By Nicole Foster
Science is constantly marching forward, and modern technologies mean that march toward the future is accelerating all of the time.
Fortunately, some doctors and researchers are putting that forward momentum to good use when it comes to heart attack prediction. These scientists are working tirelessly to find ways to predict heart attacks years before any symptoms arise — because early prediction means early intervention, and early intervention can save lives.
Physicians have been trying to predict heart attacks for as long as there have been heart attacks. Traditionally, they have relied on standard assessments of cholesterol, blood pressure, lifestyle factors and health conditions such as diabetes to predict whether a patient is likely to suffer a heart attack.
Age, lipid levels, obesity, lack of activity and stress can all contribute to blocked arteries, preventing blood flow to the heart, says Dr. Arshed Quyyumi, professor at Emory University School of Medicine. By gathering data, test results and patient information, cardiologists like Quyyumi can generate a score that indicates a patient’s heart attack risk.
“It’s not an exact prediction,” says Quyyumi. “We use the scores to reduce risk and to prevent disease, heart attack or sudden cardiac death. They’re now developing new technologies which might get us to better predict [cardiovascular disease].” Some of those technologies are even coming from corporations. Apple partnered with Stanford Medicine to use data from Apple Watches to power a massive heart study. Fitbit, TomTom, Garmin and countless other wearable technology companies build heart-monitoring tools into their products. Toyota is working with researchers at the University of Michigan to study how their cars can detect when drivers are having a cardiac event; initial results of that study are expected in 2020.
Meanwhile, cardiologists are looking to artificial intelligence (AI), retinal scans and qualitative research for new, predictive strategies.
The Synergizing Epidemiologist
Dr. Stephen Weng is an assistant professor at University of Nottingham and a research fellow for the National Institute for Health Research. He and his team have developed an algorithm that marries artificial intelligence and face-to-face time with your doctor. His system can predict heart attacks 10 years before they occur with 76 percent accuracy.
The algorithm sorts through all of the electronic patient records within a practice, recognizing a specific set of data that suggests a heart attack is imminent. In trials, the AI was able to determine an individual’s risk in a matter of minutes.
Depending on the patient’s cardiac forecast, their physician may begin appropriate interventions with medications to manage cholesterol, diabetes and high blood pressure as well as recommendations and plans to change damaging habits.
“A doctor can look at a list of individuals at risk of heart disease and say, ‘Let’s call them in,’” says Weng. “That’s prevention.” In trials, the system predicted 7.6 percent more events than traditional methods with 1.6 percent fewer false alarms.
In the sample size of 83,000 records, that means an additional 355 lives could have been saved using the AI compared to standard prediction methods. Before the program can find its way into your doctor’s office, Weng will need to rely on software companies to figure out how to make the algorithm compatible with existing in-office systems.
In order for the AI to translate in the U.S., Weng will also need to tweak the algorithm based on differing ethnicities and genetics. “This was developed in a population of British individuals and may not translate entirely to other populations,” he explains. “We’ll retrain the algorithm for the population you’re targeting. Take the same methodology, use a different population group, and it becomes a unique algorithm for that population.”
Weng has figured out all of the answers except one: What happens if a patient is found to be at low risk of a heart attack? Will that patient interpret the news as permission to indulge in unhealthy foods? Will they decide to excuse themselves from exercising, worsening their heart attack forecast? Weng will only know these answers when the algorithm is released, which he thinks will be in the next year.
The Eyes Are the Window to… the Heart?
Dr. Lily Peng, a product manager at Google, works with a team of researchers to learn how blood vessels in the eyes can predict heart attack risk. According to Peng, patients’ retinal scans contribute valuable information to her group’s algorithm.
Together, the components were quite successful at recognizing which patients had experienced a cardiovascular event. “Given the retinal image of one patient who later experienced a major cardiovascular (CV) event, such as a heart attack, and the image of another patient who did not, our algorithm could pick out the patient who had the CV event 70 percent of the time,” says Peng. “This performance approaches the accuracy of other CV risk calculators that require a blood draw to measure cholesterol.”
Although testing is still in early phases, Peng recognizes this as a very promising start. To make retinal fundus photography useful to patients, Peng and her research team will continue to study the effects of interventions such as lifestyle changes and medications in correlation with risk predictions. For now, they will keep generating new hypotheses and theories to test.
Peng hopes to someday see retinal cameras in physicians’ offices where the photographs would become a standard, non-invasive test for heart patients. “There are sophisticated, non-invasive tests for cardiovascular risk, such as coronary calcium CT scans,” says Peng. “If future research pans out, we hope that the simpler technique of retinal fundus photography could give additional information about cardiovascular risk non-invasively.”
Inside the Body
While wearable monitors, AI, cameras and other technology are extraordinarily useful tools in the fight to prevent heart attacks, some indicators may have been inside patients all along. Cardiologists are studying how certain gut bacteria, biomarkers and molecules can provide clues about a patient’s likelihood of a heart event.
The European Society of Cardiology found that measuring levels of a molecule called trimethylamine N-oxide (TMAO), which is produced by gut bacteria, could help them reliably assess a patient’s risk of heart problems. They believe that measuring TMAO levels could predict the risk of death up to seven years later.
Researchers at UT Southwestern Medical Center have identified five tests that, when combined, improve prediction of heart disease, heart failure, heart attack and stroke compared to currently recommended approaches. These include a 12-lead EKG, coronary calcium scan and blood tests for C-reactive protein, the hormone NT-proBNP and high-sensitivity troponin T.
Back at Emory, Dr. Quyyumi and his colleagues have identified a trio of biomarkers that may help with prediction.
Quyyumi is interested in looking at plaques in the bloodstream as predictors. Some plaques, he explains, remain “quiet,” while others are active. These active plaques become inflamed and are more likely to rupture, leading to heart attack or death.
His question for future research is “Can we try to detect activation of plaque by looking for blood markers?” When asked if he thought early prediction may eventually eradicate heart attacks, Quyyumi said that years ago, his answer would have been no. Today, though, he’s more optimistic. “I think it is possible. We can diagnose the condition much better. It’s possible this will become less of a problem. We’re moving in the right direction.”