JCCVS
Journal of Cardiology & Cardiovascular Surgery

Journal of Cardiology & Cardiovascular Surgery scientific, open-access, double-blind peer-reviewed journal covering a wide spectrum of topics in cardiology and cardiovascular surgery.

eISSN: 2980-1397
Creative Commons CC BY-NC-ND 4.0 International License.
EndNote Style

Online Manuscript System

Index
Original Article
Preoperative risk stratification of pulmonary nodules in cardiovascular practice: development of a CT-based logistic regression model
Abstract
Aims: Accurate risk stratification of pulmonary nodules incidentally detected during cardiovascular imaging is essential for guiding preoperative evaluation and cardiothoracic decision-making. This study aimed to identify independent predictors of pulmonary nodule malignancy and to develop a logistic regression–based risk scoring model, comparing its diagnostic performance with the Brock model.
Methods: This retrospective study included 125 patients with pulmonary nodules who underwent histopathological evaluation between January 2019 and December 2023. Patients were classified as benign (n=64) or malignant (n=61). Clinical characteristics and radiological parameters obtained from computed tomography and positron emission tomography/computed tomography were recorded. Univariable and multivariable logistic regression analyses were performed to identify independent predictors of malignancy. A weighted risk score was constructed based on regression coefficients. Discriminative performance was assessed using receiver operating characteristic curve analysis and compared with the Brock model using the DeLong test. A p value <0.05 was considered statistically significant.
Results: Multivariable analysis identified computed tomography nodule size, irregular margins, and pleural-based localization as independent predictors of malignancy (p<0.05). The proposed risk model demonstrated excellent discrimination with an area under the curve of 0.989 (95% confidence interval: 0.978–1.000), significantly superior to the Brock model (area under the curve=0.819; 95% confidence interval: 0.743–0.891; p<0.001). At the optimal cutoff value, sensitivity was 90.0% and specificity was 98.4%.
Conclusion: The developed logistic regression–based risk model provides a highly accurate tool for malignancy prediction in pulmonary nodules encountered during cardiovascular evaluation. Integration of this model into preoperative cardiovascular workflows may enhance multidisciplinary decision-making and reduce unnecessary invasive procedures.

Keywords : Pulmonary nodule, lung cancer, computed tomography, risk assessment, cardiovascular imaging, thoracic surgery, neoplasm staging, diagnostic imaging

Download Article


1. Chen D, Yang L, Zhang W, et al. Prevalence and management of pulmonary nodules: a systematic review and meta-analysis. J Thorac Dis. 2024;16(7):4619-4632. doi:10.21037/jtd-24-874
2. MacMahon H, Naidich DP, Goo JM, et al. Guidelines for management of incidental pulmonary nodules detected on CT images: 2017 Fleischner Society guidelines. Radiology. 2017;284(1):228-243. doi:10. 1148/radiol.2017161659
3. Callister MEJ, Baldwin DR, Akram AR, et al. British Thoracic Society guidelines for the investigation and management of pulmonary nodules. Thorax. 2015;70(Suppl 2):ii1-ii54. doi:10.1136/thoraxjnl-2015-207168
4. McWilliams A, Tammemägi MC, Mayo JR, et al. Probability of cancer in pulmonary nodules detected on first screening CT. N Engl J Med. 2013;369(10):910-919. doi:10.1056/NEJMoa1214726
5. Ten Haaf K, van Rosmalen J, de Koning HJ, et al. External validation of lung cancer risk prediction models: a systematic review. Thorax. 2017; 72(9):837-845. doi:10.1136/thoraxjnl-2016-208706
6. Ten Haaf K, Jeon J, Tammemägi MC, et al. Risk prediction models for lung cancer screening. JAMA. 2020;323(7):1-11. doi:10.1001/jama.2019. 22287
7. Park S, Lee SM, Kim S, et al. Development and validation of a CT-based prediction model for pulmonary nodule malignancy. Eur Respir J. 2022; 60(2):2102023. doi:10.1183/13993003.02023-2021
8. Huang Y, Liu Z, He L, et al. Radiomics signature: a potential biomarker for the prediction of lung cancer malignancy in pulmonary nodules. Eur Radiol. 2020;30(5):2911-2921. doi:10.1007/s00330-019-06513-0.
9. Wang H, Zhou Z, Li Y, et al. CT-based radiomics predicts the malignancy of pulmonary nodules: a systematic review and meta-analysis. Acad Radiol. 2023;30(12):3064-3075. doi:10.1016/j.acra.2023. 05.012.
10. Mu W, Jiang L, Zhang J, et al. Non-invasive decision support for lung cancer diagnosis based on PET/CT radiomics. Eur J Nucl Med Mol Imaging. 2020;47(3):635-644. doi:10.1007/s00259-019-04553-6
11. Nam JG, Park S, Hwang EJ, et al. Development and validation of deep learning-based automatic detection algorithm for malignant pulmonary nodules on chest CT. Radiology. 2021;299(1):218-228. doi: 10.1148/radiol.2021203846
12. de Margerie-Mellon C, Onken A, Heidinger BH, et al. Pulmonary nodules: risk stratification using volumetric and morphologic CT features. Radiology. 2021;301(1):192-202. doi:10.1148/radiol.2021203981
13. Truong MT, Sabloff BS, Ko JP. Multimodality imaging in the evaluation of pulmonary nodules. Radiol Clin North Am. 2020;58(1):41-58. doi:10. 1016/j.rcl.2019.09.004
14. Lowe VJ, Fletcher JW, Gobar L, et al. Prospective investigation of PET in lung nodules. J Clin Oncol. 2020;38(15 Suppl):e20532. doi:10.1200/JCO.2020.38.15_suppl.e20532
15. Horeweg N, Scholten ET, de Jong PA, et al. Detection of lung cancer through low-dose CT screening. N Engl J Med. 2020;382:503-513. doi: 10.1056/NEJMoa1911793
16. Baldwin DR, Gustafson J, Pickup L, et al. External validation of a radiological risk model for pulmonary nodules. Thorax. 2021;76(6):610-617. doi:10.1136/thoraxjnl-2020-215654
17. Mazzone PJ, Lam L. Evaluating pulmonary nodules: clinical practice consensus guidelines. Chest. 2022;161(1):406-421. doi:10.1016/j.chest. 2021.07.055
18. Kim H, Lee SM, Seo JB, et al. External validation and comparison of the Brock model and Lung-RADS in a lung cancer screening cohort: results from the Cancer Screening Project. Eur Radiol. 2021;31(6):4004-4015. doi:10.1007/s00330-020-07567-9
19. Li H, Salehjahromi M, Godoy MCB, et al. Lung cancer risk prediction in patients with persistent pulmonary nodules using the Brock model and Sybil model. Cancers (Basel). 2025;17(9):1499. doi:10.3390/cancers 17091499
20. Dinnessen R, Peeters D, Antonissen N, et al. Performance of a screening-trained deep learning model for pulmonary nodule malignancy estimation of incidental clinical nodules. Eur Radiol. 2026; 36(1):85-95. doi:10.1007/s00330-025-11829-1
21. Yang CJ, Kumar A, Deng JZ, et al. A national analysis of perioperative outcomes after lung cancer surgery. Ann Thorac Surg. 2021;111(4):1130-1138. doi:10.1016/j.athoracsur.2020.08.056
22. Burt BM, Shrager JB. Incidental pulmonary nodules in patients undergoing cardiac surgery: clinical implications and management strategies. Ann Thorac Surg. 2022;113(5):1582-1589. doi:10.1016/j.athoracsur.2021.09.021
23. Bilgin SS, Bilgin M. Radiological evaluation of pulmonary nodules. In: Soysal O, ed. Approach to Pulmonary Nodules. 1st ed. Türkiye Klinikleri; 2019.
24. de Koning HJ, Meza R, Plevritis SK, et al. External validation of lung cancer risk prediction models: a systematic review. Thorax. 2017;72(9): 837-845. doi:10.1136/thoraxjnl-2016-208964
Article available in :
Volume 4, Issue 1, 2026
Page : 6-13
https://doi.org/10.51271/JCCVS-0069
Article Information
Received : 14 Oca 2026
Accepted : 23 Şub 2026
Published : 28 Mar 2026
Corresponding Author :

Gülhan Albayrak: Department of Pulmonology, Şişli Hamidiye Etfal Training and Research Hospital, İstanbul, Turkiye

[email protected]
Citation : Ayhan Albayrak G. Preoperative risk stratification of pulmonary nodules in cardiovascular practice: development of a CT-based logistic regression model. J Cardiol Cardiovasc Surg. 2026;4(1):6-13. doi:10.51271/JCCVS-0069

Read: 63
Download : 31
Cited: 0
_Footer