Machine learning to predict early recurrence after oesophageal cancer surgery
Research output: Contribution to journal › Article › peer-review
Colleges, School and Institutes
- Faculty of Medicine, Cancer Sciences Academic Unit, University of Southampton, Southampton SO16 6YD, UK.
- Department of Surgery, University Medical Centre, Utrecht, the Netherlands.
- Department of Public Health Sciences and Medical Statistics, University of Southampton, Southampton, UK.
- Department of Surgery, Nottingham University Hospitals NHS Trust, Nottingham, UK.
- Department of Surgery, Portsmouth Hospitals NHS Trust, Portsmouth, UK.
- Department of Upper Gastrointestinal Surgery, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK.
- Cambridge Oesophagogastric Centre, Addenbrookes Hospital, Cambridge University Hospitals Foundation Trust, Cambridge, UK.
- Centre for Cancer Research and Cell Biology, Queen's University Belfast, Belfast, UK.
- Medical Research Council Cancer Unit, Hutchison/Medical Research Council Research Centre, University of Cambridge, Cambridge, UK. Electronic address: email@example.com.
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.
|Journal||British Journal of Surgery|
|Early online date||30 Jan 2020|
|Publication status||E-pub ahead of print - 30 Jan 2020|