LAUSR

BACKGROUND Surgical intervention remains the cornerstone of a multidisciplinary approach in the treatment of colorectal liver metastases (CLM). Nevertheless, patient outcomes vary greatly. While predictive tools can assist decision-making and patient counseling, decades of efforts have yet to result in generating a universally adopted tool in clinical practice. STUDY DESIGN An international collaborative database of CLM patients who underwent surgical therapy between 2000 and 2018 was used to select 1004 operations for this study. Two different machine learning methods were applied to construct two predictive models for recurrence and death, using 128 clinicopathologic variables: gradient-boosted trees (GBTs) and logistic regression with bootstrapping (LRB) - in a leave-one-out cross-validation. RESULTS Median survival after resection was 47.2 months, and disease-free survival was 19.0 months, with a median follow-up of 32.0 months in the cohort. Both models had good predictive power, with GBT demonstrating a superior performance in predicting overall survival (area under the receiver operating curve [AUC]: 0.773, 95%CI: 0.743-0.801 vs. LRB with AUC: 0.648, 95%CI: 0.614-0.682), and recurrence (AUC: 0.635, 95% CI: 0.599-0.669 vs. LRB with AUC: 0.570, 95%CI: 0.535-0.601). Similarly, better performances were observed predicting 3-year and 5-year survival, as well as 3-year and 5-year recurrence with GBT methods generating a higher AUC. CONCLUSION Machine learning provides powerful tools to create predictive models of survival and recurrence after surgery for CLM. The effectiveness of both machine learning models varies, but on most occasions, GBT outperforms LRB. Prospective validation of these models lays the groundwork to adopt them in clinical practice.