ScreenDx, an artificial intelligence-based algorithm for the incidental detection of pulmonary fibrosis.
Authors
Affiliations (5)
Affiliations (5)
- Division of General Internal Medicine, Dept. of Medicine, University of Louisville. 550 South Jackson Street, 3rd Floor, Ste A3K00, Louisville, KY 40202, United States.
- Philadelphia College of Osteopathic Medicine. Philadelphia, PA, 4170 City Avenue, Philadelphia, PA 19131, United States.
- Division of Pulmonary, Critical Care Medicine, and Sleep Disorders, Dept. of Medicine, University of Louisville. 550 South Jackson Street, 3rd Floor, Ste A3R40, Louisville, KY 40202, United States. Electronic address: [email protected].
- Division of Body MRI, Department of Radiology, Stanford Medicine Diagnostic Radiology, 300 Pasteur Dr Rm S092, MC 5105, Stanford, CA 94305, United States; Imvaria Inc. Berkeley, CA 94709, United States.
- Imvaria Inc. Berkeley, CA 94709, United States.
Abstract
Nonspecific symptoms and variability in radiographic reporting patterns contribute to a diagnostic delay of the diagnosis of pulmonary fibrosis. An attractive solution is the use of machine-learning algorithms to screen for radiographic features suggestive of pulmonary fibrosis. Thus, we developed and validated a machine learning classifier algorithm (ScreenDx) to screen computed tomography imaging and identify incidental cases of pulmonary fibrosis. ScreenDx is a deep learning convolutional neural network that was developed from a multi-source dataset (cohort A) of 3,658 cases of normal and abnormal CT's, including CT's from patients with COPD, emphysema, and community-acquired pneumonia. Cohort B, a US-based cohort (n = 381) was used for tuning the algorithm, and external validation was performed on cohort C (n = 683), a separate international dataset. At the optimal threshold, the sensitivity and specificity for detection of pulmonary fibrosis in cohort B was 0.91 (95 % CI 88-94 %) and 0.95 (95 % CI 93-97 %), respectively, with AUC 0.98. In the external validation dataset (cohort C), the sensitivity and specificity were 1.0 (95 % 99.9-100.0) and 0.98 (95 % CI 97.9-99.6), respectively, with AUC 0.997. There were no significant differences in the ability of ScreenDx to identify pulmonary fibrosis based on CT manufacturer (Phillips, Toshiba, GE Healthcare, or Siemens) or slice thickness (2 mm vs 2-4 mm vs 4 mm). Regardless of CT manufacturer or slice thickness, ScreenDx demonstrated high performance across two, multi-site datasets for identifying incidental cases of pulmonary fibrosis. This suggest that the algorithm may be generalizable across patient populations and different healthcare systems.