The Probability of Malignancy in Solitary Pulmonary Nodules
1997/04/28 by Stephen J. Swensen · 30 citations
Medicine · #Lung Cancer Diagnosis and Treatment #Lung Cancer Treatments and Mutations #Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
paper · doi:10.1001/archinte.1997.00440290031002
Abstract
BACKGROUND: A clinical prediction model to identify malignant nodules based on clinical data and radiological characteristics of lung nodules was derived using logistic regression from a random sample of patients (n = 419) and tested on data from a separate group of patients (n = 210). OBJECTIVE: To use multivariate logistic regression to estimate the probability of malignancy in radiologically indeterminate solitary pulmonary nodules (SPNs) in a clinically relevant subset of patients with SPNs that measured between 4 and 30 mm in diameter. PATIENTS AND METHODS: A retrospective cohort study at a multispecialty group practice included 629 patients (320 men, 309 women) with newly discovered (between January 1, 1984, and May 1, 1986) 4- to 30-mm radiologically indeterminate SPNs on chest radiography. Patients with a diagnosis of cancer within 5 years prior to the discovery of the nodule were excluded. Clinical data included age, sex, cigarette-smoking status, and history of extrathoracic malignant neoplasm, asbestos exposure, and chronic interstitial or obstructive lung disease; chest radiological data included the diameter, location, edge characteristics (eg, lobulation, spiculation, and shagginess), and other characteristics (eg, cavitation) of the SPNs. Predictors were identified in a random sample of two thirds of the patients and tested in the remaining one third. RESULTS: Sixty-five percent of the nodules were benign, 23% were malignant, and 12% were indeterminate. Three clinical characteristics (age, cigarette-smoking status, and history of cancer [diagnosis, > or = 5 years ago]) and 3 radiological characteristics (diameter, spiculation, and upper lobe location of the SPNs) were independent predictors of malignancy. The area (+/-SE) under the evaluated receiver operating characteristic curve was 0.8328 +/- 0.0226. CONCLUSION: Three clinical and 3 radiographic characteristics predicted the malignancy in radiologically indeterminate SPNs.
Cited by
- The American Cancer Society National Lung Cancer Roundtable strategic plan: Optimizing strategies for lung nodule evaluation and management
- Evaluation of Individuals With Pulmonary Nodules: When Is It Lung Cancer?
- An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification
- Performance of Lung Cancer Prediction Models for Screening-detected, Incidental, and Biopsied Pulmonary Nodules
- Cohort-Aware Agents for Individualized Lung Cancer Risk Prediction Using a Retrieval-Augmented Model Selection Framework
- Prevalence and variables associated with solitary pulmonary nodules in a routine clinic-based population: a cross-sectional study. [europepmc]
- Improved pulmonary nodule classification utilizing quantitative lung parenchyma features. [europepmc]
- Design of a prospective, multicenter, global, cohort study of electromagnetic navigation bronchoscopy. [europepmc]
- [China National Guideline of Classification, Diagnosis and Treatment for Lung Nodules (2016 Version)]. [europepmc]
- Electromagnetic navigation bronchoscopy to access lung lesions in 1,000 subjects: first results of the prospective, multicenter NAVIGATE study. [europepmc]
- Combining serum miRNAs, CEA, and CYFRA21-1 with imaging and clinical features to distinguish benign and malignant pulmonary nodules: a pilot study : Xianfeng Li et al.: Combining biomarker, imaging, and clinical features to distinguish pulmonary nodules. [europepmc]
- Evaluation of the solitary pulmonary nodule: size matters, but do not ignore the power of morphology. [europepmc]
- Lung cancer screening: nodule identification and characterization. [europepmc]
- Lung cancer prediction using machine learning and advanced imaging techniques. [europepmc]
- Management of incidental lung nodules <8 mm in diameter. [europepmc]
- Empiric Radiotherapy for Lung Cancer Collaborative Group multi-institutional evidence-based guidelines for the use of empiric stereotactic body radiation therapy for non-small cell lung cancer without pathologic confirmation. [europepmc]
- Medically inoperable stage I non-small cell lung cancer: best practices and long-term outcomes. [europepmc]
- Developing prediction models for clinical use using logistic regression: an overview. [europepmc]
- Diagnosis and management of peripheral lung nodule. [europepmc]
- Comparison of Veterans Affairs, Mayo, Brock classification models and radiologist diagnosis for classifying the malignancy of pulmonary nodules in Chinese clinical population. [europepmc]
- Evaluation of Prediction Models for Identifying Malignancy in Pulmonary Nodules Detected via Low-Dose Computed Tomography. [europepmc]
- Do we need to see to believe?-radiomics for lung nodule classification and lung cancer risk stratification. [europepmc]
- A prediction model to evaluate the pretest risk of malignancy in solitary pulmonary nodules: evidence from a large Chinese southwestern population. [europepmc]
- Can autoantibody tests enhance lung cancer screening?-an evaluation of EarlyCDT ® -Lung in context of the German Lung Cancer Screening Intervention Trial (LUSI). [europepmc]
- A prediction model based on DNA methylation biomarkers and radiological characteristics for identifying malignant from benign pulmonary nodules. [europepmc]
- Molecular biomarkers in early stage lung cancer. [europepmc]
- Shape-sensing robotic-assisted bronchoscopy for pulmonary nodules: initial multicenter experience using the Ion™ Endoluminal System. [europepmc]
- A wavelet features derived radiomics nomogram for prediction of malignant and benign early-stage lung nodules. [europepmc]
- A Classifier for Improving Early Lung Cancer Diagnosis Incorporating Artificial Intelligence and Liquid Biopsy. [europepmc]
- Diagnostic outcomes of robotic-assisted bronchoscopy for pulmonary lesions in a real-world multicenter community setting. [europepmc]
Related