Nikolaos Koutsouleris1, Thomas Wobrock2,3, Birgit Guse2, Berthold Langguth4, Michael Landgrebe4,5, Peter Eichhammer4, Elmar Frank4, Joachim Cordes6, Wolfgang Wölwer6, Francesco Musso6, Georg Winterer7, Wolfgang Gaebel6, Göran Hajak8,9, Christian Ohmann10, Pablo E Verde10, Marcella Rietschel11, Raees Ahmed12, William G Honer13, Dominic Dwyer1, Farhad Ghaseminejad13, Peter Dechent14, Berend Malchow1, Peter M Kreuzer4, Tim B Poeppl4, Thomas Schneider-Axmann1, Peter Falkai1, Alkomiet Hasan1. 1. Department of Psychiatry and Psychotherapy, Klinikum der Universität München, Ludwig-Maximilians-Universität, Munich. 2. Department of Psychiatry and Psychotherapy, Georg-August-University Goettingen. 3. County Hospitals Darmstadt-Dieburg, Groß-Umstadt. 4. Department of Psychiatry and Psychotherapy, University of Regensburg. 5. Department of Psychiatry, Psychosomatics and Psychotherapy, kbo-Lech-Mangfall-Klinik Agatharied, Germany. 6. Department of Psychiatry and Psychotherapy, Heinrich-Heine University, Düsseldorf. 7. Experimental & Clinical Research Center (ECRC), Charite - University Medicine Berlin. 8. European Clinical Research Infrastructure Network (ECRIN), Düsseldorf, Germany. 9. Coordination Centre for Clinical Trials, Heinrich-Heine-University, Düsseldorf. 10. Coordination Centre for Clinical Trials, Heinrich-Heine University, Düsseldorf. 11. Department of Genetic Epidemiology in Psychiatry, Institute of Central Mental Health, Medical Faculty Mannheim, University of Heidelberg. 12. Referat Klinische Studien Management, Georg-August-University Goettingen. 13. Institute of Mental Health, The University of British Columbia, Vancouver, Canada. 14. Department of Cognitive Neurology, Georg-August-University Goettingen.
Abstract
Background: The variability of responses to plasticity-inducing repetitive transcranial magnetic stimulation (rTMS) challenges its successful application in psychiatric care. No objective means currently exists to individually predict the patients' response to rTMS. Methods: We used machine learning to develop and validate such tools using the pre-treatment structural Magnetic Resonance Images (sMRI) of 92 patients with schizophrenia enrolled in the multisite RESIS trial (http://clinicaltrials.gov, NCT00783120): patients were randomized to either active (N = 45) or sham (N = 47) 10-Hz rTMS applied to the left dorsolateral prefrontal cortex 5 days per week for 21 days. The prediction target was nonresponse vs response defined by a ≥20% pre-post Positive and Negative Syndrome Scale (PANSS) negative score reduction. Results: Our models predicted this endpoint with a cross-validated balanced accuracy (BAC) of 85% (nonresponse/response: 79%/90%) in patients receiving active rTMS, but only with 51% (48%/55%) in the sham-treated sample. Leave-site-out cross-validation demonstrated cross-site generalizability of the active rTMS predictor despite smaller training samples (BAC: 71%). The predictive pre-treatment pattern involved gray matter density reductions in prefrontal, insular, medio-temporal, and cerebellar cortices, and increments in parietal and thalamic structures. The low BAC of 58% produced by the active rTMS predictor in sham-treated patients, as well as its poor performance in predicting positive symptom courses supported the therapeutic specificity of this brain pattern. Conclusions: Individual responses to active rTMS in patients with predominant negative schizophrenia may be accurately predicted using structural neuromarkers. Further multisite studies are needed to externally validate the proposed treatment stratifier and develop more personalized and biologically informed rTMS interventions.
RCT Entities:
Background: The variability of responses to plasticity-inducing repetitive transcranial magnetic stimulation (rTMS) challenges its successful application in psychiatric care. No objective means currently exists to individually predict the patients' response to rTMS. Methods: We used machine learning to develop and validate such tools using the pre-treatment structural Magnetic Resonance Images (sMRI) of 92 patients with schizophrenia enrolled in the multisite RESIS trial (http://clinicaltrials.gov, NCT00783120): patients were randomized to either active (N = 45) or sham (N = 47) 10-Hz rTMS applied to the left dorsolateral prefrontal cortex 5 days per week for 21 days. The prediction target was nonresponse vs response defined by a ≥20% pre-post Positive and Negative Syndrome Scale (PANSS) negative score reduction. Results: Our models predicted this endpoint with a cross-validated balanced accuracy (BAC) of 85% (nonresponse/response: 79%/90%) in patients receiving active rTMS, but only with 51% (48%/55%) in the sham-treated sample. Leave-site-out cross-validation demonstrated cross-site generalizability of the active rTMS predictor despite smaller training samples (BAC: 71%). The predictive pre-treatment pattern involved gray matter density reductions in prefrontal, insular, medio-temporal, and cerebellar cortices, and increments in parietal and thalamic structures. The low BAC of 58% produced by the active rTMS predictor in sham-treated patients, as well as its poor performance in predicting positive symptom courses supported the therapeutic specificity of this brain pattern. Conclusions: Individual responses to active rTMS in patients with predominant negative schizophrenia may be accurately predicted using structural neuromarkers. Further multisite studies are needed to externally validate the proposed treatment stratifier and develop more personalized and biologically informed rTMS interventions.
Authors: R Nardone; Y Höller; P B Langthaler; P Lochner; S Golaszewski; K Schwenker; F Brigo; E Trinka Journal: Spinal Cord Date: 2016-05-31 Impact factor: 2.772
Authors: Michael D Fox; Randy L Buckner; Matthew P White; Michael D Greicius; Alvaro Pascual-Leone Journal: Biol Psychiatry Date: 2012-06-01 Impact factor: 13.382
Authors: William K Silverstein; Yoshihiro Noda; Mera S Barr; Fidel Vila-Rodriguez; Tarek K Rajji; Paul B Fitzgerald; Jonathan Downar; Benoit H Mulsant; Simone Vigod; Zafiris J Daskalakis; Daniel M Blumberger Journal: Depress Anxiety Date: 2015-09-18 Impact factor: 6.505
Authors: Conor Liston; Ashley C Chen; Benjamin D Zebley; Andrew T Drysdale; Rebecca Gordon; Bruce Leuchter; Henning U Voss; B J Casey; Amit Etkin; Marc J Dubin Journal: Biol Psychiatry Date: 2014-02-05 Impact factor: 13.382
Authors: Leandro da Costa Lane Valiengo; Stephan Goerigk; Pedro Caldana Gordon; Frank Padberg; Mauricio Henriques Serpa; Stephanie Koebe; Leonardo Afonso Dos Santos; Roger Alberto Marcos Lovera; Juliana Barbosa de Carvalho; Martinus van de Bilt; Acioly L T Lacerda; Helio Elkis; Wagner Farid Gattaz; Andre R Brunoni Journal: JAMA Psychiatry Date: 2020-02-01 Impact factor: 21.596
Authors: Philipp Homan; Miklos Argyelan; Pamela DeRosse; Philip R Szeszko; Juan A Gallego; Lauren Hanna; Delbert G Robinson; John M Kane; Todd Lencz; Anil K Malhotra Journal: Neuropsychopharmacology Date: 2019-01-24 Impact factor: 7.853
Authors: Stephen J Brandt; Halimah Y Oral; Carla Arellano-Bravo; Martin H Plawecki; Tom A Hummer; Michael M Francis Journal: Neurotherapeutics Date: 2021-04-12 Impact factor: 7.620