Construction of a risk prediction model for moderate⁃to⁃severe cutaneous adverse events in patients with non⁃small cell lung cancer undergoing postoperative immunotherapy
Abstract
ObjectiveTo analyze the independent risk factors for moderate⁃to⁃severe cutaneous adverse events in patients with non⁃small cell lung cancer undergoing postoperative immunotherapy,and to construct a Nomogram risk prediction model.MethodsA retrospective cohort study design was adopted.A total of 750 patients with NSCLC who received postoperative immunotherapy and were admitted to the department of thoracic surgery and department of oncology of our hospital from January 2024 to December 2025 were enrolled as research subjects.The patients were divided into a derivation cohort(525 cases) and a validation cohort(225 cases) at a 7∶3 ratio.Univariate and multivariate Logistic regression analyses were performed to identify risk factors,and a Nomogram model was subsequently constructed.The receiver operating characteristic(ROC) curve,Hosmer-Lemeshow test,calibration curve,and decision curve analysis(DCA) were utilized to evaluate the performance of the model.ResultsAmong the 525 patients in the derivation cohort,86(16.4%) developed moderate⁃to⁃severe cutaneous immune⁃related adverse events(irAEs).Multivariate Logistic regression analysis showed that history of allergic diseases,surgery⁃immunotherapy interval≤4 weeks,immunotherapy cycles>6 weeks,concurrent radiotherapy or chemotherapy,platelet⁃to⁃lymphocyte ratio(PLR)>200,and eosinophil count>0.5×10⁹/L were independent risk factors for moderate⁃to⁃severe cutaneous irAEs in NSCLC patients undergoing postoperative immunotherapy(all P<0.05).The area under the receiver operating characteristic curve(AUC) of the derivation cohort was 0.893(95%CI 0.854⁃0.933).The Youden's index was 0.617.The sensitivity was 0.854.The specificity was 0.763.The AUC of the validation cohort was 0.833(95%CI 0.793⁃0.872).The P value of the Hosmer⁃Lemeshow test was 0.435.The calibration curve demonstrated favorable consistency between predicted and actual risks. Decision curve analysis verified that the model yielded positive clinical net benefits.ConclusionsHistory of allergic diseases,surgery⁃immunotherapy interval≤4 weeks,immunotherapy cycles>6 weeks,concurrent radiotherapy or chemotherapy,PLR>200,and eosinophil count>0.5×10⁹/L are independent risk factors for moderate⁃to⁃severe cutaneous irAEs in NSCLC patients undergoing postoperative immunotherapy.The established Nomogram exhibits satisfactory predictive performance,which could assist clinical medical staff in accurately identifying patients at high risk of moderate⁃to⁃severe cutaneous irAEs.
Related
- The influencing factors of postoperative sleep disturbance in elderly patients undergoing transurethral prostate surgery and the construction and validation of a machine learning prediction model
- Relationship between intraoperative hypotension and postoperative venous thromboembolism in elderly patients undergoing hip surgery and construction of a risk prediction model
- Analysis of risk factors and construction of a prediction model for postoperative deep vein thrombosis in patients with periarticular knee fractures.
- Risk factors for postoperative recurrence of chronic subdural hematoma and construction and validation of an online dynamic nomogram prediction model.
- Postoperative Opioid Use Prediction Calculator Performance in Patients Undergoing Gynecologic Surgery
BibTeX
@article{jing2026construction,
title = {{Construction of a risk prediction model for moderate⁃to⁃severe cutaneous adverse events in patients with non⁃small cell lung cancer undergoing postoperative immunotherapy}},
author = {SUN Jing and ZHANG Wenqian and QU Liangliang},
journal = {Huli yanjiu},
year = {2026},
month = nov,
url = {http://hlyj.suo1.cn/thesisDetails#10.12102/j.issn.1009-6493.2026.23.008},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Construction of a risk prediction model for moderate⁃to⁃severe cutaneous adverse events in patients with non⁃small cell lung cancer undergoing postoperative immunotherapy
AU - SUN Jing
AU - ZHANG Wenqian
AU - QU Liangliang
PY - 2026
DA - 2026/11/08
JO - Huli yanjiu
UR - http://hlyj.suo1.cn/thesisDetails#10.12102/j.issn.1009-6493.2026.23.008
AB - ObjectiveTo analyze the independent risk factors for moderate⁃to⁃severe cutaneous adverse events in patients with non⁃small cell lung cancer undergoing postoperative immunotherapy,and to construct a Nomogram risk prediction model.MethodsA retrospective cohort study design was adopted.A total of 750 patients with NSCLC who received postoperative immunotherapy and were admitted to the department of thoracic surgery and department of oncology of our hospital from January 2024 to December 2025 were enrolled as research subjects.The patients were divided into a derivation cohort(525 cases) and a validation cohort(225 cases) at a 7∶3 ratio.Univariate and multivariate Logistic regression analyses were performed to identify risk factors,and a Nomogram model was subsequently constructed.The receiver operating characteristic(ROC) curve,Hosmer-Lemeshow test,calibration curve,and decision curve analysis(DCA) were utilized to evaluate the performance of the model.ResultsAmong the 525 patients in the derivation cohort,86(16.4%) developed moderate⁃to⁃severe cutaneous immune⁃related adverse events(irAEs).Multivariate Logistic regression analysis showed that history of allergic diseases,surgery⁃immunotherapy interval≤4 weeks,immunotherapy cycles>6 weeks,concurrent radiotherapy or chemotherapy,platelet⁃to⁃lymphocyte ratio(PLR)>200,and eosinophil count>0.5×10⁹/L were independent risk factors for moderate⁃to⁃severe cutaneous irAEs in NSCLC patients undergoing postoperative immunotherapy(all P<0.05).The area under the receiver operating characteristic curve(AUC) of the derivation cohort was 0.893(95%CI 0.854⁃0.933).The Youden's index was 0.617.The sensitivity was 0.854.The specificity was 0.763.The AUC of the validation cohort was 0.833(95%CI 0.793⁃0.872).The P value of the Hosmer⁃Lemeshow test was 0.435.The calibration curve demonstrated favorable consistency between predicted and actual risks. Decision curve analysis verified that the model yielded positive clinical net benefits.ConclusionsHistory of allergic diseases,surgery⁃immunotherapy interval≤4 weeks,immunotherapy cycles>6 weeks,concurrent radiotherapy or chemotherapy,PLR>200,and eosinophil count>0.5×10⁹/L are independent risk factors for moderate⁃to⁃severe cutaneous irAEs in NSCLC patients undergoing postoperative immunotherapy.The established Nomogram exhibits satisfactory predictive performance,which could assist clinical medical staff in accurately identifying patients at high risk of moderate⁃to⁃severe cutaneous irAEs.
SN - 1009-6493
ER -