Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform.

Background Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform. Methods and Results Using >34 hours of previously acquired and annotated heart sound recordings, we trained a deep neural network to detect murmurs. To test the algorithm, we enrolled 962 patients in a clinical study and collected recordings at the 4 primary auscultation locations. Ground truth was established using patient echocardiograms and annotations by 3 expert cardiologists. Algorithm performance for detecting murmurs has sensitivity and specificity of 76.3% and 91.4%, respectively. By omitting softer murmurs, those with grade 1 intensity, sensitivity increased to 90.0%. Application of the algorithm at the appropriate anatomic auscultation location detected moderate-to-severe or greater aortic stenosis, with sensitivity of 93.2% and specificity of 86.0%, and moderate-to-severe or greater mitral regurgitation, with sensitivity of 66.2% and specificity of 94.6%. Conclusions The deep learning algorithm's ability to detect murmurs and clinically significant aortic stenosis and mitral regurgitation is comparable to expert cardiologists based on the annotated subset of our database. The findings suggest that such algorithms would have utility as front-line clinical support tools to aid clinicians in screening for cardiac murmurs caused by valvular heart disease. Registration URL: https://clinicaltrials.gov; Unique Identifier: NCT03458806.

Overcoming the cystic fibrosis sputum barrier to leading adeno-associated virus gene therapy vectors.

Gene therapy has not yet improved cystic fibrosis (CF) patient lung function in human trials, despite promising preclinical studies. In the human CF lung, inhaled gene vectors must penetrate the viscoelastic secretions coating the airways to reach target cells in the underlying epithelium. We investigated whether CF sputum acts as a barrier to leading adeno-associated virus (AAV) gene vectors, including AAV2, the only serotype tested in CF clinical trials, and AAV1, a leading candidate for future trials. Using multiple particle tracking, we found that sputum strongly impeded diffusion of AAV, regardless of serotype, by adhesive interactions and steric obstruction. Approximately 50% of AAV vectors diffused >1,000-fold more slowly in sputum than in water, with large patient-to-patient variation. We thus tested two strategies to improve AAV diffusion in sputum. We showed that an AAV2 mutant engineered to have reduced heparin binding diffused twice as fast as AAV2 on average, presumably because of reduced adhesion to sputum. We also discovered that the mucolytic N-acetylcysteine could markedly enhance AAV diffusion by altering the sputum microstructure. These studies underscore that sputum is a major barrier to CF gene delivery, and offer strategies for increasing AAV penetration through sputum to improve clinical outcomes.