nm-alexa-hows-my-heart_feature
nm-alexa-hows-my-heart_preview

The Future of Artificial Intelligence in Cardiology

Move aside, Captain Kirk. The light placed on artificial intelligence in the field of medicine grows increasingly bright, illuminating opportunity across all specialties. It’s a mission fueled with possibility, with promising research already being developed.

Among those paving the way for the future, Northwestern Medicine Bluhm Cardiovascular Institute announced a $25 million gift that will help develop a first-of-its-kind center that utilizes artificial intelligence and machine learning to advance the study and treatment of heart disease. This will allow for earlier detection, which will lead to better management and outcomes.

Rethinking the Stethoscope?

Bluhm Cardiovascular Institute is pioneering the use of artificial intelligence (AI) for cardiac screening in a new study of Eko’s cardiac monitoring platform. The study aims to demonstrate that Eko’s digital stethoscopes and AI algorithms can interpret heart sounds accurately to help screen for pathologic heart murmurs and valvular heart disease.

“If proven effective, Eko’s platform could be a much simpler, lower-cost way to identify patients with heart disease,” says James Thomas, MD, director of the Center for Heart Valve Disease at Bluhm Cardiovascular Institute. “We are looking to support and advance work that broadens access to the best diagnostic tools in health care, regardless of whether a patient lives in the city, a more rural area or even in a remote locale in the developing world. Deep learning provides that expert knowledge, regardless of a patient’s location.”

Despite serving as an icon in medicine for two centuries, the stethoscope can be a challenging tool for healthcare providers to master. It takes a highly trained professional to separate subtle abnormalities from normal heart sounds. Using AI for cardiac screening in the Eko cardiac monitoring platform would allow general practitioners to be able to detect heart murmurs or life-threatening disease.

Improving Cardiac Imaging

Northwestern Medicine has also partnered with Bay Labs, a San Francisco-based startup focused on applying deep learning to ultrasound and cardiovascular imaging, to examine how AI can be used to guide acquisition (and ultimately interpretation) of echocardiograms, or ultrasound examinations of the heart. This would enable certified medical assistants to perform echoes and other imaging testing that typically require years of specialized training. The study, called SHAPE (Seeing the Heart With AI Powered Echo), is the first project of its kind. A similar study using nurses to scan patients is coming to the Northwestern Echo Lab.

This type of technology taps into deep learning, an AI method that imitates the human brain in processing data for decision-making and continues to learn the more data it receives. This would allow primary care settings to use advanced technology to diagnose heart conditions earlier, and involve cardiologists to confirm diagnosis and initiate care sooner.

“Deep learning will have a profound impact in cardiac imaging in the future, and the ability to simplify acquisition will be a tremendous advantage to bring echocardiograms to the point-of-care in primary care offices,” says Patrick M. McCarthy, MD, chief of cardiac surgery at Northwestern Memorial Hospital.

Training Future AI Specialists in Heart Disease

Another exciting initiative of Bluhm Cardiovascular Institute’s Center for Artificial Intelligence in Cardiovascular Medicine is a collaboration with computer scientists from Northwestern University’s Evanston campus to offer a first-of-its-kind intensive fellowship teaching deep-learning techniques to trainees in cardiology and cardiac surgery. Beginning with a three-month AI “boot camp,” trainees will learn the tools and techniques of AI programming, then spend the remainder of the year applying this methodology to important problems in cardiology.

Alexa, How’s My Heart?

The patient wearables industry, which involves technology synced with your smartphone and other devices, continues to be an area of exploration. Using a deep neural network to access heart rate data, wearables may detect possible irregularities in your heart rhythm. These devices have the potential to read your EKG.

So while it may sound like a scene from sci-fi movie, AI is being readily embraced in health care, and it is sure to play a vital role in the coming years.

Northwestern Medicine Bluhm Cardiovascular Institute