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.
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.
J Affect Disord. 2019 Jun 1;252:47-54. doi: 10.1016/j.jad.2019.03.077. Epub 2019 Mar 30.
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.
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.
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).
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.
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.
重复经颅磁刺激（TMS）对重度抑郁症（MDD）具有临床疗效，对包括创伤后应激障碍（PTSD）在内的其他病症也在进行研究。了解 TMS 作用机制并开发预测反应的生物标志物仍然是重要目标。我们应用了机器学习和脑电图（EEG）相结合的方法，测试了机器学习对 EEG 相干性的分析是否会（1）预测 MDD 和 PTSD 共病患者的临床结局，以及（2）确定个体是否接受了 TMS 疗程。
我们在 TMS（左背外侧前额叶 5Hz）前后采集了 8 通道静息状态 EEG。我们使用 Lasso 回归和支持向量机（SVM）来检验假设，即基线 EEG 相干性预测治疗结果，并评估 TMS 后 EEG 相干性是否发生变化。
在我们的样本中，TMS 的临床疗效可以根据治疗前的 EEG 相干性进行预测（n=29）。治疗后，29 例中有 13 例 MDD 自我报告评分降低超过 50%，12 例 PTSD 自我报告评分降低超过 50%。对于 MDD，ROC 曲线下面积为 0.83（95%置信区间为 0.69-0.94），对于 PTSD 为 0.71（95%置信区间为 0.54-0.87）。SVM 分类器能够准确地将 EEG 记录分配到 TMS 治疗前后。Alpha、Beta、Theta 和 Delta 频段的准确率分别为 75.4±1.5%、77.4±1.4%、73.8±1.5%和 78.6±1.4%，均显著高于 50%（p<0.001）。
这项工作的局限性包括缺乏假治疗条件、样本量适中以及电极排列稀疏。尽管存在这些方法学上的限制，但我们仍发现了具有验证性和临床意义的结果。
机器学习成功地以高特异性预测了 TMS 的无反应性，并使用 EEG 相干性识别了 TMS 治疗前后的状态。这种方法可能提供机制上的见解，并可能成为 TMS 候选者的一种有用的临床筛选工具。
