A decision tree model to distinguish between benign and malignant pulmonary nodules on CT scans

- OBJECTIVE: Chest computed tomography (CT) is increasingly being used to screen for lung cancer. Machine learning mod -els could facilitate the distinction between be-nign and malignant pulmonary nodules. This study aimed to develop and validate a simple clinical prediction model to distinguish between benign and malignant lung nodules.PATIENTS AND METHODS: Patients who un-derwent a video thoracic-assisted lobectomy be-tween January 2013 and December 2020 at a Chi-nese hospital were enrolled in the study. The clin-ical characteristics of the patients were extracted from their medical records. Univariate and mul-tivariate analyses were used to identify the risk factors for malignancy. A decision tree model with 10-fold cross-validation was constructed to predict the malignancy of the nodules. The sensi-tivity, specificity, and area under the curve (AUC) of a receiver operatic characteristics curve were used to evaluate the model's prediction accura-cy in relation to the pathological gold standard.RESULTS: Out of the 1,199 patients with pul-monary nodules enrolled in the study, 890 were pathologically confirmed to have malignant le-sions. The multivariate analysis identified satel-lite lesions as an independent predictor for be-nign pulmonary nodules. Conversely, the lobulat-ed sign, burr sign, density, vascular convergence sign, and pleural indentation sign were identified as independent predictors for malignant pulmo-nary nodules. The decision tree analysis identi-fied the density of the lesion, the burr sign, the vascular convergence sign, and the drinking his-tory as predictors of malignancy. The area under the curve of the decision tree model was 0.746 (95% CI 0.705-0.778), while the sensitivity and specificity were 0.762 and 0.799, respectively.CONCLUSIONS: The decision tree model accurately characterized the pulmonary nod-ule and could be used to guide clinical deci-sion-making.