Kenjiro Kotake

Background: Owing to significant clinical heterogeneity, the achievement of accurate survival forecasting for individuals with colorectal cancer and peritoneal metastasis continues to be a complex undertaking. We aimed to transcend traditional prognostic limitations by evaluating machine learning boosting models against standard regression-based methods in terms of estimating overall survival (OS). Methods: Utilizing a multi-institutional registry of 150 patients diagnosed with synchronous peritoneal metastasis of colorectal cancer, we integrated 124 clinicopathological variables to refine our predictive models. Beyond standard preprocessing—including standardization and median imputation—we rigorously compared XGBoost and LightGBM against Ridge, Lasso, and linear regression via five-fold cross-validation. To specifically address right-censoring, an XGBoost Cox model was implemented and validated using Harrell’s C-index, with SHAP and LIME providing essential model interpretability. Results: Boosting models consistently outperformed linear alternatives, which struggled with high error rates and negative R2 values. Specifically, XGBoost achieved an MAE of 475 ± 60 and an RMSE of 585 ± 88. The XGBoost Cox model reached a C-index of 0.64 ± 0.06. SHAP analysis highlighted inflammatory markers and peritoneal disease extent as the most influential prognostic drivers. Conclusions: While boosting models offer a clear accuracy advantage over linear methods, their prognostic power remains moderate. These findings underscore the potential of ensemble learning in oncology, yet mandate external validation before these tools can be integrated into clinical decision-making.

Background: Prognostic prediction for colorectal cancer patients with peritoneal metastasis remains challenging due to clinical and biological heterogeneity. We aimed to evaluate the utility of machine learning, comparing high-performance boosting models with interpretable regression approaches for overall survival (OS) prediction. Methods: We analyzed a multi-institutional registry cohort of 150 colorectal cancer patients with synchronous peritoneal metastases. A total of 124 variables were included; continuous variables were standardized, categorical variables were one-hot encoded, and missing values were imputed using the median. Models included XGBoost, LightGBM, Ridge regression, Lasso regression, and linear regression. Training was performed with 3-fold cross-validation, and hyperparameters were optimized using Optuna. Evaluation metrics included mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²). Model interpretability was assessed using SHAP values, LIME local explanations, and regression coefficients. Results: Boosting models consistently outperformed linear models. XGBoost achieved the best performance (MAE 424, RMSE 526, R² = 0.04), while LightGBM showed comparable accuracy. In contrast, Ridge, Lasso, and Linear regression yielded high errors (MAE > 900, RMSE > 1200) with negative R² values, indicating poor predictive ability. SHAP analysis highlighted systemic inflammation markers (CRP, BUN), surgical assessment of tumor depth, operative factors (time, bleeding), and peritoneal metastasis characteristics as major determinants of OS. LIME analyses further provided case-specific interpretability, identifying feature contributions in long-, intermediate-, and short-term survivors. Conclusion: Boosting models, particularly XGBoost, demonstrated superior performance compared with traditional regression models in predicting OS for colorectal cancer patients with peritoneal metastasis, although absolute predictive accuracy remains modest. Integration of SHAP and LIME linked model outputs with clinically plausible prognostic factors, enhancing interpretability. Ensemble learning may provide a promising adjunct for prognostic assessment and should be validated in larger, genomically enriched cohorts.

Introduction: Two-stage hepatectomy (TSH) enables patients to undergo surgery for colorectal liver metastasis (CRLM), which one-stage hepatectomy cannot remove. Although the outcome of TSH has been reported, there is no original report from Japan. The aim of this retrospective study was to evaluate the outcome of TSH in Japanese patients with CRLM. Methods: The authors conducted a retrospective cohort study using the nationwide database that included clinical information of 12 519 patients treated with CRLM between 2005 and 2017 in Japan. The primary outcome measure was overall survival. The second outcome measure was progression-free survival. Fisher’s exact test, χ² test and Mann–Whitney U test were conducted to examine an intergroup difference. Univariate and multivariate analyses were performed using Cox regression model. Survival analysis was performed by Kaplan–Meier method and log-rank test. Results: Of the database, 53 patients undergoing TSH using portal vein embolization (PVE) were identified and analyzed. Their morbidity and in-hospital mortality rates at the second hepatectomy were 26.4% and 0.0%. The mean observation period was 21.8 months. The estimated 1-, 3- and 5-year overall survival rate were 92.5%, 70.8% and 34.7%. Multivariate analyses showed that more than 10 liver nodules significantly increased the mortality risk by 4.2-fold (95% CI 1.224–14.99, P= 0.023). Survival analysis revealed that repeat hepatectomy for disease progression after TSH was superior to chemotherapy in overall survival (mean: 49.6 vs. 18.7, months, P= 0.004). Conclusion: In the Japanese cohort, TSH was confirmed to be a safety procedure with an acceptable survival outcome. More than 10 liver nodules may be a predictor for unfavorable outcomes of patients with CRLM undergoing TSH. Furthermore, repeat hepatectomy can be a salvage treatment for resectable intrahepatic recurrence after TSH.