Electroencephalography-based Precise Repetitive Transcranial Magnetic Stimulation Treatment

Major depression disorder (MDD) is increasingly conceptualized as a disorder of brain networks, which related to dysregulation of functional connectivity. rTMS has the advantages of being safe, non-invasive and well-tolerated, and has been clarified by the FDA to be used in the treatment of depression with some positive efficacy. Machine learning based on EEG data, exploring machine learning and big data analytics methods, and applying the output reference value recommendations to the personalized treatment of depressed patients are expected to be more effective in promoting the alleviation of patients' depressive symptoms. Every participant meeting the inclusion criteria will be fully informed of the study and be asked to sign the written informed consent before enrollment. Outpatient physicians will conduct the initial screening, collecting all diagnostic and medication information from the medical records at each follow-up visit. Several psychiatrists, all of whom are qualified and well-trained, will conduct clinical assessments at baseline and follow-up at the end of weekly TMS treatments, as well as clinical follow-up 3 months after the end of treatment. Clinical assessments will include HAMD, HAMA, CGI scale and etc. EEG parameter assessments will include changes in alpha-band spectral connectivity at baseline and after every 5 TMS treatments. During the treatment period, patients will be randomly grouped into the precision group, which will be treated with rTMS based on personalized modulation of EEG data, and the conventional group, which will be treated with TMS at a frequency of 10 Hz to stimulate the left dorsolateral prefrontal cortex (DLPFC). The treatments will be administered once a day, 5 times a week for 4 weeks, totaling 20 sessions. At the end of each week's treatment the patient's EEG will be recorded and the patient will be clinically evaluated by a qualified and well-trained psychiatrist. The original medication regimen will be maintained as much as possible during the treatment period, and adverse effects such as headaches will be faithfully recorded. The sample size calculation for this study was based on a priori power analysis using G\*Power 3.1.9.7. Among the imputed parameters it was chosen to include α = 0.05, power (1-ß) = 0.9. We used effect size f = 0.2 as parameter for the effect size estimation, based on the findings from previous study reported that the depressive symptom changes before and after rTMS intervention in patients with MDD. Two groups, corresponding to the two experimental conditions of the study, and age, sex, educational level, symptom, in total of 4 covariates were included. Taking into account a dropout rate of 15%, the final estimated number of participants is 70.