When someone answers the door and enters a hospital room, carrying a stethoscope is a clear sign that they are a doctor. This device has been around for over 200 years and remains a staple in the clinic despite significant advances in diagnostics and medical technologies.
The stethoscope is a medical instrument used to listen to and amplify the internal sounds produced by the body. Doctors still use these sounds as early indicators of heart or lung disease. For example, a heart murmur or lung crackle usually indicates the presence of a problem. Although there have been significant advances in imaging and monitoring technologies, the stethoscope remains a quick, accessible, and cost-effective tool for assessing patient health.
While stethoscopes remain useful today, audible symptoms of the disease usually appear only in later stages. At that point, treatments are less likely to work and results are often unfavorable. This is especially true for heart disease, where changes in heart sounds are not always clearly defined and can be difficult to hear.
We are scientists and engineers exploring ways to use heart sounds to detect diseases earlier and more accurately. Our research suggests that combining stethoscopes with artificial intelligence could help doctors rely less on the human ear to diagnose heart disease, resulting in more timely and effective treatments.
History of the stethoscope
The invention of the stethoscope is widely attributed to the 19th century French physician, René Théophile Hyacinthe Laënnec. Before the stethoscope, doctors used to place their ear directly on the patient’s chest to listen for abnormalities in breathing and heart sounds.
In 1816, a girl with symptoms of heart disease consulted Laënnec. However, placing your ear on your chest was considered socially inappropriate. Inspired by children who transmitted sounds through a long wooden stick, he rolled up a sheet of paper to listen to his heart. He was surprised by the sudden clarity of heart sounds, and thus the first stethoscope was born.
Over the next two decades, researchers modified the shape of this primitive stethoscope to improve its comfort, portability, and sound transmission. This included the incorporation of a thin, flat membrane called a diaphragm, which vibrates and amplifies sound.
The next major breakthrough came in the mid-1850s, when Irish physician Arthur Leared and American physician George Philip Cammann developed stethoscopes capable of transmitting sounds to both ears. These binaural stethoscopes use two flexible tubes connected to separate earcups, allowing for clearer and more balanced sound by reducing outside noise.
These early models are remarkably similar to the stethoscopes used by doctors today, with only slight modifications designed primarily for user comfort.
We recommend: The first heart transplant in Mexico turns 37: history of an illegal intervention
listening to the heart
Medical schools continue to teach the art of auscultation: the use of sound to evaluate the function of the heart, lungs, and other organs. Digital models of stethoscopes, commercially available since the early 2000s, offer new tools such as sound amplification and recording; However, the basic principle introduced by Laënnec still endures.
When listening to the heart, doctors pay close attention to the familiar “lub-dub” rhythm of each beat. The first sound, the lub, is produced when the valves between the upper and lower chambers of the heart close as they contract and push blood toward the body. The second sound, the dub, is produced when the valves leading out of the heart close as they relax and fill with blood.
In addition to these two normal sounds, doctors also look for unusual noises, such as murmurs, extra beats, or clicking, which may indicate problems with blood flow or proper functioning of the heart valves.
Heart sounds can vary considerably depending on the type of heart disease present. Sometimes different diseases produce the same abnormal noise. For example, a systolic murmur (an extra noise between the first and second heart sounds) may be heard with a narrowing of the aortic or pulmonary valve. However, the same murmur can also appear when the heart is structurally normal and healthy. This overlap makes it difficult to diagnose diseases based solely on the presence of murmurs.
Teaching AI to hear what people can’t
AI technology can identify hidden differences in the sounds of healthy and damaged hearts and use them to diagnose diseases even before traditional acoustic changes, such as murmurs, appear. Instead of relying on the presence of additional or abnormal noises to diagnose illnesses, AI can detect differences in sound that are too weak or subtle for the human ear to detect.
To develop these algorithms, researchers record heart sounds using digital stethoscopes. These stethoscopes convert sound into electronic signals that can be amplified, stored, and analyzed by computers. Researchers can then label which sounds are normal or abnormal to train an algorithm that recognizes patterns in the sounds and can then use them to predict whether new sounds are normal or abnormal.
Researchers are developing algorithms that can analyze digitally recorded heart sounds in combination with digital stethoscopes as an inexpensive, non-invasive and accessible tool for heart disease detection. However, many of these algorithms are based on moderate to severe heart disease data sets. Because of the difficulty of finding patients in the early stages of the disease, before symptoms begin to appear, algorithms lack much information about what hearts sound like in the early stages.
To address this shortcoming, our team uses animal models to teach algorithms to analyze heart sounds and detect early signs of disease. After training the algorithms with these sounds, we evaluated their accuracy by comparing them with images of calcium buildup in the heart.
Our research suggests that an AI-based algorithm can correctly classify healthy heart sounds in more than 95% of cases and even differentiate between types of heart disease with close to 85% accuracy. More importantly, our algorithm is able to detect the early stages of the disease, before heart murmurs or structural changes appear.
* Valentina Dargam is Research Associate Professor of Biomedical Engineering, Florida International University; Joshua Hutcheson is Associate Professor of Biomedical Engineering, Florida International University.
This text was originally published in The Conversation
Little text and great information in our X, follow us!
