AI and Acoustic Health

Doctors have been listening to the sounds our bodies make for centuries. Before the invention of stethoscopes, they simply put their ears to their patients' chests or abdomens, to listen to the sounds produced by our body's internal workings. Today, the practice of auscultation, using a stethoscope to examine a patient, has evolved into a sophisticated diagnostic tool that provides valuable insights into various aspects of our health: lungs, heart, bowel, vocal cords, joints, arterial conditions, sleep quality and more. Moreover, by amalgamating biomarkers and clinical data with a myriad of acoustic cues like sneezes, breath patterns, speech, throat clearings, wheezes, and more, the healthcare decision-making process stands poised for remarkable enhancement. 

Auscultation is a valuable diagnostic tool because it is safe and noninvasive. Doctors place their stethoscopes at various positions on the chest to listen to different heart valves. The sounds they hear include the closure of valves, blood flow, and vibrations of heart tissues. A swishing sound may indicate a heart murmur, which can be benign or serious. In some cases, doctors may hear a sound resembling the rubbing together of two pieces of leather. It can be a sign of pericarditis, an inflammation of the sac surrounding the heart. 

Modern medicine embraces technology to enhance diagnostic accuracy. Digital stethoscopes, for instance, enable the development of integrated artificial intelligence (AI) systems. These AI-assisted auscultation tools aim to remove subjectivity, improve diagnostic precision, and compensate for diminishing auscultatory skills. However, a key challenge lies in normalizing data across devices, as the frequency responses of stethoscopes from various manufacturers can differ significantly.

Innovations in auscultation aren't limited to medical settings. SleepRoutine, an app developed by Asleep Inc., utilizes deep learning algorithms trained with breathing sound data from Seoul National University Bundang Hospital to offer efficient sleep tracking. It offers a non-intrusive and convenient approach to understanding and improving sleep quality. Feedback and feedforward microphones integral to active noise canceling (ANC) hearables can tune in to heartbeats, while feedforward microphones capture the rhythm of respirations. 

The application of body sounds in medical diagnostics is expanding. Previous studies have explored the use of bowel sounds in a wide range of conditions, from intestinal issues to neurological disorders. With the integration of AI technologies, the potential for more advanced diagnostic tools becomes evident. AI-driven analysis of bowel sounds holds promise in creating accessible, patient-friendly, and cost-effective devices that eliminate risks associated with radiation or invasive procedures. The emergence of microwave-based digital phonoenterography opens exciting opportunities for gastrointestinal health. Acoustic monitoring using AI analysis technology has the potential to diagnose various pathological conditions, such as wheezing and blistering sounds and in assessing upper airway presence of fluid, to quantify aspiration risk during monitored anaesthesia care

Incorporating AI techniques into body sound analysis not only assists medical professionals in diagnosing various pathologies but also empowers individuals to take a proactive role in tracking their health independently. These advancements underscore the ever-evolving intersection of technology and healthcare, promising better outcomes and a deeper understanding of our well-being.


Lee T, Cho Y, Cha KS, Jung J, Cho J, Kim H, Kim D, Hong J, Lee D, Keum M, Kushida CA, Yoon IY, Kim JW. Accuracy of 11 Wearable, Nearable, and Airable Consumer Sleep Trackers: Prospective Multicenter Validation Study. JMIR Mhealth Uhealth. 2023 Nov 2;11:e50983. doi: 10.2196/50983. PMID: 37917155.

Arjoune Y, Nguyen TN, Doroshow RW, Shekhar R. Technical characterisation of digital stethoscopes: towards scalable artificial intelligence-based auscultation. Journal of Medical Engineering & Technology. 2023 Apr 3;47(3):165-78.

.Redij R, Kaur A, Muddaloor P, Sethi AK, Aedma K, Rajagopal A, Gopalakrishnan K, Yadav A, Damani DN, Chedid VG, Wang XJ. Practicing Digital Gastroenterology through Phonoenterography Leveraging Artificial Intelligence: Future Perspectives Using Microwave Systems. Sensors. 2023 Feb 18;23(4):2302.

Soomro AM, Naeem AB, Rajwana MA, Bashir MY, Senapati B. Advancements in AI-Guided Analysis of Cough Sounds for COVID-19 Screening: A Comprehensive Review. Journal of Computing & Biomedical Informatics. 2023 Jun 5;5(01):105-17.


Popular posts from this blog

AI for Predicting Heart Transplant Outcomes

Smart Wearables for Cardiac Monitoring