Predicting Response to Repetitive Transcranial Magnetic Stimulation in Patients With Schizophrenia Using Structural Magnetic Resonance Imaging : A Multisite Machine Learning Analysis
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.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2018 |
|---|---|
| Erschienen: |
2018 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:44 |
|---|---|
| Enthalten in: |
Schizophrenia bulletin - 44(2018), 5 vom: 20. Aug., Seite 1021-1034 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Koutsouleris, Nikolaos [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Journal Article |
|---|
| Anmerkungen: |
Date Completed 08.02.2019 Date Revised 10.12.2019 published: Print ClinicalTrials.gov: NCT00783120 Citation Status MEDLINE |
|---|
| doi: |
10.1093/schbul/sbx114 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM27651341X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM27651341X | ||
| 003 | DE-627 | ||
| 005 | 20231225012158.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2018 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1093/schbul/sbx114 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n0921.xml |
| 035 | |a (DE-627)NLM27651341X | ||
| 035 | |a (NLM)28981875 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Koutsouleris, Nikolaos |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Predicting Response to Repetitive Transcranial Magnetic Stimulation in Patients With Schizophrenia Using Structural Magnetic Resonance Imaging |b A Multisite Machine Learning Analysis |
| 264 | 1 | |c 2018 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 08.02.2019 | ||
| 500 | |a Date Revised 10.12.2019 | ||
| 500 | |a published: Print | ||
| 500 | |a ClinicalTrials.gov: NCT00783120 | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 520 | |a 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 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Multicenter Study | |
| 650 | 4 | |a Randomized Controlled Trial | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Wobrock, Thomas |e verfasserin |4 aut | |
| 700 | 1 | |a Guse, Birgit |e verfasserin |4 aut | |
| 700 | 1 | |a Langguth, Berthold |e verfasserin |4 aut | |
| 700 | 1 | |a Landgrebe, Michael |e verfasserin |4 aut | |
| 700 | 1 | |a Eichhammer, Peter |e verfasserin |4 aut | |
| 700 | 1 | |a Frank, Elmar |e verfasserin |4 aut | |
| 700 | 1 | |a Cordes, Joachim |e verfasserin |4 aut | |
| 700 | 1 | |a Wölwer, Wolfgang |e verfasserin |4 aut | |
| 700 | 1 | |a Musso, Francesco |e verfasserin |4 aut | |
| 700 | 1 | |a Winterer, Georg |e verfasserin |4 aut | |
| 700 | 1 | |a Gaebel, Wolfgang |e verfasserin |4 aut | |
| 700 | 1 | |a Hajak, Göran |e verfasserin |4 aut | |
| 700 | 1 | |a Ohmann, Christian |e verfasserin |4 aut | |
| 700 | 1 | |a Verde, Pablo E |e verfasserin |4 aut | |
| 700 | 1 | |a Rietschel, Marcella |e verfasserin |4 aut | |
| 700 | 1 | |a Ahmed, Raees |e verfasserin |4 aut | |
| 700 | 1 | |a Honer, William G |e verfasserin |4 aut | |
| 700 | 1 | |a Dwyer, Dominic |e verfasserin |4 aut | |
| 700 | 1 | |a Ghaseminejad, Farhad |e verfasserin |4 aut | |
| 700 | 1 | |a Dechent, Peter |e verfasserin |4 aut | |
| 700 | 1 | |a Malchow, Berend |e verfasserin |4 aut | |
| 700 | 1 | |a Kreuzer, Peter M |e verfasserin |4 aut | |
| 700 | 1 | |a Poeppl, Tim B |e verfasserin |4 aut | |
| 700 | 1 | |a Schneider-Axmann, Thomas |e verfasserin |4 aut | |
| 700 | 1 | |a Falkai, Peter |e verfasserin |4 aut | |
| 700 | 1 | |a Hasan, Alkomiet |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Schizophrenia bulletin |d 1974 |g 44(2018), 5 vom: 20. Aug., Seite 1021-1034 |w (DE-627)NLM000023388 |x 1745-1701 |7 nnns |
| 773 | 1 | 8 | |g volume:44 |g year:2018 |g number:5 |g day:20 |g month:08 |g pages:1021-1034 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1093/schbul/sbx114 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 44 |j 2018 |e 5 |b 20 |c 08 |h 1021-1034 | ||