Amin Zandvakili1, Noah S Philip2, Stephanie R Jones3, Audrey R Tyrka4, Benjamin D Greenberg2, Linda L Carpenter4. 1. Butler Hospital, Providence, RI 02906, United States; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI 02906, United States; Center for Neurorestoration and Neurotechnology, Providence VA Medical Center, Providence, RI 02908, United States. Electronic address: amin_zandvakili@brown.edu. 2. Butler Hospital, Providence, RI 02906, United States; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI 02906, United States; Center for Neurorestoration and Neurotechnology, Providence VA Medical Center, Providence, RI 02908, United States. 3. Center for Neurorestoration and Neurotechnology, Providence VA Medical Center, Providence, RI 02908, United States; Department of Neuroscience, Brown University, Providence, RI 02906, United States. 4. Butler Hospital, Providence, RI 02906, United States; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI 02906, United States.
Abstract
BACKGROUND: Repetitive transcranial magnetic stimulation (TMS) is clinically effective for major depressive disorder (MDD) and investigational for other conditions including posttraumatic stress disorder (PTSD). Understanding the mechanisms of TMS action and developing biomarkers predicting response remain important goals. We applied a combination of machine learning and electroencephalography (EEG), testing whether machine learning analysis of EEG coherence would (1) predict clinical outcomes in individuals with comorbid MDD and PTSD, and (2) determine whether an individual had received a TMS course. METHODS: We collected resting-state 8-channel EEG before and after TMS (5 Hz to the left dorsolateral prefrontal cortex). We used Lasso regression and Support Vector Machine (SVM) to test the hypothesis that baseline EEG coherence predicted the outcome and to assess if EEG coherence changed after TMS. RESULTS: In our sample, clinical response to TMS were predictable based on pretreatment EEG coherence (n = 29). After treatment, 13/29 had more than 50% reduction in MDD self-report score 12/29 had more than 50% reduction in PTSD self-report score. For MDD, area under roc curve was for MDD was 0.83 (95% confidence interval 0.69-0.94) and for PTSD was 0.71 (95% confidence interval 0.54-0.87). SVM classifier was able to accurately assign EEG recordings to pre- and post-TMS treatment. The accuracy for Alpha, Beta, Theta and Delta bands was 75.4 ± 1.5%, 77.4 ± 1.4%, 73.8 ± 1.5%, and 78.6 ± 1.4%, respectively, all significantly better than chance (50%, p < 0.001). LIMITATION: Limitations of this work include lack of sham condition, modest sample size, and a sparse electrode array. Despite these methodological limitations, we found validated and clinically meaningful results. CONCLUSIONS: Machine learning successfully predicted non-response to TMS with high specificity, and identified pre- and post-TMS status using EEG coherence. This approach may provide mechanistic insights and may also become a clinically useful screening tool for TMS candidates.
BACKGROUND: Repetitive transcranial magnetic stimulation (TMS) is clinically effective for major depressive disorder (MDD) and investigational for other conditions including posttraumatic stress disorder (PTSD). Understanding the mechanisms of TMS action and developing biomarkers predicting response remain important goals. We applied a combination of machine learning and electroencephalography (EEG), testing whether machine learning analysis of EEG coherence would (1) predict clinical outcomes in individuals with comorbid MDD and PTSD, and (2) determine whether an individual had received a TMS course. METHODS: We collected resting-state 8-channel EEG before and after TMS (5 Hz to the left dorsolateral prefrontal cortex). We used Lasso regression and Support Vector Machine (SVM) to test the hypothesis that baseline EEG coherence predicted the outcome and to assess if EEG coherence changed after TMS. RESULTS: In our sample, clinical response to TMS were predictable based on pretreatment EEG coherence (n = 29). After treatment, 13/29 had more than 50% reduction in MDD self-report score 12/29 had more than 50% reduction in PTSD self-report score. For MDD, area under roc curve was for MDD was 0.83 (95% confidence interval 0.69-0.94) and for PTSD was 0.71 (95% confidence interval 0.54-0.87). SVM classifier was able to accurately assign EEG recordings to pre- and post-TMS treatment. The accuracy for Alpha, Beta, Theta and Delta bands was 75.4 ± 1.5%, 77.4 ± 1.4%, 73.8 ± 1.5%, and 78.6 ± 1.4%, respectively, all significantly better than chance (50%, p < 0.001). LIMITATION: Limitations of this work include lack of sham condition, modest sample size, and a sparse electrode array. Despite these methodological limitations, we found validated and clinically meaningful results. CONCLUSIONS: Machine learning successfully predicted non-response to TMS with high specificity, and identified pre- and post-TMS status using EEG coherence. This approach may provide mechanistic insights and may also become a clinically useful screening tool for TMS candidates.
Authors: M Jandl; R Bittner; A Sack; B Weber; T Günther; D Pieschl; W-P Kaschka; K Maurer Journal: J Neural Transm (Vienna) Date: 2004-10-27 Impact factor: 3.575
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: Alik S Widge; M Taha Bilge; Rebecca Montana; Weilynn Chang; Carolyn I Rodriguez; Thilo Deckersbach; Linda L Carpenter; Ned H Kalin; Charles B Nemeroff Journal: Am J Psychiatry Date: 2018-10-03 Impact factor: 18.112
Authors: Xingbao Li; Ziad Nahas; F Andrew Kozel; Berry Anderson; Daryl E Bohning; Mark S George Journal: Biol Psychiatry Date: 2004-05-01 Impact factor: 13.382
Authors: Ahmad Khodayari-Rostamabad; James P Reilly; Gary M Hasey; Hubert de Bruin; Duncan J Maccrimmon Journal: Clin Neurophysiol Date: 2013-05-15 Impact factor: 3.708
Authors: Yunan Xu; Yizi Lin; Ryan P Bell; Sheri L Towe; John M Pearson; Tauseef Nadeem; Cliburn Chan; Christina S Meade Journal: J Neurovirol Date: 2021-01-19 Impact factor: 2.643
Authors: Gloria Obuobi-Donkor; Vincent Israel Opoku Agyapong; Ejemai Eboreime; Jennifer Bond; Natalie Phung; Scarlett Eyben; Jake Hayward; Yanbo Zhang; Frank MacMaster; Steven Clelland; Russell Greiner; Chelsea Jones; Bo Cao; Suzette Brémault-Phillips; Kristopher Wells; Xin-Min Li; Carla Hilario; Andrew J Greenshaw Journal: JMIR Res Protoc Date: 2022-04-25
Authors: Nicholas J Petrosino; Camila Cosmo; Yosef A Berlow; Amin Zandvakili; Mascha van 't Wout-Frank; Noah S Philip Journal: Ther Adv Psychopharmacol Date: 2021-10-28
Authors: Gonzalo Salazar de Pablo; Erich Studerus; Julio Vaquerizo-Serrano; Jessica Irving; Ana Catalan; Dominic Oliver; Helen Baldwin; Andrea Danese; Seena Fazel; Ewout W Steyerberg; Daniel Stahl; Paolo Fusar-Poli Journal: Schizophr Bull Date: 2021-03-16 Impact factor: 9.306