Nomogram for predicting the response of modified electroconvulsive therapy in patients with bipolar depressive episodes: a retrospective cohort study

Depressive episodes are a major manifestation of bipolar disorder, a common mental illness associated with substantial morbidity and premature mortality. Modified electroconvulsive therapy (MECT) is an effective physical treatment for bipolar depressive episodes. However, the clinical response to MECT varies considerably among individuals, and effective predictive indicators are still lacking. This study aimed to develop a nomogram prediction model for MECT response in patients with bipolar depressive episodes.

This retrospective set study enrolled 318 patients with bipolar depressive episodes who were randomly divided into a training set (n = 222) and a validation set (n = 96) at a 7:3 ratio. Based on the MECT response, the 222 patients in the training set were classified into responders (n = 175) and non-responders (n = 47). All patients were assessed using the 17-item Hamilton Depression Rating Scale (HAMD-17), response was defined as a reduction of at least 50% in the total HAMD-17 score. Sociodemographic, clinical, electrocardiogram, and echocardiogram parameters were collected. Independent predictors were identified using univariate and multivariate logistic regression analyses, and a nomogram prediction model was constructed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration was assessed using calibration curves, and clinical applicability was evaluated using decision curve analysis (DCA). Internal validation was performed using the Bootstrap method.

Among the training set, 175 patients (78.8%) were responders and 47 (21.2%) non-responders. Multivariate logistic regression analysis revealed that higher educational level, longer P wave duration, and higher standard deviation of normal NN intervals (SDNN) were independent protective factors for MECT response, whereas increased left atrial diameter was an independent risk factor. The nomogram incorporating these four predictors achieved AUCs of 0.872 in the training set and 0.893 in the validation set. Calibration curves indicated good agreement between predicted and observed probabilities. DCA demonstrated a significant net benefit of the model.

The nomogram model, incorporating educational level, P wave duration, SDNN, and left atrial diameter, demonstrated favorable predictive performance and clinical utility for MECT response in bipolar depressive episodes. This model provides clinicians with an objective basis to early identify patients likely to benefit and optimize individualized therapies.

Not applicable.