Nomogram prediction of overall survival in small cell lung cancer patients treated with platinum-based chemotherapy: based on pre-treatment multi-parameter
YE Ruolei1, 2, SU Yanping3, 4, MAO Yanfei2,ZHANG Yihong3, ZHANG Ying3, XU Yanyan2, LUO Songmei2.
1.College of Pharmacy, Zhejiang Chinese Medical University, Hangzhou 310000, China; 2.Department of Pharmacy, the Fifth Affiliated Hospital of Wenzhou Medical University, Lishui 323000, China; 3.Department of Radiology, the Fifth Affiliated Hospital of Wenzhou Medical University, Lishui 323000, China; 4.Zhejiang Key Laboratory of Imaging Diagnosis and Interventional Minimally invasive Research, the Fifth Affiliated Hospital of Wenzhou Medical University, Lishui 323000, China
YE Ruolei,SU Yanping,MAO Yanfei, et al. Nomogram prediction of overall survival in small cell lung cancer patients treated with platinum-based chemotherapy: based on pre-treatment multi-parameter[J]. JOURNAL OF WEZHOU MEDICAL UNIVERSITY, 2024, 54(7): 589-597.
Abstract：Objective: To investigate the application value of a nomogram constructed based on pretreatment multi-parameter in predicting the overall survival (OS) of patients with small cell lung cancer (SCLC) undergoing platinum-based chemotherapy. Methods: A retrospective analysis was carried out on a cohort of 155 patients diagnosed with SCLC confirmed through pathology at the Fifth Affiliated Hospital of Wenzhou Medical University from February 2014 to February 2023. These patients received first-line chemotherapy based on platinum compounds. Telephone follow-ups were conducted to gather OS data for the included patients. Patients were randomly divided into a training set (n=111) and a validation set (n=44) at a ratio of 7:3. Prior to treatment,all patients underwent chest CT scans and various hematological examinations. The least absolute shrinkage and selection operator (LASSO) regression was utilized for feature selection among factors. Following this, univariate and multivariate Cox regression analyses were utilized to identify independent predictors predicting OS in patients with SCLC. Subsequently, a nomogram was constructed based on the identified factors. The performance and
clinical value of the model were evaluated using time-dependent receiver operating characteristic (Time ROC) curve analysis, Time-dependent AUC curve, calibration curve, and decision curve analysis (DCA). The Kaplan-Meier curve was used to analyze the impact of high versus low-risk groups on patient prognosis. Results:Following LASSO screening in the training set, five features associated with prognosis of SCLC platinum-based chemotherapy were identified: gender, Veterans’ Administration Lung Study Group (VALSG) staging, platinum sensitivity, cytokeratin 19 fragment (Cyfra21-1), and platelet count. These features were determined through univariate and multivariate Cox regression analyses to be independent predictors for predicting OS in SCLC patients undergoing platinum-based chemotherapy (P<0.05). The constructed nomogram prediction model demonstrated AUC values for predicting 6, 12, and 18-month OS in the training set and validation set as follows: 0.90(0.82-0.97), 0.84 (0.73-0.91), 0.88 (0.83-0.92) and 0.80 (0.66-0.94), 0.82 (0.69-0.96), 0.86 (0.72-0.95) respectively.The calibration curve indicated good consistency between actual values and model-predicted probabilities, while DCA curves indicated a high clinical utility of the model. The Kaplan-Meier curves for the training and validation groups both demonstrated an association between patients in the high-risk group and shorter overall survival (P<0.001). Conclusion: The nomogram constructed based on pre-treatment multi-parameter can offer valuable guidance in predicting OS for SCLC patients undergoing platinum-based chemotherapy.
