BackgroundDistal cholangiocarcinoma (dCCA), originating from the common bile duct, is greatly associated with a dismal prognosis. A series of different studies based on cancer classification have been developed, aimed to optimize therapy and predict and improve prognosis. In this study, we explored and compared several novel machine learning models that might lead to an improvement in prediction accuracy and treatment options for patients with dCCA.MethodsIn this study, 169 patients with dCCA were recruited and randomly divided into the training cohort (n = 118) and the validation cohort (n = 51), and their medical records were reviewed, including survival outcomes, laboratory values, treatment strategies, pathological results, and demographic information. Variables identified as independently associated with the primary outcome by least absolute shrinkage and selection operator (LASSO) regression, the random survival forest (RSF) algorithm, and univariate and multivariate Cox regression analyses were introduced to establish the following different machine learning models and canonical regression model: support vector machine (SVM), SurvivalTree, Coxboost, RSF, DeepSurv, and Cox proportional hazards (CoxPH). We measured and compared the performance of models using the receiver operating characteristic (ROC) curve, integrated Brier score (IBS), and concordance index (C-index) following cross-validation. The machine learning model with the best performance was screened out and compared with the TNM Classification using ROC, IBS, and C-index. Finally, patients were stratified based on the model with the best performance to assess whether they benefited from postoperative chemotherapy through the log-rank test.ResultsAmong medical features, five variables, including tumor differentiation, T-stage, lymph node metastasis (LNM), albumin-to-fibrinogen ratio (AFR), and carbohydrate antigen 19-9 (CA19-9), were used to develop machine learning models. In the training cohort and the validation cohort, C-index achieved 0.763 vs. 0.686 (SVM), 0.749 vs. 0.692 (SurvivalTree), 0.747 vs. 0.690 (Coxboost), 0.745 vs. 0.690 (RSF), 0.746 vs. 0.711 (DeepSurv), and 0.724 vs. 0.701 (CoxPH), respectively. The DeepSurv model (0.823 vs. 0.754) had the highest mean area under the ROC curve (AUC) than other models, including SVM (0.819 vs. 0.736), SurvivalTree (0.814 vs. 0.737), Coxboost (0.816 vs. 0.734), RSF (0.813 vs. 0.730), and CoxPH (0.788 vs. 0.753). The IBS of the DeepSurv model (0.132 vs. 0.147) was lower than that of SurvivalTree (0.135 vs. 0.236), Coxboost (0.141 vs. 0.207), RSF (0.140 vs. 0.225), and CoxPH (0.145 vs. 0.196). Results of the calibration chart and decision curve analysis (DCA) also demonstrated that DeepSurv had a satisfactory predictive performance. In addition, the performance of the DeepSurv model was better than that of the TNM Classification in C-index, mean AUC, and IBS (0.746 vs. 0.598, 0.823 vs. 0.613, and 0.132 vs. 0.186, respectively) in the training cohort. Patients were stratified and divided into high- and low-risk groups based on the DeepSurv model. In the training cohort, patients in the high-risk group would not benefit from postoperative chemotherapy (p = 0.519). In the low-risk group, patients receiving postoperative chemotherapy might have a better prognosis (p = 0.035).ConclusionsIn this study, the DeepSurv model was good at predicting prognosis and risk stratification to guide treatment options. AFR level might be a potential prognostic factor for dCCA. For the low-risk group in the DeepSurv model, patients might benefit from postoperative chemotherapy.
BackgroundTo investigate the clinical significance of preoperative inflammatory status in patients with pancreatic head carcinoma (PHC), we performed a single-center study to assess it.MethodWe studied a total of 164 patients with PHC undergoing PD surgery (with or without allogeneic venous replacement) from January 2018 to April 2022. Systemic immune-inflammation index (SII) was the most important peripheral immune index in predicting the prognosis according to XGBoost analysis. The optimal cutoff value of SII for OS was calculated according to Youden index based on the receiver operating characteristic (ROC) curve and the cohort was divided into Low SII group and High SII group. Demographic, clinical data, laboratory data, follow-up data variables were obtained and compared between the two groups. Kaplan-Meier curves, univariable and multivariable Cox regression models were used to determine the association between preoperative inflammation index, nutritional index and TNM staging system with OS and DFS respectively.ResultsThe median follow-up time was 16 months (IQR 23), and 41.4% of recurrences occurred within 1 year. The cutoff value of SII was 563, with a sensitivity of 70.3%, and a specificity of 60.7%. Peripheral immune status was different between the two groups. Patients in High SII group had higher PAR, NLR than those in Low SII group (P <0.01, <0.01, respectively), and lower PNI (P <0.01). Kaplan–Meier analysis showed significantly poorer OS and DFS (P < 0.001, <0.001, respectively) in patients with high SII. By using the multivariable Cox regression model, high SII (HR, 2.056; 95% CI, 1.082–3.905, P=0.028) was significant predictor of OS. Of these 68 high-risk patients who recurrence within one year, patients with widespread metastasis had lower SII and worse prognosis (P <0.01).ConclusionHigh SII was significantly associated with poor prognosis in patients with PHC. However, in patients who recurrence within one year, SII was lower in patients at TNM stage III. Thus, care needs to be taken to differentiate those high-risk patients.
BackgroundThe preoperative prognostic nutritional index (PNI) is an indicator of systemic immune-nutritional condition and is a well-known prognostic biomarker in cancer patients. This study aims to reflect the correlation between the preoperative PNI and prognosis in patients with borderline resectable pancreatic cancer (BRPC) after pancreaticoduodenectomy (PD).MethodsMedical records of patients with BRPC after PD between Jan 2011 and Dec 2021 in our hospital were retrospectively analyzed. The preoperative PNI was calculated, and the receiver operating characteristic curve was obtained based on the preoperative PNI and the 1-year survival rate. Patients were divided into two groups (High-PNI and Low-PNI) following the best cut-off value of the preoperative PNI, and demographic and pathologic findings were compared between the two groups. Univariate and multivariate analysis were performed to identify risk factors in recurrence and long-term survival.ResultsThe best cut-off value for the preoperative PNI was 44.6 (sensitivity: 62.46%; specificity: 83.33%; area under the curve: 0.724). Patients in the low-PNI group had significantly shorter recurrence-free survival (P=0.008) and overall survival (P=0.009). The preoperative PNI (P=0.009) and lymph node metastasis (P=0.04) were independent risk factors for tumor recurrence. The preoperative PNI (P=0.001), lymph node metastasis (P=0.04), neoadjuvant chemotherapy (P=0.04) were independent risk factors for long-term survival in patients.ConclusionThe preoperative PNI, lymph node metastasis, neoadjuvant chemotherapy were independent risk factors for recurrence and long-term survival in patients with BRPC. The preoperative PNI might be an indicator that can predict BRPC patients’ recurrence and survival. Patients with high-PNI would benefit from neoadjuvant chemotherapy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.