Background: Lower respiratory tract (LRT) involvement, observed in about 20% of patients suffering from coronavirus disease 2019 (COVID-19) is associated with a more severe clinical course, adverse outcomes and long-term sequelae. Early identification of LRT involvement could facilitated targeted and timely interventions that could alter the short- and long-term disease outcomes. The LungPass is an automated lung sound analysis platform developed using neural network technology and previously trained. We hypothesised that the LungPass could be used as a screening tool for LRT involvement in patients with COVID-19.
Methods: In a prospective observational study involving 282 individuals with presenting in the emergency department with a strong clinical suspicion of COVID-19 and imaging findings consistent with COVID-19 LRT involvement (25.5% had concomitant hypoxia), and 32 healthy controls, we assessed the sensitivity and specificity of the LungPass in identifying LRT involvement in COVID-19. We also compared the auscultatory findings of the LungPass compared to a chest physician using a traditional, high-quality stethoscope.
Results: Among individuals with COVID-19 LRT involvement, the LungPass identified crackles in at least one auscultation site in 93.6% and in two or more points in 84%. Moreover, the LungPass identified any abnormal lung sound (crackles or wheeze) in at least one auscultation site in 98.6% and in at least two points in 94% of the participants. The respective percentages for the respiratory physicians were lower.
Considering the presence of any added abnormal sound (crackles or wheeze) in at least two auscultation points as evidence of LRT involvement, LungPass demonstrated a sensitivity of 98.6% (95% confidence intervals [CI]: 96.4%-99.6%) and a specificity of 96.9% (95% CI: 83.8%-99.9%) in identifying COVID-19 LRT involvement.
Conclusion: This exploratory study suggests the LungPass is a sensitive and specific platform for identifying LRT involvement due to COVID-19, even before the development of hypoxia.
Computerized lung sound analysis as diagnostic aid for the detection of abnormal lung sounds: A systematic review and meta-analysis
