The prevalence and recurrence rate of depressive disorder are high, while the recognition and cure rate are low. Early intervention can improve the quality of life of patients with depression. In clinical practice, it has been found that psychological treatments can effectively improve the symptoms and prognosis of depression.Cognitive behavior therapy(CBT) has been widely used in the treatment of depression, however, its mechanisms are still unclear. In this paper, the neuroimaging studies of patients with depression before and after CBT were summarized, and the structural or functional changes of different brain regions in patients with depression before and after CBT were described. The findings suggest that CBT improved depressive symptoms by increasing gray matter volume, activation level, and functional connectivity strength in the dorsolateral prefrontal cortex, reducing activation levels in the amygdala and parahippocampal gyrus, and restoring abnormal brain network activity or functional connectivity. Larger gray matter volume in anterior cingulate gyrus and higher activation levels in hippocampus and amygdala before treatment can effectively predict the effect of CBT in depressed patients. In the future, machine learning could be combined with brain imaging data to more accurately predict the effectiveness of CBT in treating depression.

Background: Exploratory eye movements (EEMs) and P300 are often used to facilitate the clinical diagnosis of depression. However, There were few studies using the combination of EEMs and P300 to build a model for detecting depression and predicting a curative effect. Methods: Sixty patients were recruited for 2 groups: high frequency repetitive transcranial magnetic stimulation (rTMS) combined with paroxetine group and simple paroxetine group. Clinical efficacy was evaluated by the Hamilton Depression scale-24(HAMD-24), EEMs and P300. The classification model of the auxiliary diagnosis of depression and the prediction model of the two treatments were developed based on a machine learning algorithm. Results: The classification model with the greatest accuracy for patients with depression and healthy controls was 95.24% (AUC = 0.75, recall = 1.00, precision = 0.95, F1-score = 0.97). The root mean square error (RMSE) of the model for predicting the efficacy of high frequency rTMS combined with paroxetine was 3.54 (MAE [mean absolute error] = 2.56, R-2 = -0.53). The RMSE of the model for predicting the efficacy of paroxetine was 4.97 (MAE = 4.00, R-2 = -0.91). Conclusion: Based on the machine learning algorithm, P300 and EEMs data was suitable for modeling to distinguish depression patients and healthy individuals. However, it was not suitable for predicting the efficacy of high frequency rTMS combined with paroxetine or to predict the efficacy of paroxetine.

强迫症的治疗现状 有赖于现代媒体的宣传与科普宣教,强迫症作为精神科的"顽疾"之一,如今在普通人群中也拥有极高的知名度.反复洗手、反复检查门窗、害怕猫狗及传染病……这些体验其实也常常发生在普通人身上,然而洗手终有净时,检查后也终归放心,害怕猫狗更可绕行,随后也就能继续自己的日常生活了.但对于真正的强迫症病人而言,思想和行为就此滞留,随之而来的是洪水猛兽般的穷思竭虑,这是健康人很难感同身受到的痛苦.国外资料显示强迫症的终生患病率高达2％1,这种以持续的强迫思维和反复的强迫动作为主要临床特征的常见疾病难以治愈,除此之外还具有起病早、病情迁延、易复发、易致残等特点,不仅家属为之焦虑,患者为之痛苦,连医生也为之头疼,可谓是精神科公认的"难题".