft (DFG grants SM 80/7-2, SFB 940, TRR 265, NE 1383/14-1), the Medical Research Foundation and Medical Research Council (grants MR/R00465X/1 and MR/S020306/1), the National Institutes of Health (NIH) funded ENIGMA (grants 5U54EB020403-05 and 1R56AG058854-01). Further support was provided by grants from: the ANR (ANR-12-SAMA-0004, AAPG2019—GeBra), the Eranet Neuron (AF12-NEUR0008-01—WM2NA; and ANR-18-NEUR00002-01—ADORe), the Fondation de France (00081242), the Fondation pour la Recherche M{\'e}dicale (DPA20140629802), the Mission Interminist{\'e}rielle de Lutte-contre-les-Drogues-et-les-Conduites-Addictives (MILDECA), the Assistance-Publique-H{\^o}pitaux-de-Paris and INSERM (interface grant), Paris Sud University IDEX 2012, the Fondation de l{\textquoteright}Avenir (grant AP-RM-17-013), the F{\'e}d{\'e}ration pour la Recherche sur le Cerveau; the National Institutes of Health, Science Foundation Ireland (16/ERCD/3797), U.S.A. (Axon, Testosterone and Mental Health during Adolescence; RO1 MH085772-01A1), and by NIH Consortium grant U54 EB020403, supported by a cross-NIH alliance that funds Big Data to Knowledge Centres of Excellence. The INSERM, and the Strasbourg University and SATT CONECTUS, provided sponsorship (PI: Jean-Luc Martinot). Pr. Gilles Berstchy is acknowledged for his support. Pr. Stephane Lehericy and the radiographer staff at Centre de NeuroImagerie de Recherche de l{\textquoteright}Institut du Cerveau ( http://www.cenir.org/mri.html?lang=en ) are acknowledged for their support in MRI datasets acquisition. Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = dec,

day = "8",

doi = "10.1038/s41380-022-01840-z",

language = "English",

journal = "Molecular Psychiatry",

issn = "1359-4184",

publisher = "Springer Nature [academic journals on nature.com]",

}

TY - JOUR

T1 - Anxiety onset in adolescents

T2 - a machine-learning prediction

AU - IMAGEN Consortium

AU - Chavanne, Alice V.

AU - Paillère Martinot, Marie Laure

AU - Penttilä, Jani

AU - Grimmer, Yvonne

AU - Conrod, Patricia

AU - Stringaris, Argyris

AU - van Noort, Betteke

AU - Isensee, Corinna

AU - Becker, Andreas

AU - Banaschewski, Tobias

AU - Bokde, Arun L.W.

AU - Desrivières, Sylvane

AU - Flor, Herta

AU - Grigis, Antoine

AU - Garavan, Hugh

AU - Gowland, Penny

AU - Heinz, Andreas

AU - Bruehl, Ruediger

AU - Nees, Frauke

AU - Papadopoulos Orfanos, Dimitri

AU - Paus, Tomáš

AU - Poustka, Luise

AU - Hohmann, Sarah

AU - Millenet, Sabina

AU - Fröhner, Juliane H.

AU - Smolka, Michael N.

AU - Walter, Henrik

AU - Whelan, Robert

AU - Schumann, Gunter

AU - Martinot, Jean Luc

AU - Artiges, Eric

AU - Aydin, Semiha

AU - Bach, Christine

AU - Banaschewski, Tobias

AU - Barbot, Alexis

AU - Barker, Gareth

AU - Bokde, Arun

AU - Bordas, Nadège

AU - Bricaud, Zuleima

AU - Bromberg, Uli

AU - Bruehl, Ruediger

AU - Büchel, Christian

AU - Cattrell, Anna

AU - Conrod, Patricia

AU - Jia, Tianye

AU - Nymberg, Charlotte

AU - Reuter, Jan

AU - Ruggeri, Barbara

AU - Schumann, Gunter

N1 - Funding Information: This work received support from the following sources: the European Union-funded FP6 Integrated Project IMAGEN (Reinforcement-related behavior in normal brain function and psychopathology) (LSHM-CT-2007-037286), the Horizon 2020 funded ERC Advanced Grant “STRATIFY” (Brain network based stratification of reinforcement-related disorders) (695313), Human Brain Project (HBP SGA 2, 785907, and HBP SGA 3, 945539), the Medical Research Council Grant 'c-VEDA’ (Consortium on Vulnerability to Externalizing Disorders and Addictions) (MR/N000390/1), the National Institute of Health (NIH) (R01DA049238, A decentralized macro and micro gene-by-environment interaction analysis of substance use behavior and its brain biomarkers), the National Institute for Health Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King’s College London, the Bundesministerium für Bildung und Forschung (BMBF grants 01GS08152; 01EV0711; Forschungsnetz AERIAL 01EE1406A, 01EE1406B; Forschungsnetz IMAC- Mind 01GL1745B), the Deutsche Forschungsgemeinschaft (DFG grants SM 80/7-2, SFB 940, TRR 265, NE 1383/14-1), the Medical Research Foundation and Medical Research Council (grants MR/R00465X/1 and MR/S020306/1), the National Institutes of Health (NIH) funded ENIGMA (grants 5U54EB020403-05 and 1R56AG058854-01). Further support was provided by grants from: the ANR (ANR-12-SAMA-0004, AAPG2019—GeBra), the Eranet Neuron (AF12-NEUR0008-01—WM2NA; and ANR-18-NEUR00002-01—ADORe), the Fondation de France (00081242), the Fondation pour la Recherche Médicale (DPA20140629802), the Mission Interministérielle de Lutte-contre-les-Drogues-et-les-Conduites-Addictives (MILDECA), the Assistance-Publique-Hôpitaux-de-Paris and INSERM (interface grant), Paris Sud University IDEX 2012, the Fondation de l’Avenir (grant AP-RM-17-013), the Fédération pour la Recherche sur le Cerveau; the National Institutes of Health, Science Foundation Ireland (16/ERCD/3797), U.S.A. (Axon, Testosterone and Mental Health during Adolescence; RO1 MH085772-01A1), and by NIH Consortium grant U54 EB020403, supported by a cross-NIH alliance that funds Big Data to Knowledge Centres of Excellence. The INSERM, and the Strasbourg University and SATT CONECTUS, provided sponsorship (PI: Jean-Luc Martinot). Pr. Gilles Berstchy is acknowledged for his support. Pr. Stephane Lehericy and the radiographer staff at Centre de NeuroImagerie de Recherche de l’Institut du Cerveau ( http://www.cenir.org/mri.html?lang=en ) are acknowledged for their support in MRI datasets acquisition. Publisher Copyright: © 2022, The Author(s).

PY - 2022/12/8

Y1 - 2022/12/8

N2 - Recent longitudinal studies in youth have reported MRI correlates of prospective anxiety symptoms during adolescence, a vulnerable period for the onset of anxiety disorders. However, their predictive value has not been established. Individual prediction through machine-learning algorithms might help bridge the gap to clinical relevance. A voting classifier with Random Forest, Support Vector Machine and Logistic Regression algorithms was used to evaluate the predictive pertinence of gray matter volumes of interest and psychometric scores in the detection of prospective clinical anxiety. Participants with clinical anxiety at age 18–23 (N = 156) were investigated at age 14 along with healthy controls (N = 424). Shapley values were extracted for in-depth interpretation of feature importance. Prospective prediction of pooled anxiety disorders relied mostly on psychometric features and achieved moderate performance (area under the receiver operating curve = 0.68), while generalized anxiety disorder (GAD) prediction achieved similar performance. MRI regional volumes did not improve the prediction performance of prospective pooled anxiety disorders with respect to psychometric features alone, but they improved the prediction performance of GAD, with the caudate and pallidum volumes being among the most contributing features. To conclude, in non-anxious 14 year old adolescents, future clinical anxiety onset 4–8 years later could be individually predicted. Psychometric features such as neuroticism, hopelessness and emotional symptoms were the main contributors to pooled anxiety disorders prediction. Neuroanatomical data, such as caudate and pallidum volume, proved valuable for GAD and should be included in prospective clinical anxiety prediction in adolescents.

AB - Recent longitudinal studies in youth have reported MRI correlates of prospective anxiety symptoms during adolescence, a vulnerable period for the onset of anxiety disorders. However, their predictive value has not been established. Individual prediction through machine-learning algorithms might help bridge the gap to clinical relevance. A voting classifier with Random Forest, Support Vector Machine and Logistic Regression algorithms was used to evaluate the predictive pertinence of gray matter volumes of interest and psychometric scores in the detection of prospective clinical anxiety. Participants with clinical anxiety at age 18–23 (N = 156) were investigated at age 14 along with healthy controls (N = 424). Shapley values were extracted for in-depth interpretation of feature importance. Prospective prediction of pooled anxiety disorders relied mostly on psychometric features and achieved moderate performance (area under the receiver operating curve = 0.68), while generalized anxiety disorder (GAD) prediction achieved similar performance. MRI regional volumes did not improve the prediction performance of prospective pooled anxiety disorders with respect to psychometric features alone, but they improved the prediction performance of GAD, with the caudate and pallidum volumes being among the most contributing features. To conclude, in non-anxious 14 year old adolescents, future clinical anxiety onset 4–8 years later could be individually predicted. Psychometric features such as neuroticism, hopelessness and emotional symptoms were the main contributors to pooled anxiety disorders prediction. Neuroanatomical data, such as caudate and pallidum volume, proved valuable for GAD and should be included in prospective clinical anxiety prediction in adolescents.

UR - http://www.scopus.com/inward/record.url?scp=85143809874&partnerID=8YFLogxK

U2 - 10.1038/s41380-022-01840-z

DO - 10.1038/s41380-022-01840-z

M3 - Article

C2 - 36481929

AN - SCOPUS:85143809874

SN - 1359-4184

JO - Molecular Psychiatry

JF - Molecular Psychiatry

ER -

Anxiety onset in adolescents: a machine-learning prediction

Abstract

Access to Document

Other files and links

Fingerprint

Cite this