Abstract

Pulmonary complications, including infections, are highly prevalent in patients after hematopoietic cell transplant with chronic graft-versus-host disease. These comorbid diseases can make the diagnosis of early lung graft-versus-host disease (bronchiolitis obliterans syndrome) challenging. A quantitative method to differentiate among these pulmonary diseases can address diagnostic challenges and facilitate earlier and more targeted therapy.We conducted a single center study of 66 patients with computed tomography chest scans analyzed with a quantitative imaging tool known as parametric response mapping. Parametric response mapping results were correlated with pulmonary function tests and clinical characteristics. Five parametric response mapping metrics were applied to K-means clustering and support vector machine models to distinguish among post-transplant lung complications solely from quantitative output.Compared to parametric response mapping, spirometry showed a moderate correlation with radiographic air trapping, and total lung capacity and residual volume showed a strong correlation with radiographic lung volumes. K-means clustering analysis distinguished 4 unique clusters. Clusters 2 and 3 represented obstructive physiology (encompassing 81% of patients with bronchiolitis obliterans syndrome) in increasing severity (percent air trapping 15.6% and 43.0%, respectively). Cluster 1 was dominated by normal lung, and cluster 4 was characterized by patients with parenchymal opacities. A support vector machine algorithm differentiated bronchiolitis obliterans syndrome with specificity of 88%, sensitivity of 83%, accuracy of 86% and an area under the receiver operating characteristic curve of 0.85.Our machine learning models offer a quantitative approach for the identification of bronchiolitis obliterans syndrome versus other lung diseases, including late pulmonary complications after hematopoietic cell transplant.

View details for DOI 10.1016/j.chest.2020.02.076

View details for PubMedID 32343962