Abstract: Objective  To explore the predictive value of microRNA-19b-3p (miR-19b-3p)evaluated by Logistic regression combined with ROC curve in the treatment of depression. 
Methods  A total of 112 patients with depression admitted to our hospital were selected as the research subjects (case group), and 60 healthy volunteers who presented to our hospital for physical examination during the same period were selected as the control group. The expression levels of peripheral serum miR-19b-3p in all subjects were detected by real-time quantitative polymerase chain reaction (PCR), and the expression levels of serum miR-19b-3p in the two groups before treatment and changes in the expression levels of serum miR-19b-3p in the case group before and after treatment were compared. According to the therapeutic effect, the case group was subdivided into a good prognosis group and a poor prognosis group, and the serum miR-19b-3p expression levels and other factors were compared between the good prognosis group and the poor prognosis group. Logistic regression analysis was used to identify the risk factors for poor prognosis in patients with depression, and receiver operating characteristic (ROC) curve was drawn to analyze the predictive value of serum miR-19b-3p expression levels before and after treatment for poor prognosis in patients with depression. 
Results  Before treatment, the serum miR-19b-3p level in the case group was higher than that in the control group (P＜0.05), and after treatment, the serum miR-19b-3p level in the case group was lower than that before treatment (P＜0.05). Family history of depression (positive), poor treatment compliance, poor family social support, poor relationship with neighbors, the proportion of major life events, the number of episodes, and serum miR-19b-3p levels before and after treatment were higher in the poor prognosis group than in the good prognosis group (P＜0.05). Logistic regression analysis showed that poor treatment compliance, poor family social support, associated psychotic symptoms, miR-19b-3p (before and after treatment), and major life events were all risk factors for poor prognosis in patients with depression (P＜0.05). ROC curve analysis showed that the area under the ROCcurve (AUC), sensitivity, specificity and the optimal cut-off point of serum mir-19b-3p level before treatment in predicting the poor prognosis of patients with depression were 0.739, 78.56%, 64.28%, and 11.25, respectively. The AUC, sensitivity, specificity, and optimal cut-off point of serum miR-19b-3p levels after treatment in predicting poor prognosis in patients with depression were 0.756, 80.75%, 60.15%, and 7.14, respectively. 
Conclusion  Serum miR-19b-3p is abnormally highly expressed in patients with depression, which has a certain relationship with the poor prognosis of patients with depression, and can be used to predict the prognosis of patients with depression.

Key words: depressive disorder, miR-19b-3p, prognosis