Anxiety onset in adolescents: a machine-learning prediction

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Beitragende

  • Alice V. Chavanne - , Université Paris-Saclay, Humboldt-Universität zu Berlin (Autor:in)
  • Marie Laure Paillère Martinot - , Université Paris-Saclay, Sorbonne Université, Assistance publique – Hôpitaux de Paris (Autor:in)
  • Jani Penttilä - , Tampere University Hospital (Autor:in)
  • Yvonne Grimmer - , Universität Heidelberg (Autor:in)
  • Patricia Conrod - , University of Montreal (Autor:in)
  • Argyris Stringaris - , University College London (Autor:in)
  • Betteke van Noort - , Charité – Universitätsmedizin Berlin (Autor:in)
  • Corinna Isensee - , Georg-August-Universität Göttingen (Autor:in)
  • Andreas Becker - , Georg-August-Universität Göttingen (Autor:in)
  • Tobias Banaschewski - , Universität Heidelberg, Zentralinstitut für Seelische Gesundheit (ZI) (Autor:in)
  • Arun Bokde - , Trinity College Dublin (Autor:in)
  • Sylvane Desrivières - , King's College London (KCL) (Autor:in)
  • Herta Flor - , Universität Heidelberg, Universität Mannheim, Zentralinstitut für Seelische Gesundheit (ZI) (Autor:in)
  • Antoine Grigis - , Université Paris-Saclay (Autor:in)
  • Hugh Garavan - , University of Vermont (Autor:in)
  • Penny Gowland - , University of Nottingham (Autor:in)
  • Andreas Heinz - , Charité – Universitätsmedizin Berlin (Autor:in)
  • Ruediger Bruehl - , Physikalisch-Technische Bundesanstalt (Autor:in)
  • Frauke Nees - , Universität Heidelberg, Christian-Albrechts-Universität zu Kiel (CAU), Universität Hamburg (Autor:in)
  • Dimitri Papadopoulos Orfanos - , Université Paris-Saclay (Autor:in)
  • Tomáš Paus - , University of Montreal (Autor:in)
  • Luise Poustka - , Georg-August-Universität Göttingen (Autor:in)
  • Sarah Hohmann - , Universität Heidelberg (Autor:in)
  • Sabina Millenet - , Universität Heidelberg (Autor:in)
  • Juliane H. Fröhner - , Klinik und Poliklinik für Psychiatrie und Psychotherapie (Autor:in)
  • Michael N. Smolka - , Klinik und Poliklinik für Psychiatrie und Psychotherapie (Autor:in)
  • Henrik Walter - , Charité – Universitätsmedizin Berlin (Autor:in)
  • Robert Whelan - , Trinity College Dublin (Autor:in)
  • Gunter Schumann - , Fudan University, Charité – Universitätsmedizin Berlin (Autor:in)
  • Jean Luc Martinot - , Université Paris-Saclay, École normale supérieure Paris-Saclay (Autor:in)

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.

Details

OriginalspracheEnglisch
Seiten (von - bis)639-646
Seitenumfang8
FachzeitschriftMolecular psychiatry
Jahrgang28
Ausgabenummer2
Frühes Online-Datum8 Dez. 2022
PublikationsstatusVeröffentlicht - Feb. 2023
Peer-Review-StatusJa

Externe IDs

PubMed 36481929
ORCID /0000-0001-5398-5569/work/150329518
ORCID /0000-0002-8493-6396/work/150330244

Schlagworte

Ziele für nachhaltige Entwicklung

Schlagwörter

  • Humans, Adolescent, Young Adult, Adult, Prospective Studies, Anxiety Disorders/psychology, Anxiety, Algorithms, Machine Learning

Bibliotheksschlagworte