Physiologically Informed Digital Auscultation for Pneumonia Detection in Long-term Care Residents
Updated
Updated · arxiv.org · Sep 23
Physiologically Informed Digital Auscultation for Pneumonia Detection in Long-term Care Residents
1 articles · Updated · arxiv.org · Sep 23
Summary
Researchers have developed an automated digital auscultation system to detect pneumonia in long-term care residents using machine learning on multi-channel lung sound recordings.
The system, trained on data from 185 Japanese residents, showed improved accuracy when supervised with radiologist-confirmed chest X-rays compared to clinician diagnoses.
This approach could enhance pneumonia diagnosis in frail elderly populations, potentially reducing diagnostic delays and unnecessary antibiotic use in nursing homes.