Cancer medicine · 2026
Machine Learning-Driven Prognostic Model Integrating Lymphocyte-to-C-Reactive Protein Ratio and TNM Staging in Gallbladder Cancer.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wang Mingyang, Chen Zhengyu, E Fusheng, Gu Jun, Bao Runfa
Аннотация
BACKGROUND: A comprehensive preoperative assessment of the patient's physical condition is crucial for predicting the prognosis of patients undergoing radical cholecystectomy for gallbladder cancer (GBC). This study aimed to develop a prognostic model integrating preoperative hematological parameters and clinical information to predict postoperative survival in patients with GBC.
METHODS: Patients who underwent radical cholecystectomy for GBC between 2000 and 2024 at Xinhua Hospital, affiliated with Shanghai Jiao Tong University School of Medicine, and Shigatse People's Hospital were included in this study. Data on demographic features, clinical parameters, laboratory results, and clinical outcomes were collected. Univariate and multivariate Cox regression analyses, time-dependent ROC curve analysis, and the least absolute shrinkage and selection operator (LASSO) regression were used to identify the key factors for model development. Various machine learning models were constructed based on these findings. Internal validation assessed model stability, while clinical decision analysis evaluated its practical utility.
RESULTS: A total of 184 patients were included, with a mean age of 67 years. Key predictors identified through univariate and multivariate Cox regression, time-dependent ROC, and LASSO analyses were the lymphocyte-to-C-reactive protein ratio (LCR) and tumor-node-metastasis (TNM) staging. The best-performing model was logistic regression, with the following area under the curve (AUC) values: for the training set, 0.785 at 1 year, 0.853 at 2 years, and 0.873 at 3 years; and for the test set, 0.800 at 1 year, 0.870 at 2 years, and 0.872 at 3 years. Clinical decision analysis confirmed the model's clinical applicability.
CONCLUSION: The machine learning model incorporating LCR and TNM staging is a robust tool for predicting postoperative survival following radical resection for GBC.
METHODS: Patients who underwent radical cholecystectomy for GBC between 2000 and 2024 at Xinhua Hospital, affiliated with Shanghai Jiao Tong University School of Medicine, and Shigatse People's Hospital were included in this study. Data on demographic features, clinical parameters, laboratory results, and clinical outcomes were collected. Univariate and multivariate Cox regression analyses, time-dependent ROC curve analysis, and the least absolute shrinkage and selection operator (LASSO) regression were used to identify the key factors for model development. Various machine learning models were constructed based on these findings. Internal validation assessed model stability, while clinical decision analysis evaluated its practical utility.
RESULTS: A total of 184 patients were included, with a mean age of 67 years. Key predictors identified through univariate and multivariate Cox regression, time-dependent ROC, and LASSO analyses were the lymphocyte-to-C-reactive protein ratio (LCR) and tumor-node-metastasis (TNM) staging. The best-performing model was logistic regression, with the following area under the curve (AUC) values: for the training set, 0.785 at 1 year, 0.853 at 2 years, and 0.873 at 3 years; and for the test set, 0.800 at 1 year, 0.870 at 2 years, and 0.872 at 3 years. Clinical decision analysis confirmed the model's clinical applicability.
CONCLUSION: The machine learning model incorporating LCR and TNM staging is a robust tool for predicting postoperative survival following radical resection for GBC.