AI-powered digital stethoscopes show promise in bridging screening gaps

As tuberculosis (TB) continues as the deadliest infectious cause of deaths globally, a new study has shown that artificial intelligence (AI)-enabled digital stethoscopes can help fill critical screening gaps, especially in hard-to-reach areas.

In a commentary published in the journal Med (Cell Press), global experts contended that stethoscopes combined with digital technology and AI can be a better option against the challenges faced in screening programmes, such as under-detection, high cost, and inequitable access.

“AI-enabled digital stethoscopes have demonstrated promising accuracy and feasibility for detecting lung and cardiovascular abnormalities, with promising results in early TB studies. Training and validation in diverse, high-burden settings are essential to explore the potential of this tool further,” said corresponding author Madhukar Pai from McGill University, Canada, along with researchers from the UAE, Germany, and Switzerland.

Despite advancements in screening and diagnostic tools, an estimated 2.7 million people with TB were missed by current screening programmes, as per data from the World Health Organization (WHO). Routine symptom screening is also likely to miss people with asymptomatic or subclinical TB.

While the WHO recently recommended several AI-powered computer-aided detection (CAD) software, as well as ultra-portable radiography hardware, higher operating costs and upfront hardware act as a deterrent.

This particularly appeared difficult in primary care settings and or among pregnant women due to radiation concerns.

At the same time, AI showed significant potential for screening, including applications beyond CAD of TB from radiographs, said the researchers.

“One application of AI for disease screening is to interpret acoustic (sound) biomarkers of disease, with potential to identify sounds that appear nonspecific or are inaudible to the human ear,” they added, while highlighting the potential of AI in detecting and interpreting cough biomarkers and lung auscultation to analyse breath sounds.