Using polygenic scores and clinical data for bipolar disorder patient stratification and lithium response prediction: machine learning approach - Université Paris Cité Accéder directement au contenu
Article Dans Une Revue British Journal of Psychiatry Année : 2022

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

Micah Cearns (1) , Azmeraw Amare (2) , Klaus Oliver Schubert (1) , Anbupalam Thalamuthu (3) , Joseph Frank (4) , Fabian Streit (4) , Mazda Adli (5) , Nirmala Akula (6, 7) , Kazufumi Akiyama (8) , Raffaella Ardau (9) , Bárbara Arias (10, 11) , Jean-Michel Aubry (12) , Lena Backlund (13, 14) , Abesh Kumar Bhattacharjee (15) , Frank Bellivier (16) , Antonio Benabarre (10, 17, 11) , Susanne Bengesser (18) , Joanna Biernacka (19) , Armin Birner (18) , Clara Brichant-Petitjean (16) , Pablo Cervantes (20) , Hsi-Chung Chen (21) , Caterina Chillotti (9) , Sven Cichon (22, 23) , Cristiana Cruceanu (24, 25) , Piotr Czerski (26) , Nina Dalkner (18) , Alexandre Dayer (12) , Franziska Degenhardt (22) , Maria Del Zompo (9) , J Raymond Depaulo (27) , Bruno Étain (16) , Peter Falkai (28) , Andreas Forstner (22, 23, 29) , Louise Frisen (14, 30) , Mark Frye (31) , Janice Fullerton (32) , Sébastien Gard (33) , Julie Garnham (34) , Fernando Goes (27) , Maria Grigoroiu-Serbanescu (35) , Paul Grof (36) , Ryota Hashimoto (37) , Joanna Hauser (26) , Urs Heilbronner (38, 39, 40) , Stefan Herms (22, 23) , Per Hoffmann (22, 23) , Andrea Hofmann (22) , Liping Hou (6, 7) , Yi-Hsiang Hsu (41, 42) , Stephane Jamain (43) , Esther Jiménez (10, 17, 11) , Jean-Pierre Kahn (44) , Layla Kassem (6, 7) , Po-Hsiu Kuo (21) , Tadafumi Kato (45) , John Kelsoe (15) , Sarah Kittel-Schneider (46) , Sebastian Kliwicki (26) , Barbara König (47) , Ichiro Kusumi (48) , Gonzalo Laje (6, 7) , Mikael Landén (49, 30) , Catharina Lavebratt (14, 30) , Marion Leboyer (43) , Susan Leckband (50) , Mario Maj (51) , Mirko Manchia (9, 34) , Lina Martinsson (30) , Michael Mccarthy (15, 50) , Susan Mcelroy (52) , Francesc Colom (11, 53, 54) , Marina Mitjans (11, 53, 54) , Francis Mondimore (27) , Palmiero Monteleone (55) , Caroline Nievergelt (15) , Markus Nöthen (22) , Tomas Novák (56) , Claire O'Donovan (34) , Norio Ozaki (57) , Vincent Millischer (13, 14, 58) , Sergi Papiol (40, 28) , Andrea Pfennig (59, 60) , Claudia Pisanu (9) , James Potash (27) , Andreas Reif (46) , Eva Reininghaus (18) , Guy Rouleau (61, 25) , Janusz Rybakowski (26) , Martin Schalling (13, 14) , Peter Schofield (32, 62) , Barbara Schweizer (27) , Giovanni Severino (9) , Tatyana Shekhtman (15) , Paul Shilling (15) , Katzutaka Shimoda (8) , Christian Simhandl (63) , Claire Slaney (34) , Alessio Squassina (9) , Thomas Stamm (5) , Pavla Stopkova (56) , Fasil Tekola-Ayele (64) , Alfonso Tortorella (65) , Gustavo Turecki (24) , Julia Veeh (46) , Eduard Vieta (10, 17, 11) , Stephanie Witt (66, 67) , Gloria Roberts (32) , Peter Zandi (68) , Martin Alda (34) , Michael Bauer (59, 60) , Francis Mcmahon (6, 7) , Philip Mitchell (32) , Thomas Schulze (66, 67, 6, 7, 27, 40, 28, 69, 38) , Marcella Rietschel (66, 67) , Scott Clark (70) , Bernhard Baune (71, 72, 73, 74)
1 University of South Australia [Adelaide]
2 SAHMRI - South Australian Health and Medical Research Institute [ Adelaide]
3 Centre for Healthy Brain Ageing (CHeBA), School of Psychiatry, UNSW Medicine, University of New South Wales, Sydney
4 University Medical Center Heidelberg
5 Charité - UniversitätsMedizin = Charité - University Hospital [Berlin]
6 NIMH - National Institute of Mental Health
7 NIH - National Institutes of Health [Bethesda, MD, USA]
8 Dokkyo Medical University
9 UniCa - Università degli Studi di Cagliari = University of Cagliari
10 University of Barcelona
11 CIBER-SAM - Centro de Investigación Biomédica en Red Salud Mental [Madrid]
12 HUG - Hôpitaux universitaires de Genève = University Hospitals of Geneva
13 Karolinska Institute
14 Karolinska University Hospital [Stockholm]
15 UC San Diego - University of California [San Diego]
16 OPTeN (UMR_S 1144 / U1144) - Optimisation thérapeutique en Neuropsychopharmacologie
17 IDIBAPS - Institut d'Investigacions Biomèdiques August Pi i Sunyer
18 Medical University of Graz
19 HSR - Department of Health Sciences Research [Mayo Clinic]
20 MUHC - McGill University Health Center [Montreal]
21 NTU - National Taiwan University [Taiwan]
22 Universität Bonn = University of Bonn
23 University Hospital Basel [Basel]
24 Douglas Mental Health University Institute [Montréal]
25 McGill University = Université McGill [Montréal, Canada]
26 PUMS - Poznan University of Medical Sciences [Poland]
27 JHU - Johns Hopkins University
28 LMU - Ludwig Maximilian University [Munich] = Ludwig Maximilians Universität München
29 Unibas - Université de Bâle = University of Basel = Basel Universität
30 Karolinska Institutet [Stockholm]
31 Mayo Clinic
32 UNSW - University of New South Wales [Sydney]
33 Centre hospitalier Charles Perrens [Bordeaux]
34 Dalhousie University [Halifax]
35 ERA-LEARN - Prof. Dr. Alexandru Obregia Psychiatry Hospital
36 MDCO - Mood Disorders Center of Ottawa
37 Osaka University [Osaka]
38 Georg-August-University = Georg-August-Universität Göttingen
39 UMG - University Medical Center Göttingen
40 IPPG - Institute of Psychiatric Phenomics and Genomics
41 Harvard School of Public Health
42 HMS - Harvard Medical School [Boston]
43 IMRB - Institut Mondor de Recherche Biomédicale
44 CPN - Centre Psychothérapique de Nancy [Laxou]
45 Juntendo University
46 Frankfurt University Hospital
47 LK Neunkirchen - Landesklinikum Neunkirchen
48 Hokkaido University [Sapporo, Japan]
49 Sahlgrenska Academy at University of Gothenburg [Göteborg]
50 VASDHS - VA San Diego Healthcare System [San Diego, CA, USA]
51 Università degli studi della Campania "Luigi Vanvitelli" = University of the Study of Campania Luigi Vanvitelli
52 UC - University of Cincinnati
53 IMIM-Hospital del Mar
54 ISC - Instituto de Salud Carlos III [Madrid]
55 UNISA - Università degli Studi di Salerno = University of Salerno
56 NIMH - National Institute of Mental Health [Klecany, Czech Republic]
57 Nagoya University
58 Medizinische Universität Wien = Medical University of Vienna
59 University Hospital Carl Gustav Carus [Dresden, Germany]
60 TU Dresden - Technische Universität Dresden = Dresden University of Technology
61 Montreal Neurological Institute and Hospital
62 NeuRA - Neuroscience Research Australia
63 SFU - Sigmund Freud University
64 NICHD - Eunice Kennedy Shriver National Institute of Child Health and Human Development
65 UNIPG - Università degli Studi di Perugia = University of Perugia
66 University Hospital Mannheim | Universitätsmedizin Mannheim
67 Universität Heidelberg [Heidelberg] = Heidelberg University
68 Johns Hopkins Bloomberg School of Public Health [Baltimore]
69 University Medical Center
70 University of Adelaide
71 WWU - Westfälische Wilhelms-Universität Münster = University of Münster
72 Melbourne Medical School [Melbourne]
73 University of Melbourne
74 The Florey Institute of Neuroscience and Mental Health
Micah Cearns
Hsi-Chung Chen
Mark Frye
  • Fonction : Auteur
Norio Ozaki
  • Fonction : Auteur
Gloria Roberts
Martin Alda

Résumé

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.
Fichier principal
Vignette du fichier
BJPsych.2022.28.pdf (660.58 Ko) Télécharger le fichier
Origine : Publication financée par une institution

Dates et versions

inserm-03847149 , version 1 (10-11-2022)

Identifiants

Citer

Micah Cearns, Azmeraw Amare, Klaus Oliver Schubert, Anbupalam Thalamuthu, Joseph Frank, et al.. Using polygenic scores and clinical data for bipolar disorder patient stratification and lithium response prediction: machine learning approach. British Journal of Psychiatry, 2022, 220 (4), pp.219-228. ⟨10.1192/bjp.2022.28⟩. ⟨inserm-03847149⟩
16 Consultations
44 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More