Explainable machine learning methods and respiratory oscillometry for the diagnosis of respiratory abnormalities in sarcoidosis.

BACKGROUND: In this work, we developed many machine learning classifiers to assist in diagnosing respiratory changes associated with sarcoidosis, based on results from the Forced Oscillation Technique (FOT), a non-invasive method used to assess pulmonary mechanics. In addition to accurate results, there is a particular interest in their interpretability and explainability, so we used Genetic Programming since the classification is made with intelligible expressions and we also evaluate the feature importance in different experiments to find the more discriminative features. METHODOLOGY/PRINCIPAL FINDINGS: We used genetic programming in its traditional tree form and a grammar-based form. To check if interpretable results are competitive, we compared their performance to K-Nearest Neighbors, Support Vector Machine, AdaBoost, Random Forest, LightGBM, XGBoost, Decision Trees and Logistic Regressor. We also performed experiments with fuzzy features and tested a feature selection technique to bring even more interpretability. The data used to feed the classifiers come from the FOT exams in 72 individuals, of which 25 were healthy, and 47 were diagnosed with sarcoidosis. Among the latter, 24 showed normal conditions by spirometry, and 23 showed respiratory changes. The results achieved high accuracy (AUC > 0.90) in two analyses performed (controls vs. individuals with sarcoidosis and normal spirometry and controls vs. individuals with sarcoidosis and altered spirometry). Genetic Programming and Grammatical Evolution were particularly beneficial because they provide intelligible expressions to make the classification. The observation of which features were selected most frequently also brought explainability to the study of sarcoidosis. CONCLUSIONS: The proposed system may provide decision support for clinicians when they are struggling to give a confirmed clinical diagnosis. Clinicians may reference the prediction results and make better decisions, improving the productivity of pulmonary function services by AI-assisted workflow.

Respiratory resistance and reactance in adults with sickle cell anemia: Correlation with functional exercise capacity and diagnostic use.

BACKGROUND: The improvement in sickle cell anemia (SCA) care resulted in the emergence of a large population of adults living with this disease. The mechanisms of lung injury in this new population are largely unknown. The forced oscillation technique (FOT) represents the current state-of-the-art in the assessment of lung function. The present work uses the FOT to improve our knowledge about the respiratory abnormalities in SCA, evaluates the associations of FOT with the functional exercise capacity and investigates the early detection of respiratory abnormalities. METHODOLOGY/PRINCIPAL FINDINGS: Spirometric classification of restrictive abnormalities resulted in three categories: controls (n = 23), patients with a normal exam (n = 21) and presenting pulmonary restriction (n = 24). FOT analysis showed that, besides restrictive changes (reduced compliance; p<0.001), there is also an increase in respiratory resistance (p<0.001) and ventilation heterogeneity (p<0.01). FOT parameters are associated with functional exercise capacity (R = -0.38), pulmonary diffusion (R = 0.66), respiratory muscle performance (R = 0.41), pulmonary volumes (R = 0.56) and airway obstruction (R = 0.54). The diagnostic accuracy was evaluated by investigating the area under the receiver operating characteristic curve (AUC). A combination of FOT and machine learning (ML) classifiers showed adequate diagnostic accuracy in the detection of early respiratory abnormalities (AUC = 0.82). CONCLUSIONS: In this study, the use of FOT showed that adults with SCA develop a mixed pattern of respiratory disease. Changes in FOT parameters are associated with functional exercise capacity decline, abnormal pulmonary mechanics and diffusion. FOT associated with ML methods accurately diagnosed early respiratory abnormalities. This suggested the potential utility of the FOT and ML clinical decision support systems in the identification of respiratory abnormalities in patients with SCA.