Development of a Machine Learning Algorithm to Forecast the Likelihood of Postoperative Neurological Complications in Patients With Parotid Tumors

Abstract

Objective: The objective of this study was to create and verify a machine learning-driven predictive model to forecast the likelihood of facial nerve impairment in patients with parotid tumors following surgery. Methods: We retrospectively collected data from patients with parotid tumors between 2013 and 2023 to develop a prediction model for postoperative facial nerve dysfunction using 5 ML techniques: Logistic Regression (Logit), Random Forest (RF), XGBoost (XGB), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Predictor variables were screened using binomial-LASSO regression. Results: The study had a total of 403 participants, out of which 56 individuals encountered facial nerve damage after the surgery. By employing binomial-LASSO regression, we have successfully identified 8 crucial predictive variables: tumor kind, tumor pain, surgeon’s experience, tumor volume, basophil percentage, red blood cell count, partial thromboplastin time, and prothrombin time. The models utilizing ANN and Logit achieved higher area under the curve (AUC) values, namely 0.829, which was significantly better than the SVM model that had an AUC of 0.724. There were no noticeable disparities in the AUC values between the ANN and Logit models, as well as between these models and other techniques like RF and XGB. Conclusion: Using machine learning, our prediction model accurately predicts the likelihood that patients with parotid tumors may experience facial nerve damage following surgery. By using this model, doctors can assess patients’ risks more accurately before to surgery, and it may also help optimize postoperative treatment techniques. It is anticipated that this tool would enhance patients’ quality of life and therapeutic outcomes.