Authors: Julien Heitmann, Alban Glangetas, Jonathan Doenz, Juliane Dervaux, Deeksha M. Shama, Daniel Hinjos Garcia, Mohamed Rida Benissa, Aymeric Cantais, Alexandre Perez, Daniel Müller, Tatjana Chavdarova, Isabelle Ruchonnet-Metrailler, Johan N. Siebert, Laurence Lacroix, Martin Jaggi, Alain Gervaix, Mary-Anne Hartley, , Florence Hugon, Derrick Fassbind, Makura Barro, Georges Bediang, N. E. L. Hafidi, M. Bouskraoui, Idrissa Ba
Published: 2023-06-02
DOI: 10.1038/s41746-023-00838-3
Source: Full article
AbstractThe interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize and automate evaluation. We used 35.9 hours of auscultation audio from 572 pediatric outpatients to developDeepBreath: a deep learning model identifying the audible signatures of acute respiratory illness in children. It comprises a convolutional neural network followed by a logistic regression classifier, aggregating estimates on recordings from eight thoracic sites into a single prediction at the patient-level. Patients were either healthy controls (29%) or had one of three acute respiratory illnesses (71%) including pneumonia, wheezing disorders (bronchitis/asthma), and bronchiolitis). To ensure objective estimates on model generalisability,DeepBreathis trained on patients from two countries (Switzerland, Brazil), and results are reported on an internal 5-fold cross-validation as well as externally validated (extval) on three other countries (Senegal, Cameroon, Morocco).DeepBreathdifferentiated healthy and pathological breathing with an Area Under the Receiver-Operator Characteristic (AUROC) of 0.93 (standard deviation [SD] ± 0.01 on internal validation). Similarly promising results were obtained for pneumonia (AUROC 0.75 ± 0.10), wheezing disorders (AUROC 0.91 ± 0.03), and bronchiolitis (AUROC 0.94 ± 0.02). Extval AUROCs were 0.89, 0.74, 0.74 and 0.87 respectively. All either matched or were significant improvements on a clinical baseline model using age and respiratory rate. Temporal attention showed clear alignment between model prediction and independently annotated respiratory cycles, providing evidence thatDeepBreathextracts physiologically meaningful representations.DeepBreathprovides a framework for interpretable deep learning to identify the objective audio signatures of respiratory pathology.