Digital Pulmonology Practice with Phonopulmography Leveraging Artificial Intelligence: Future Perspectives Using Dual Microwave Acoustic Sensing and Imaging

Our plain-English summary of Digital Pulmonology Practice with Phonopulmography Leveraging Artificial Intelligence: Future Perspectives Using Dual Microwave Acoustic Sensing and Imaging, by A.K. Sethi, P. Muddaloor, P. Anvekar, et al (Sensors, 2023).

The study

• Authors: A.K. Sethi, P. Muddaloor, P. Anvekar, J. Agarwal, A. Mohan, M. Singh, K. Gopalakrishnan, A. Yadav, A. Adhikari, D. Damani, K. Kulkarni, C.A. Aakre, A.J. Ryu, V.N. Iyer, S.P. Arunachalam
• Journal: Sensors
• Published: 2023;23(12)
• Type of article: Review
• Cited by: 4 articles, as counted by NIH iCite
• Read it: PubMed · Publisher · Free full text

Abstract

Respiratory disorders, being one of the leading causes of disability worldwide, account for constant evolution in management technologies, resulting in the incorporation of artificial intelligence (AI) in the recording and analysis of lung sounds to aid diagnosis in clinical pulmonology practice. Although lung sound auscultation is a common clinical practice, its use in diagnosis is limited due to its high variability and subjectivity. We review the origin of lung sounds, various auscultation and processing methods over the years and their clinical applications to understand the potential for a lung sound auscultation and analysis device. Respiratory sounds result from the intra-pulmonary collision of molecules contained in the air, leading to turbulent flow and subsequent sound production. These sounds have been recorded via an electronic stethoscope and analyzed using back-propagation neural networks, wavelet transform models, Gaussian mixture models and recently with machine learning and deep learning models with possible use in asthma, COVID-19, asbestosis and interstitial lung disease. The purpose of this review was to summarize lung sound physiology, recording technologies and diagnostics methods using AI for digital pulmonology practice. Future research and development in recording and analyzing respiratory sounds in real time could revolutionize clinical practice for both the patients and the healthcare personnel.

In plain English

This article was a narrative review, not an original study. The authors summarized published literature on how lung sounds are produced, how they are recorded with electronic stethoscopes, and how computer methods, including artificial intelligence, have been used to analyze them. They tabulated studies from 1989 to 2022 and described uses in tuberculosis, pneumonia, COVID-19, interstitial pulmonary fibrosis, COPD, asthma, cystic fibrosis and lung cancer. Asbestos appeared only briefly. On asbestos, the review summarized one earlier study of lung-sound frequencies in patients with asbestos-related lung injury. That study reported that the frequency distribution of lung sounds was significantly associated with interstitial lung fibrosis on high-resolution CT scoring. Inspiratory crackles and high frequencies were linked to fibrotic changes, and low frequencies to emphysematous components. The review also noted that earlier writers had described the crackles of asbestos-related lung fibrosis as characteristic. The authors stated that small sample sizes and failure to filter environmental noise have limited clinical use. They concluded that digital lung sounds show promising potential but that more research is warranted. They also proposed future microwave-based sensors combining sound recording and lung imaging.

We wrote this plain-English summary from the full article with the help of AI, and a second AI model checked each sentence against the article. It is not the authors' wording; the abstract and the article are their own account.

What the study did and found

• Design: Narrative review of published literature on lung sound physiology, recording technologies and AI-based analysis, with a forward-looking proposal for microwave-based sensing
• Who was studied: Published studies, no patients studied directly. A table summarized studies from 1989 to 2022. No search method or number of studies screened is described.
• Exposure: Not an exposure study. Asbestos appears only through a cited earlier study of lung sounds in patients with asbestos-related lung injury, and through historical descriptions of crackles in asbestos-related lung fibrosis. No fiber types or doses are given.
• Main results:
  • The review cited an earlier study (reference 91) reporting that the frequency distribution of lung sounds measured with a computerized lung sound analyzer was significantly associated with interstitial lung fibrosis on high-resolution CT scoring in patients with asbestos-related lung injury.
  • In that cited study of asbestos-related lung injury, inspiratory crackles and high sound frequencies were associated with fibrotic changes, and low sound frequencies with emphysematous components.
  • The review noted historical descriptions: Smither called the crackles of asbestos-induced lung fibrosis characteristic, and Wood and Gloyne described them as a major hallmark of this industrial disease.
  • In a cited study of 39 people with interstitial pulmonary fibrosis (IPF), 95 with congestive heart failure (CHF) and 123 with pneumonia, IPF crackles were distinguished from pneumonia crackles with sensitivity 0.82, specificity 0.88 and accuracy 0.86. They were distinguished from CHF crackles with sensitivity 0.77, specificity 0.85 and accuracy 0.82.
  • In a cited study of patients with rheumatoid arthritis, analysis with a Velcro sound detector (VECTOR) showed 93.2% sensitivity for interstitial lung disease.
• The authors' conclusion: The authors concluded that studies show promising potential for digital lung sounds in pulmonology practice but that more research is warranted. They also concluded that a microwave-based dual sensing approach offers an opportunity for future practice.
• Limitations the authors state:
  • The authors stated that the reviewed research lacked substantial sample sizes and that current models cannot filter environmental noise, which has hindered everyday clinical use.
  • The authors noted that many AI models are black-box types, which limits interpretability.
  • The authors stated that the literature on lung sounds in lung cancer was too limited to draw a definite conclusion.

Topics

Medical terms in this study, explained in our Lexicon: Pulmonology, Interstitial Lung Disease.

Related studies

• Bedside to bench and back again-translational research in interventional pulmonology — B. Iqbal, H.J. Choi, et al. (2025)
• Artificial Intelligence-based Quantification of Pleural Plaque Volume and Association With Lung Function in Asbestos-exposed Patients — K.B.W. Groot Lipman, T.N. Boellaard, et al. (2024)
• Artificial intelligence-based diagnosis of asbestosis: analysis of a database with applicants for asbestosis state aid — K.B.W. Groot Lipman, C.J. de Gooijer, et al. (2023)
• Predicting Mesothelioma Using Artificial Intelligence: A Scoping Review of Common Models and Applications — M. Ram, M.R. Afrash, et al. (2025)
• Development of rapid and highly accurate method to measure concentration of fibers in atmosphere using artificial intelligence and scanning electron microscopy — Y. Iida, K. Watanabe, et al. (2021)
• Application of artificial intelligence in the analysis of asbestos fibers — R. Lee, D. Van Orden, et al. (2025)

Browse more research in Sensors, or return to medical research.