Use of Machine Learning and Statistical Algorithms to Predict Hospital Length of Stay Following Colorectal Cancer Resection: A South African Pilot Study

The aim of this pilot study was to develop logistic regression (LR) and support vector machine (SVM) models that differentiate low from high risk for prolonged hospital length of stay (LOS) in a South African cohort of 383 colorectal cancer (CRC) patients that underwent surgical resection with curative intent. Additionally, the impact of 10-fold cross-validation (CV), Monte Carlo CV and bootstrap internal validation methods on the performance of the two models was evaluated. The median LOS was nine days, and prolonged LOS was defined as greater than nine days post-operation. Pre-operative factors associated with prolonged LOS were a prior history of hypertension and an Eastern Cooperative Oncology Group (ECOG) score between 2-4. Postoperative factors related to prolonged LOS were the need for a stoma as part of the surgical procedure and the development of post-surgical complications. The risk of prolonged LOS was higher in male patients and in any patient with lower pre-operative haemoglobin (Hb). The highest AU-ROC was achieved using LR 0.823 (CI: 0.798 - 0.849) and SVM 0.821 (CI: 0.776 - 0.825), with each model using the Monte Carlo CV method for internal validation. However, bootstrapping resulted in models with slightly lower variability. We found no significant difference between the models across the three internal validation methods. The LR and SVM algorithms used in this study required incorporating important features for optimal hospital LOS predictions. Factors identified in this study, especially postoperative complications, can be employed as a simple and quick test clinician may flag a patient at risk for prolonged LOS.