Computers can help predict who might die after a heart attack
About 1.5 million Americans have heart attacks each year. Most end up recovering, but around 2.5% of them are dead within 90 days and 5 percent die within a year. Currently, no method can precisely predict who’s at risk: Is it your 74-year old father or the 49-year-old mom you chat with at the gym?
Common ways to identify high-risk patients include measuring certain biochemical substances, tracking the heart’s activity with echocardiograph (EKG) data and medical history. But such indicators don’t identify everyone who is high-risk. How then, can you up your odds?
Well, a team of cardiologists and computer scientists from MIT and the University of Michigan have come up with a series of computational biomarkers based on EKG data that when combined with standard measures can better predict which heart attack patients are more likely to die. Their research is published this week in the journal Science Translational Medicine.
Saving Tens Of Thousands
MIT Electrical Engineering and Computer Science Associate Professor Collin Stultz, one of the study authors and a cardiologist at Brigham and Women’s Hospital and the West Roxbury VA Hospital, says by overlaying the new computer-derived markers onto the standard biomarkers, one’s ability to predict the risk of death after a heart attack increases by about 10 percent, which could “potentially save tens of thousands of lives each year.” Continue reading
CEO turnover, attitudes toward medical errors and the overall gestalt of a hospital has a direct impact on heart attack patients’ 30-day survival, according to a Yale study detailed in The Wall Street Journal.
The study, which appear in The Annals of Internal Medicine, concludes:
High-performing hospitals were characterized by an organizational culture that supported efforts to improve…care across the hospital. Evidence-based protocols and processes, although important, may not be sufficient for achieving high hospital performance in care for patients…
In other words the culture and priorities of a hospital may be as important as its medical protocols in terms whether you live or die after a heart attack.
Or, as the story says:
…the presence of a “strong organizational culture” was associated with variances in death rates of as much as 9.5 percentage points.
The researchers conducted interviews with a total of 158 staffers — all involved with heart attack care — at 11 hospitals across the U.S. They found few differences in what protocols the hospitals used in treating heart attacks, but big ones in how hospitals were managed and how they approached quality improvement.
“It’s not so much what they’re doing but how they’re doing it,” Leslie Curry, a researcher at Yale’s Global Health Leadership Institute and lead author of the study…
High turnover among nurses was also a trait of hospitals with high 30-day mortality rates, the researchers found.
Using mistakes as learning experiences as opposed to reasons for punishment was another characteristic of top performers, Curry says. And views of nurses, pharmacists, technicians and even housekeeping staff were highly valued in the team approach used at the best hospitals, she added.
Inspired by our own reporting about the new “hands-only” CPR method (here and here, including how-to videos) I took a CPR course last night at my local health department, and am happy to report that aside from the highly useful practice performing chest compressions, I came away with a musical tip:
The best song to help you maintain the rapid rhythm you need for chest compressions is not, as previously suggested, The Beegees’ ‘Stayin’ Alive.’ Why mar heroic lifesaving with hideous disco? Our instructor suggested an alternative much more to my taste: Queen’s “Another One Bites The Dust.”
Think of those excellent three beats before the chorus. They get you right into the 100-beats-per-minute rhythm you need. Just one thought, though: Maybe best not to sing the lyrics aloud to your patient…
The new CPR guidelines from the American Heart Association are not due out until next week. But Dr. Aaron Baggish of Massachusetts General Hospital — and many other cardiologists — have no doubt about what’s coming: A recommendation that everyone learn the new “hands-only” CPR.
See our earlier post on the technique and its nuances here.
The new guidelines are eagerly awaited, Dr. Baggish said, and based on extensive research showing that the new “compression-only” technique is twice as effective as the old standby. (The latest study came out just yesterday in The Lancet. It’s here.)
“The new guidelines are going to emphasize the importance of early chest compression as the important first step in CPR.” he said. “And this is a major change in the paradigm. For a long time, we’ve tried to get air into people before worrying about chest compressions, and for a number of reasons, it’s now clear that’s not the best thing.” Continue reading
The best e-mailer I know, a Cape Cod octogenarian named Jack Alden, sends me a few gems a week — helpful hints, bits of wisdom, jokes that lighten my days. A couple of weeks ago, he passed along this University of Arizona video on a new form of CPR.
At the time, all I thought was that it looked strenuous — you have to do rapidfire compressions on the heart attack victim’s chest — but effective. And that it was nice that you didn’t have to encounter alien saliva by going mouth to mouth with the patient.
Now there’s a major new study out in the Journal of the American Medical Association suggesting that this new, simpler form of CPR can save more lives, in large part because it makes bystanders more willing to try to help. The journal’s video report on its study is here:
The move toward simplifying CPR is the lead story in the Harvard Health Letter this month. Evidence in favor of the simpler CPR is growing, it says, but there are some nuances:
Among patients diagnosed as having a probable heart attack, emergency room staffs tend to treat everyone alike. But among patients merely suffering chest pain, those who are African-American or Hispanic are less likely to be classified as emergency cases and to get EKGs and other cardiac testing, according to a national study just released by Massachusetts General Hospital and published in the journal Academic Emergency Medicine.
The hospital reports:
Among patients who received an ED diagnosis of probable myocardial infarction (heart attack), there were no significant differences in initial symptoms between racial or ethnic groups…But among all those presenting with chest pain, African American and Hispanic patients were significantly less likely than white patients to be triaged as emergent. In addition, African American and Hispanic patients, as well as those who were uninsured or covered by Medicaid, were less likely to receive such basic cardiac testing procedures as ECG, cardiac monitoring or measurement of cardiac enzymes. Factors such as whether patients arrived by ambulance or the day of the week on which they were seen did not make any difference.
“These differences in ED triage may be important drivers of disparities in testing, procedures and eventual outcomes,” says [lead author Lenny] Lopez. “If you are misclassified at this first step, you’re less likely to get the ECG because your condition is not considered urgent. In the long term, you may have an even more severe heart attack that could have been prevented if intervention had occurred earlier. This is not an area of medicine where there is a lack of clarity about what we are supposed to do, so quality improvement strategies need to focus on 100 percent guideline-driven triage management for every single patient.”