Development of a model based on the age-adjusted Charlson comorbidity index to predict survival for resected perihilar cholangiocarcinoma

Machine learning model to predict early recurrence in patients with perihilar cholangiocarcinoma planned treatment with curative resection: a multicenter study

BACKGROUND

Early recurrence is the leading cause of death for patients with perihilar cholangiocarcinoma (pCCA) after surgery. Identifying high-risk patients preoperatively is important. This study aimed to construct a preoperative prediction model for the early recurrence of patients with pCCA to facilitate planned treatment with curative resection.

METHODS

This study ultimately enrolled 400 patients with pCCA after curative resection in 5 hospitals between 2013 and 2019. They were randomly divided into training (n = 300) and testing groups (n = 100) at a ratio of 3:1. Associated variables were identified via least absolute shrinkage and selection operator (LASSO) regression. Four machine learning models were constructed: support vector machine, random forest (RF), logistic regression, and K-nearest neighbors. The predictive ability of the models was evaluated via receiving operating characteristic (ROC) curves, precision-recall curve (PRC) curves, and decision curve analysis. Kaplan-Meier (K-M) survival curves were drawn for the high-/low-risk population.

RESULTS

Five factors: carbohydrate antigen 19-9, tumor size, total bilirubin, hepatic artery invasion, and portal vein invasion, were selected by LASSO regression. In both the training and testing groups, the ROC curve (area under the curve: 0.983 vs 0.952) and the PRC (0.981 vs 0.939) showed that RF was the best. The cutoff value for distinguishing high- and low-risk patients was 0.51. K-M survival curves revealed that in both groups, there was a significant difference in RFS between high- and low-risk patients (P < .001).

CONCLUSION

This study used preoperative variables from a large, multicenter database to construct a machine learning model that could effectively predict the early recurrence of pCCA in patients to facilitate planned treatment with curative resection and help clinicians make better treatment decisions.

Marital status as an independent prognostic factor for survival in women with vaginal cancer: evidence from the SEER database analysis

This study aimed to evaluate the influence of marital status on the survival outcomes of women diagnosed with vaginal cancer, considering the potential role of sociodemographic factors in patient prognosis. Utilizing data from the Surveillance, Epidemiology, and End Results database, the study included 6046 women with primary vaginal cancer diagnosed between 2000 and 2020. The propensity score matching (PSM) method was employed to balance comparison groups and account for confounding factors. The primary outcomes were overall survival (OS) and cancer-specific survival (CSS), with Cox proportional-hazards regression models used for statistical analysis. Married patients exhibited better survival outcomes than their unmarried counterparts [OS: hazard ratio = 1.520, 95% confidence interval (CI) = 1.430-1.630, P < 0.001; CSS: hazard ratio = 1.380, 95% CI = 1.270-1.490, P < 0.001]. Subgroup analyses stratified by age and race highlighted a significant survival benefit for married individuals, particularly those aged 50-69 years and white patients. After PSM, the widowed subgroup within the unmarried category showed worse survival outcomes (OS: hazard ratio = 1.580, 95% CI = 1.430-1.750, P < 0.001; CSS: hazard ratio = 1.360, 95% CI = 1.200-1.530, P < 0.001). This study demonstrates that marital status serves as an independent prognostic factor for OS and CSS among patients with primary vaginal cancer, which supports that unmarried people need more individualized care strategies.

Association between Pre-operative Body Mass Index and Surgical Infection in Perihilar Cholangiocarcinoma Patients Treated with Curative Resection: A Multi-center Study

Background: The objective of this study was to investigate the association between pre-operative body mass index (BMI) and surgical infection in perihilar cholangiocarcinoma (pCCA) patients treated with curative resection. Methods: Consecutive pCCA patients were enrolled from four tertiary hospitals between 2008 and 2022. According to pre-operative BMI, the patients were divided into three groups: low BMI (≤18.4 kg/m2), normal BMI (18.5-24.9 kg/m2), and high BMI (≥25.0 kg/m2). The incidence of surgical infection among the three groups was compared. Multivariable logistic regression models were used to determine the independent risk factors associated with surgical infection. Results: A total of 371 patients were enrolled, including 283 patients (76.3%) in the normal BMI group, 30 patients (8.1%) in the low BMI group, and 58 patients (15.6%) in the high BMI group. The incidence of surgical infection was significantly higher in the patients in the low BMI and high BMI groups than in the normal BMI group. The multivariable logistic regression model showed that low BMI and high BMI were independently associated with the occurrence of surgical infection. Conclusions: The pCCA patients with a normal BMI treated with curative resection could have a lower risk of surgical infection than pCCA patients with an abnormal BMI.

The prognostic value of age-adjusted Charlson comorbidity index in laparoscopic resection for hilar cholangiocarcinoma

The prognostic role of the Age-Adjusted Charlson Comorbidity Index (ACCI) in hilar cholangiocarcinoma patients undergoing laparoscopic resection is unclear. To evaluate ACCI's effect on overall survival (OS) and recurrence-free survival (RFS), we gathered data from 136 patients who underwent laparoscopic resection for hilar cholangiocarcinoma at Zhengzhou University People's Hospital between 1 June 2018 and 1 June 2022. ACCI scores were categorized into high ACCI (ACCI > 4.0) and low ACCI (ACCI ≤ 4.0) groups. We examined ACCI's association with OS and RFS using Cox regression analyses and developed an ACCI-based nomogram for survival prediction. Our analysis revealed that higher ACCI scores (ACCI > 4.0) (HR = 2.14, 95%CI: 1.37-3.34) were identified as an independent risk factor significantly affecting both OS and RFS in postoperative patients with hilar cholangiocarcinoma (p < 0.05). TNM stage III-IV (HR = 7.42, 95%CI: 3.11-17.68), not undergoing R0 resection (HR = 1.58, 95%CI: 1.01-2.46), hemorrhage quantity > 350 mL (HR = 1.92, 95%CI: 1.24-2.97), and not receiving chemotherapy (HR = 1.89, 95%CI: 1.21-2.95) were also independent risk factors for OS. The ACCI-based nomogram accurately predicted the 1-, 2-, and 3-year OS rates, with Area Under the Curve (AUC) values of 0.818, 0.844, and 0.924, respectively. Calibration curves confirmed the nomogram's accuracy, and decision curve analysis highlighted its superior predictive performance. These findings suggest that a higher ACCI is associated with a worse prognosis in patients undergoing laparoscopic resection for hilar cholangiocarcinoma. The ACCI-based nomogram could aid clinicians in making accurate predictions about patient survival and facilitate individualized treatment planning.