1. Development and validation of a nomogram for predicting histologic subtypes of subpleural non-small cell lung cancer using ultrasound parameters and clinical data.
- Author
-
Mao, Feng, Shen, Mengjun, Zhang, Yi, Chen, Hongwei, Cong, Yang, Zhu, Huiming, Tang, Chunhong, Zhang, Shengmin, and Wang, Yin
- Abstract
Aims: To develop and validate an individualized nomogram for differentiating the histologic subtypes (adenocarcinoma and squamous cell carcinoma) of subpleural non-small cell lung cancer (NSCLC) based on ultrasound parameters and clinical data. Methods: This study was conducted retrospectively between March 2018 and December 2019. Patients were randomly assigned to a development cohort (DC, n=179) and a validation cohort (VC, n=77). A total of 7 clinical parameters and 16 ultrasound parameters were collected. Least absolute shrinkage and selection operator regression analysis was employed to identify the most significant predictors utilizing a 10-fold cross-validation. The multivariate logistic regression model was applied to investigate the relevant factors. An individualized nomogram was then developed. Receiver operating characteristic (ROC) curve, calibration plot and decision curve analysis (DCA) were applied for model validation in both DC and VC. Results: Following the final regression analysis, gender, serum carcinoembryonic antigen, lesion size and perfusion defect in contrast-enhanced ultrasound were entered into the nomogram. The model showed moderate predictive ability, with an area under the ROC curve of 0.867 for DC and 0.838 for VC. The calibration curves of the model showed good agreement between actual and predicted probabilities. The ROC and DCA curves demonstrated that the nomogram exhibited a good predictive performance. Conclusion: We developed a nomogram that can predict the histologic subtypes of subpleural NSCLC. Both internal and external validation revealed optimal discrimination and calibration, indicating that the nomogram may have clinical utility. This model has the potential to assist clinicians in making treatment recommendations. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF