Chest
Original Research: Thoracic OncologyDevelopment of a Risk Prediction Model to Estimate the Probability of Malignancy in Pulmonary Nodules Being Considered for Biopsy
Section snippets
Patients and Methods
The current study received approval from the Cleveland Clinic Institutional Review Board (#16-243). The need for informed consent was waived due to minimal risk. The dataset included a retrospective convenience sample of patients aged > 18 years with a PN measuring < 30 mm in diameter with a definitive histopathologic diagnosis according to results of lung biopsy or resection at the Cleveland Clinic between 2007 and 2016. Individuals < 18 years of age, PNs found by using a lung cancer screening
Results
A total of 301 patients with PNs were identified for model building. Two hundred (66.5%) had malignant PNs. There were 95 men with malignant nodules, and 54 men with benign nodules. Clinical characteristics and imaging features of the PNs are described in Table 1. Most of the PNs included in the analysis were solid (74.1%) on CT imaging. The remainder were part-solid (19.9%) and GGN (6.0%). Among the malignant nodules, 134 (67.0%) were adenocarcinomas, 33 (16.5%) were squamous cell carcinomas,
Discussion
The goal of the current project was to develop novel lung nodule risk prediction models to estimate the probability of malignancy in PNs clinically considered to have a high enough risk of malignancy to recommend (nonsurgical or surgical) biopsy. The initial multivariate logistic regression model, built without FDG-PET or surveillance imaging results, exhibited excellent accuracy (C-index of 0.79 after bootstrap validation) and calibration (Fig 1). Its accuracy was higher than the Mayo Clinic
Conclusions
We sought to build models that could estimate the probability of malignancy in patients with PNs believed to have a high enough probability of malignancy to justify an invasive biopsy. To that end, we built a model, with several submodels, that can be used by clinicians regardless of the prebiopsy phase of nodule evaluation their patient is at when seen in clinic. Our algorithm generates not only a probability of malignancy but also a ratio of malignant and benign nodules within each
Acknowledgments
Author contributions: H. K. C. takes responsibility for the content of the article, including the data and analysis. M. R., H. K. C., and P. J. M. had full access to all of the data in the study and take responsibility for the integrity of the data and the accuracy of the data analysis. All authors contributed substantially to the study design, data analysis and interpretation, and the writing of the manuscript; and all authors provided final approval of the version to be published and have
References (8)
- et al.
Evaluation of individuals with pulmonary nodules: when is it lung cancer? Diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians evidence-based clinical practice guidelines
Chest
(2013) - et al.
Clinical prediction model to characterize pulmonary nodules: validation and added value of 18F-fluorodeoxyglucose positron emission tomography
Chest
(2005) - et al.
A clinical model to estimate the pretest probability of lung cancer in patients with solitary pulmonary nodules
Chest
(2007) - et al.
Guidelines for management of incidental pulmonary nodules detected on CT images: from the Fleischner Society 2017
Radiology
(2017)
Cited by (25)
Imaging of Solid Pulmonary Nodules
2023, Clinics in Chest MedicinePredicting lung nodules malignancy
2022, PulmonologyCitation Excerpt :Several other prediction models have been created using clinical and radiological criteria to assist clinicians to discriminate malignant from benign nodules. Older age, smoking history, maximum nodule diameter and spiculation in chest CT appear most frequently as predictors of lung cancer in most of the final models.16,24,26,35.Çô37 Overall, our model discriminated well with an excellent overall performance.
Risk-Based lung cancer screening: A systematic review
2020, Lung CancerManagement of Lung Nodules and Lung Cancer Screening During the COVID-19 Pandemic: CHEST Expert Panel Report
2020, Journal of the American College of Radiology
FUNDING/SUPPORT: The authors have reported to CHEST that no funding was received for this study.