Applying Machine Learning to Predict Esophageal Cancer Recurrence after Esophagectomy

Artificial intelligence and machine learning (ML) models have recently been adapted to healthcare applications with promising results. The objective of this proof-of-concept study was to develop an ML model designed to predict esophageal cancer recurrence after esophagectomy. We conducted a retrospective study of 260 consecutive patients who underwent esophagectomy for esophageal cancer from 2009 through 2018. Patient-specific characteristics were collected. Risk prediction models for different prediction windows were constructed via a sequential forward selection process. To enhance the robustness of this framework, five traditional machine learning algorithms including Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Naive Bayes (NB) were implemented in our analysis. Model performance was assessed by calculating sensitivity, specificity, positive predictive value (PPV), F1 score, area under the receiver operating characteristic curve (AUC), and overall accuracy using five-fold cross-validation. Feature importance analysis was conducted to provide insights into important risk factors associated with esophageal cancer recurrence.