Construction of a nomogram prediction model for PD-L1 expression in non-small cell lungcancer using spectral CT parameters and clinical features(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2025年第4期
- Page:
- 443-449
- Research Field:
- 医学影像物理
- Publishing date:
Info
- Title:
- Construction of a nomogram prediction model for PD-L1 expression in non-small cell lungcancer using spectral CT parameters and clinical features
- Author(s):
- ZHU Kaibo; DENG Liangna; WANG Haisheng; LIU Jianqiang; LUO Pan; ZHOU Junlin
- Department of Radiology, Lanzhou University Second Hospital/the Second Clinical Medical School, Lanzhou University/KeyLaboratory of Medical Imaging of Gansu Province/Gansu International Scientific and Technological Cooperation Base of MedicalImaging Artificial Intelligence, Lanzhou 730030, China
- Keywords:
- non-small cell lung cancer; nomogram; spectral CT; programmed cell death ligand 1
- PACS:
- R318
- DOI:
- 10.3969/j.issn.1005-202X.2025.04.004
- Abstract:
- Objective To investigate the preoperative prediction of the expression level of programmed cell death ligand 1(PD-L1) in non-small cell lung cancer (NSCLC) by a nomogram model constructed with clinical data, conventional CTsigns and spectral CT parameters. Methods A retrospective analysis was conducted on 52 patients with pathologicallyconfirmed NSCLC and undergoing preoperative spectral CT examination. The patients were categorized into positive andnegative groups according to PD-L1 expression level, and their clinical data, conventional CT signs and spectral CTparameters were collected. Specifically, clinical data included gender, age, Ki-67 and tumor markers; conventional CT signsincluded tumor density, margins, calcification, spiculation, lobulation, pleural indentation and cavitation; and spectral CTparameters measured in the arterial and venous phases included effective atomic number (Eff-Z), iodine concentration (IC),water concentration (WC) and normalized iodine concentration (NIC). Intergroup differences were analyzed, andmultivariate Logistic regression was used to identify independent predictors and establish the prediction model which wasevaluated for prediction performance and accuracy using receiver operating characteristic (ROC) curves, calibration curveand decision curve analyses. Results For clinical data, only the difference in gender between two groups had statistical significance (P<0.05). The spectral CT parameters (IC, NIC and Eff-Z) in the arterial and venous phases of PD-L1 positivegroup were all greater than those of PD-L1 negative group, with statistically significant differences (P<0.05). MultivariateLogistic regression analysis identified gender (P=0.024), venous-phase Eff-Z (P=0.002), and venous-phase IC (P=0.003)as independent predictive factors for PD-L1 expression. The nomogram prediction model constructed with theseindependent predictors had an area under curve of 0.80, a sensitivity of 88.00%, and a specificity of 59.00%. Thecalibration curve showed that the predicted values had a high consistency with the actual values. The decision curverevealed that when the high-risk threshold was between 0.10 and 0.83, the model could achieve the maximum net benefit.Conclusion The nomogram model constructed with spectral CT parameters and clinical data has certain value in predictingthe expression level of PD-L1 in NSCLC.
Last Update: 2025-04-30