A CT-based nomogram for differentiating invasive fungal disease of the lung from bacterial pneumonia

Background: There is an annual increase in the incidence of invasive fungal disease (IFD) of the lung in the world, but it is always a challenge for physicians to make a early diagnosis of IFD of the lung. Methods: A total of 214 patients with IFD of the lung or clinically confirmed BP were retrospectively enrolled from two institutions (171 patients from one institution in the training set and 43 patients from another institution in the test set). The features of thoracic CT images of the 214 patients were analyzed on the picture archiving and communication system by two radiologists, and these CT images were importe d into RadCloud to perform radiomics analysis. A clinical model from radiologic analysis、a radiomics model from radiomic analysis and a combined model from integrating radiologic and radiomic analysis was constructed in the training set, and a nomogram based the combined model was further developed. The area under the ROC curve (AUC) of receiver operating characteristic (ROC) curve was calculated to assess the diagnostic performance of three models. Decision curve analysis(DCA) was conducted to evaluate clinical utility of three models by estimating the net benefit at a range of threshold probabilities. Results: The combined model had the most excellent diagnostic performance with both the training set (AUC: 0.944) and test set (AUC: 0.911) in differentiating IFD of lung from BP among three models, and obtained the greatest net benefit among three models by DCA. Conclusion: Our proposed nomogram, based on a combined model integrating radiologic and radiomics analysis, has a powerful predictive capability for differentiating IFD from BP. A good clinical outcome could be obtained using our nomogram.