Developing radiology diagnostic tools for pulmonary fibrosis using machine learning methods.

Background: Accurate and prompt diagnosis of the different patterns for pulmonary fibrosis is essential for patient management. However, accurate diagnosis of the specific pattern is challenging due to overlapping radiographic characteristics.

Materials And Methods: We conducted a retrospective chart review utilizing two machine learning methods, classification and regression tree and Bayesian additive regression tree, to select the most important radiographic features for diagnosing the three most common fibrosis patterns and created an online diagnostic app for convenient implementation.

Results: Four hundred patients (median age of 67 with inter quartile range 58-73; 200 males) were included in the study. Peripheral distribution, homogeneity, lower lobe predominance and mosaic attenuation of fibrosis are the four most important features identified. Bayesian additive regression tree demonstrates better performance than classification and regression tree in diagnosis prediction and provides the predicted probability of each diagnosis with uncertainty intervals for each combination of features.

Conclusion: The model and app built with Bayesian additive regression tree can be used as an effective tool in assisting radiologists in the diagnostic process of pulmonary fibrosis pattern recognition.