Post-Operative Outcome Predictions in Vestibular Schwannoma Using Machine Learning Algorithms

Abstract

Background/Objectives: This study aimed to develop a machine learning (ML) algorithm that can predict unplanned reoperations and surgical/medical complications after vestibular schwannoma (VS) surgery. Methods: All pre- and peri-operative variables available in the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database (n = 110), except those directly related to our outcome variables, were used as input variables. A deep neural network model consisting of seven layers was developed using the Keras open-source library, with a 70:30 breakdown for training and testing. The feature importance of input variables was measured to elucidate their relative permutation effect in the ML model. Results: Of the 1783 patients with VS undergoing surgery, unplanned reoperation, surgical complications, and medical complications were seen in 8.5%, 5.2%, and 6.2% of patients, respectively. The deep neural network model had area under the curve of receiver operating characteristics (ROC-AUC) of 0.6315 (reoperation), 0.7939 (medical complications), and 0.719 (surgical complications). Accuracy, specificity, and negative predictive values of the model for all outcome variables ranged from 82.1 to 96.6%, while positive predictive values and sensitivity ranged from 16.7 to 51.5%. Variables such as the length of stay post-operation until discharge, days from operation to discharge, and the total hospital length of stay had the highest permutation importance. Conclusions: We developed an effective ML algorithm predicting unplanned reoperation and surgical/medical complications post-VS surgery. This may offer physicians guidance into potential post-surgical outcomes to allow for personalized medical care plans for VS patients.