AI to Revolutionize the Stethoscope

Connor Landsgraf, CEO of San Francisco startup Eko Devices, believes it is time to upgrade the stethoscope, which he pointed out has not changed since the 1880s.  He claims many physicians do not get adequate training on how to interpret the sounds they hear with a classic stethoscope. He says the result is “rampant misdiagnosis”.  Eko has developed a computerized insert for stethoscopes. The insert will provide data from the stethoscope to a smartphone, which can then analyze the data and compare it with cloud-based sound patterns representing various conditions. The goal is to help physicians make data-driven decisions resulting in improved patient outcomes. This paragraph was my book, Robot Attitude: How Robots and Artificial Intelligence Will Make Our Lives Better. Things have changed since then.

The company has one product achievement after another. In 2018, Eko introduced CORE Digital Stethoscope featuring noise cancellation, amplification, and recording capabilities. The Eko device looks like a stethoscope except it has a digital capturing device in the familiar black tube. The following year, Eko launched its app, allowing on-device sound visualization, annotation, and sharing of recordings. In 2020, Eko AI software received its first FDA clearance, aiding in the detection of murmurs and atrial fibrillation (AFib). The following year Eko introduced CORE 500™ Digital Stethoscope, offering improved sound quality and AI-powered analysis for both murmurs and AFib. AI has added a lot of capability to the digital stethoscope, and much more is on the way.

In 2022, Eko expanded its AI capabilities with the introduction of lung sound analysis algorithms for detecting pneumonia and chronic obstructive pulmonary disease (COPD). I know several pulmonologists who have a huge amount of anecdotal data in their brains from decades of listening to people’s chests. One study suggested, with the power of AI and the digital stethoscope, a resident pulmonologist in training can provide a more accurate diagnosis.

In 2023, Eko secured additional FDA clearances for its AI software, further solidifying its role in diagnostic support. The company introduced Eko SENSORA, a platform which will further integrate AI and revolutionize cardiac and pulmonary care. SENSORA goes beyond just providing a digital stethoscope or AI assistance. It’s a cloud-based platform which combines Eko’s AI-powered algorithms with their digital stethoscopes to offer a range of valuable tools and functionalities for healthcare professionals.

 The new features introduced by SENSORA are significant. Structural Murmur Detection will use AI algorithms to analyze heart sounds and flag potential murmurs with high accuracy, aiding in the early detection of valvular heart disease (VHD). VHD is a broad term encompassing any abnormality affecting the heart’s four valves. Another important feature is Eko’s Virtual Care & Telehealth will facilitate remote consultations using Eko’s digital stethoscopes, enabling healthcare providers to examine and diagnose patients even when physically distant. Overall, Eko SENSORA represents a paradigm shift in cardiac and pulmonary care.

Integrating AI and digital technology will bring advanced analysis and insights to the 100+ year-old ubiquitous medical tool. The AI algorithms will help identify potential issues earlier, enabling timely interventions and treatment. The bottom line is Eko and its SENSORA platform will move healthcare a big step closer to data-driven healthcare and pave the way for personalized medicine and informed clinical decision-making.

In study data published in the journal Circulation and presented at the American Heart Association’s scientific sessions last week, Eko found the AI tool could significantly improve murmur detection and the rate of valvular heart disease (VHD) diagnoses. The study spanned a total of 369 patients who were at least 50 years old and had never been diagnosed with VHD or a heart murmur. Each patient was examined using both a standard analog stethoscope and one of Eko’s digital stethoscopes, equipped with the AI algorithm. After comparing the results of each examination to echocardiogram data, the AI-equipped stethoscope was found to be able to spot signs of VHD with about 94% sensitivity, compared to just over 41% for the standard stethoscopes. In total, the AI was able to identify 22 patients with “moderate-or-greater” cases of the disease that had gone previously overlooked, while the analog method uncovered only eight new cases.

There is much more to the study which needs to be analyzed. The technology is not perfect, but it looks clear to me AI will have a growing positive impact on healthcare outcomes for patients. This is just one area of healthcare. I expect five years from now we will be amazed at how much AI had improved health outcomes.

Note: I use Bard AI and other AI chatbots as my research assistants. AI can boost productivity for anyone who creates content. Sometimes I get incorrect data from AI, and when something looks suspicious, I dig deeper. Sometimes the data varies by sources where AI finds it. I take responsibility for my posts and if anyone spots an error, I will appreciate knowing it, and will correct it.