Abstract The diagnostic performance of the World Health Organization’s Integrated Management of Childhood Illness guidelines for child pneumonia could be improved by incorporating lung auscultation. Although challenging for non-physician health workers to effectively use a conventional stethoscope, a digital stethoscope enhanced by artificial intelligence capabilities may be an alternative. In this feasibility study we aimed to evaluate whether non-physician primary care health workers can record quality lung sounds from under-5-year-old children. Non-physician primary care health workers called community health care providers recorded lung sounds from four protocolised chest positions using a digital stethoscope in 2-59-month-old children attending first-level rural clinics in Bangladesh. A paediatrician listening panel, trained to a standardised interpretation protocol, classified the recordings. A quality recording was defined a priori as the panel classifying three of four chest positions on a participant as interpretable. Lung sounds were recorded from 990 children, and the panel classified 867 children as having a quality recording (87.6%; 95% confidence interval: 85.4%, 89.6%). Of these, 89.8% (766/853) were recorded within five minutes. This study demonstrates non-physician primary care health workers at rural, first-level clinics in Bangladesh are capable of timely, quality recordings of lung sounds from most children using a digital stethoscope.
Ahmed et al. (Tue,) studied this question.