Using polygenic scores and clinical data for bipolar disorder patient stratification and lithium response prediction: machine learning approach

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Beitragende

  • Major Depressive Disorder Working Group of the Psychiatric Genomics Consortium - (Autor:in)
  • Klinik und Poliklinik für Psychiatrie und Psychotherapie
  • University of Adelaide
  • South Australian Health And Medical Research Institute
  • University of New South Wales
  • Department for Psychiatry and Psychotherapy
  • Dokkyo Medical University
  • University Hospital of Cagliari
  • UIC Barcelona International University of Catalonia
  • Hôpitaux universitaires de Genève
  • Karolinska-Universitätskrankenhaus
  • University of California San Diego Health
  • Groupe Hospitalier Saint-Louis-Lariboisière-F.Widal
  • Klinikum Klagenfurt am Wörthersee
  • Centre Universitaire de Sante McGill
  • National Taiwan University Hospital
  • Universitätsspital Basel
  • McGill University
  • University of Medical Sciences Poznan
  • Universität Bonn
  • Johns Hopkins University
  • Klinikum der Ludwig-Maximilians-Universität (LMU) München
  • Service de psychiatrie
  • Dalhousie University
  • Alexandru Obregia Clinical Psychiatric Hospital
  • Mood Disorders Center of Ottawa
  • Osaka University
  • Universitäts GefäßCentrum
  • National Institute of Mental Health (NIMH)
  • Universität Heidelberg
  • Georg-August-Universität Göttingen
  • Nationales Zentrum für Tumorerkrankungen (NCT) Heidelberg
  • National Health Research Institutes Taiwan
  • Vrije Universiteit Amsterdam (VU)
  • Medizinische Universität Graz

Abstract

BACKGROUND: Response to lithium in patients with bipolar disorder is associated with clinical and transdiagnostic genetic factors. The predictive combination of these variables might help clinicians better predict which patients will respond to lithium treatment.

AIMS: To use a combination of transdiagnostic genetic and clinical factors to predict lithium response in patients with bipolar disorder.

METHOD: This study utilised genetic and clinical data (n = 1034) collected as part of the International Consortium on Lithium Genetics (ConLi+Gen) project. Polygenic risk scores (PRS) were computed for schizophrenia and major depressive disorder, and then combined with clinical variables using a cross-validated machine-learning regression approach. Unimodal, multimodal and genetically stratified models were trained and validated using ridge, elastic net and random forest regression on 692 patients with bipolar disorder from ten study sites using leave-site-out cross-validation. All models were then tested on an independent test set of 342 patients. The best performing models were then tested in a classification framework.

RESULTS: The best performing linear model explained 5.1% (P = 0.0001) of variance in lithium response and was composed of clinical variables, PRS variables and interaction terms between them. The best performing non-linear model used only clinical variables and explained 8.1% (P = 0.0001) of variance in lithium response. A priori genomic stratification improved non-linear model performance to 13.7% (P = 0.0001) and improved the binary classification of lithium response. This model stratified patients based on their meta-polygenic loadings for major depressive disorder and schizophrenia and was then trained using clinical data.

CONCLUSIONS: Using PRS to first stratify patients genetically and then train machine-learning models with clinical predictors led to large improvements in lithium response prediction. When used with other PRS and biological markers in the future this approach may help inform which patients are most likely to respond to lithium treatment.

Details

OriginalspracheEnglisch
Seiten (von - bis)1-10
Seitenumfang10
FachzeitschriftBritish Journal of Psychiatry
PublikationsstatusElektronische Veröffentlichung vor Drucklegung - 28 Feb. 2022
Peer-Review-StatusJa

Externe IDs

Scopus 85126276148
ORCID /0000-0002-3415-5583/work/150329749
ORCID /0000-0002-2666-859X/work/150329167

Schlagworte