Machine Learning to Predict Early Recurrence After Oesophageal Cancer Surgery

Abstract

Background: Early cancer recurrence after oesophagectomy is a common problem, with an incidence of 20-30 per cent despite the widespread use of neoadjuvant treatment. Quantification of this risk is difficult and existing models perform poorly. This study aimed to develop a predictive model for early recurrence after surgery for oesophageal adenocarcinoma using a large multinational cohort and machine learning approaches.Methods: Consecutive patients who underwent oesophagectomy for adenocarcinoma and had neoadjuvant treatment in one Dutch and six UK oesophagogastric units were analysed. Using clinical characteristics and postoperative histopathology, models were generated using elastic net regression (ELR) and the machine learning methods random forest (RF) and extreme gradient boosting (XGB). Finally, a combined (ensemble) model of these was generated. The relative importance of factors to outcome was calculated as a percentage contribution to the model.Results: A total of 812 patients were included. The recurrence rate at less than 1 year was 29⋅1 per cent. All of the models demonstrated good discrimination. Internally validated areas under the receiver operating characteristic (ROC) curve (AUCs) were similar, with the ensemble model performing best (AUC 0⋅791 for ELR, 0⋅801 for RF, 0⋅804 for XGB, 0⋅805 for ensemble). Performance was similar when internal-external validation was used (validation across sites, AUC 0⋅804 for ensemble). In the final model, the most important variables were number of positive lymph nodes (25⋅7 per cent) and lymphovascular invasion (16⋅9 per cent). Conclusion:The model derived using machine learning approaches and an international data set provided excellent performance in quantifying the risk of early recurrence after surgery, and will be useful in prognostication for clinicians and patients.

Predicting Long-term Survival and Time-to-recurrence After Esophagectomy in Patients With Esophageal Cancer

“…Predictor variables that have the most significant impact on survival and recurrence are consistent with clinical experience and published literature. These include advanced pathological stage, lymphovascular invasion, poor tumor differentiation, and positive margin status 7,8,17. Pathological tumor staging at the time of surgery was preferred in variable selection due to its relatively increased accuracy over the clinical tumor stage (determined before surgery), which often over-stages patients 34.…”

“…Predictor variables were selected based on the literature review and clinical importance 7,8,17. A full list of variables considered for inclusion can be found in Supplementary Table 1 (Supplemental Digital Content 1, http://links.lww.com/SLA/D930).…”

“…The final variables used in model development were determined from a subset of preselected variables chosen based on a literature review and clinical importance 7,8,17. Permutation-based RSF variable importance (VIMP) with bootstrapped confidence intervals (CIs) was used for OS and DFS with any predictors demonstrating a VIMP>0 being included in the final model (Supplementary Tables 3, 4, Supplemental Digital Content 1, http://links.lww.com/SLA/D930).…”

“…The final variables used in model development were determined from a subset of preselected variables chosen based on a literature review and clinical importance. 7,8,17 Permutationbased RSF variable importance (VIMP) with bootstrapped confidence intervals (CIs) was used for OS and DFS with any predictors demonstrating a VIMP > 0 being included in the final model (Supplementary Tables 3, 4, Supplemental Digital Content 1, http://links.lww.com/SLA/D930). The models were trained using 16 variables: patient age, sex, American Society of Anesthesiology grade, tumor location, resection margin status, clinical N stage, pathological TNM stage, differentiation grade, histology subtype, lymphatic invasion, venous invasion, tumor regression grade, treatment protocol, Clavien-Dindo grade.…”

“…Nonetheless, a paucity of evidence exists in the literature concerning prognostication for esophageal cancer 15. Existing models have failed to gain widespread clinical use or advocation as a “gold standard,” with the lack of actionable guidance limiting overall utility 16–20. Advances in machine learning (ML) techniques, with random survival forest (RSF) models, in particular, have demonstrated promising results in multiple settings and have been used for esophageal cancer in developing the seventh and eighth editions of the TNM staging manuals,11,13,16 but performance in a clinical environment when compared with traditional statistical methods remains as yet unresolved.…”