Heart disease is the number one cause of death in the US every year since the 1920sand good for almost one in three deaths in 2019 (874,613 lives lost). frustrating, at least 200,000 dead of heart disease and stroke could be avoided every year. The solution starts with correctly identifying patients with heart disease and ensuring they are treated in a timely manner and appropriately. Using the latest data science tools, such as artificial intelligence (AI), we can leverage the vast amount of healthcare data being generated to solve this problem. However, before talking about solutions, let’s dive deeper into the problem.
First we need to know who has heart disease. Millions of Americans, and many more worldwide, suffer from treatable heart disease, but many are unaware of their condition and live “undiagnosed” for years. Without knowing who actually has heart disease, patients cannot be treated to avoid potentially devastating consequences. For example, atrial fibrillation (Afib) is an abnormal heart rhythm that affects 5.3 million Americans. It significantly increases the risk of stroke; in reality, almost a quarter of all strokes of unclear origin result in a new diagnosis of Afib, and these strokes usually result in permanent debilitation. Two-thirds of strokes related to Afib are preventable if doctors and patients are aware of the diagnosis; unfortunately one an estimated 700,000 Americans suffer from Afib but don’t know they have it.
Second, even if we know that patients have heart disease, a large proportion are not receiving guideline-based medical therapies that have been proven to prolong life and reduce suffering. Of the thousands of heart failure patients in a recent research, three of four patients missed at least one of eight indicated, guideline-recommended therapies. Undertreatment has been a problem we’ve faced in the US for decades, and it’s not unique to cardiology. A Study from 2003 showed that only half of the medical care recommended by the guideline was provided to US adults, for a variety of acute and chronic conditions, including preventive care. The combination of both undertreated and undiagnosed heart disease leads to a large burden of likely avoidable, debilitating consequences such as stroke and premature death.
How can such a large burden of heart disease go undiagnosed or untreated when the US has access to some of the most advanced treatments and healthcare technology? The problem — and therefore the solution — is multifaceted and very complex. A recent research sheds some light on one of the major obstacles: the vast amounts of data and guidelines clinicians must sift through in order to effectively treat patients. Researchers have estimated that primary care physicians need 26.7 hours a day of 24 hours to keep pace with and provide essential guideline-oriented medical care to patients. This impossible task leads to enormous frustration and burnout for doctors, while patients are left with the burden of an undiagnosed or undertreated disease.
More specifically, a cardiologist under 10 minutes averaged to interpret an echocardiogram (an ultrasound or imaging study of the heart). An echocardiogram consists of about 100 separate videos, so the cardiologist only has a few seconds to flip through each video to make a diagnosis. This leaves little to no time for perusing a patient’s medical history and file, which often consists of hundreds of clinical notes, labs, and complicated test reports. Important clinical information that can aid in accurate interpretation of the echocardiogram, such as family history or recent abnormal lab results, is often buried.
Data science and AI, which have already shown promise in cardiology, can help solve this problem. A study published in Nature Biomedical Technology showed that a neural network, a type of AI, can help improve doctors’ ability to predict clinical outcomes from echocardiograms. Neural networks are the same type of AI method that enables facial or object recognition in photos taken with our smartphones, and these approaches are now showing promise to help find undiagnosed heart disease. Multiple studies, such as Research in The Lancet and a study we co-authored Circulation, have demonstrated the ability to identify patients at high risk for undiagnosed Afib by using AI to analyze their 12-lead electrocardiogram (ECG). In the Circulation study, more than half of the patients who had a stroke as their first manifestation of Afib would have had a “high risk” result prior to the stroke if their EKG had been analyzed. This gives us hope that integrating these algorithms into clinical practice can help us treat patients more quickly to prevent stroke. Afib is just the tip of the iceberg – new studies are regularly published that use data science and AI to address a variety of heart and cardiovascular diseases, including structural heart diseaseabnormal electrical activity in the heart, pulmonary hypertensionand even approaches to reduce the undertreatment of atrial fibrillation and heart failure.
With mounting evidence highlighting the promise of new technologies, how do we ensure they are implemented clinically to minimize the devastating consequences of undiagnosed and undertreated heart disease? Although the steps are complex, we can learn from the playbook of other medical specialists, such as oncologists who treat cancer, the second lead cause of death for Americans. Oncologists have widely adopted data-driven precision medicine; they expect a combination of multimodal molecular, clinical and imaging data to not only inform what therapies they offer to patients with cancer, but also help match their patients with clinical research trials to bring the next generation of novel cancer therapies to market.
Cardiology is now able to make the most of multimodal clinical data — clinicians can soon expect to see a patient’s ECG or echocardiogram interpreted using AI algorithms, within the context of all available imaging, lab and genomic data. This not only ensures the most accurate diagnoses, but also optimizes important next steps to be discussed with patients, including potential therapies, additional investigations to evaluate the risk of undiagnosed heart disease, and relevant clinical trials. It’s time to move beyond the status quo of the past decades and step forward into the data-driven precision medicine of the future. If we don’t, the consequences of undiagnosed and undertreated heart disease will continue to devastate millions of people.