Predicting the need for electroconvulsive therapy via machine learning trained on electronic health record data

Objective Electroconvulsive therapy (ECT) is an effective treatment of severe manifestations of mental illness. Since delay in initiation of ECT can have detrimental effects, prediction of the need for ECT could improve outcomes via more timely treatment initiation. This study aimed to predict the need for ECT following admission to a psychiatric hospital. Methods This cohort study was based on electronic health record (EHR) data from routine clinical practice. Adult patients admitted to a hospital within the Psychiatric Services of the Central Denmark Region between January 2013 and November 2021 were included in the study. The outcome was initiation of ECT >7 days (to not include patients admitted for planned ECT) and ≤67 days after admission. The data was randomly split into an 85% training set and a 15% test set. On the 7 th day of the inpatient stay, machine learning models (extreme gradient boosting (XGBoost)) were trained to predict initiation of ECT and subsequently tested on the test set, using the area under the receiver operating characteristic curve (AUROC) as the main performance measure. Results The cohort consisted of 41,610 patients with 164,961 admissions eligible for prediction. In the test set the trained model predicted ECT initiation with an AUROC of 0.94, 47% sensitivity, 98% specificity, positive predictive value of 24% and negative predictive value of 99%. The top predictors were the highest suicide assessment score and the mean Brøset violence checklist score in the preceding three months. Conclusions EHR data from routine clinical practice can be used to predict need for ECT. This may lead to more timely treatment initiation.