Shape shifting: Researchers at MIT use a technique called dynamic time warping to compare the shape of individual waves in an electrocardiogram, shown here. This approach aligns waves based on features that correspond to the same underlying physiological activity, allowing an automated and accurate comparison. The measure, dubbed morphological variability, appears to predict who is at greatest risk of death after a heart attack.
Collin Stultz
EKG patterns show who will likely die after a heart attack.
A new approach to analyzing electrocardiograms--a ubiquitous test of the heart's electrical function--could predict who is most likely to die after a heart attack. Researchers at MIT found that measuring how much the shape of the electrical waveform varies from beat to beat identifies high-risk patients better than existing risk factors. If the findings hold up in further clinical trials, the technology could be used to figure out which heart attack patients need the most aggressive treatment.
Scientists hope the same approach will eventually help them predict when a healthy person is likely to suffer a cardiac problem. They are working with Texas Instruments to integrate the software into the new generation of wearable heart monitors.
The research also shows how computational analysis can glean useful information from the reams of medical data routinely collected and ignored. "It's a very novel approach," says Jean-Philippe Couderc, biomedical engineer at the University of Rochester, who was not involved in the project. "It's a unique way of looking at how the electrocardiogram varies on a beat to beat basis."
Electrocardiograms record the heart's electrical activity through sensors placed on the chest. Cardiologists can then spot abnormal heart rhythms by visually inspecting the resulting waveform for major features linked to the function of the top and bottom chambers of the heart, as well as the heart's ability to "reset" itself between beats. While some simple algorithms exist to analyze this data, they are notoriously inaccurate. "Cardiologists routinely ignore them," says Collin Stultz, a professor at MIT, as well as a practicing cardiologist, who is involved in the project.
To determine if more subtle features within electrocardiogram data could provide useful clinical information, Stultz, John Guttag, also at MIT, and Zeeshan Syed, now at the University of Michigan, started with a large data set of 24-hour electrocardiogram recordings collected at Brigham and Women's Hospital in Boston as part of a clinical trial for a new drug. Employing a number of computational techniques, including signal processing, data mining, and machine learning, the researchers developed a way to analyze how the shape of the electrical waveform varies, a measure they dubbed morphological variability. At the heart of the approach is a method called dynamic time warping, used in speech recognition and more recently in genome analysis, which allows researchers to align and compare individual beats. "We compute the differences for every pair of beats," says Stultz. "If there is lots of variability, that patient is in bad shape."
The team then applied the algorithm they had developed to a second set of electrocardiogram recordings and found that patients with the highest morphological variability were six to eight times more likely to die after a heart attack than those with low variability. "We found that it consistently works as well or better than commonly accepted risk metrics that physicians use," says Stultz, including diabetes, age and smoking status, as well as cardiac ultrasound and various blood tests.
A pacemaker-like device aims to get victims to the hospital faster.
John Guttag says using computers to automate some diagnostics could make medicine more personal.
The problem is that although the test is cheap... in itself, and another tool for quality, the issue is the tort risks.
For example, if the computer points to an increase chance of a heart attack... and the doctor discards it or if the probibility is unlikely and the patient has a heart attack, the physician could risk a tort case for failure to diagnose.
Thus, the physician will be face with ordering many more expensive tests to protect himself from a tort.
All of medicine is probability... For the consumer and the physician its a lose-lose situation...
Just one more , damned if you do, damned if you don't, unaswerable solution.
Until there is radical tort reform, such as arbitration... the costs of care will only increase dramatically, since, the number one cause of death is cardiac related.
ron hansing, md
I believe Dr. Hansing's viewpoint to be informed, yet pessimistic. First, scientific exploration, as is the topic of this article, should not initially be constrained by limiters like tort reform. Instead, the endeavor should be viewed for what it is, an attempt down the road to possibly bring order and efficiency (benefits) to future patients and researchers.
Finally, tort reform in and of itself is merely an oxymoron, like jumbo shrimp or light beer. Having been on both sides of the conflict, the practical level of reform that could (or should) be implemented is very low, and would, in my view, deal mainly with reformation of the American Rule (mainly when it is applied and how). Thus, reacting to tort reform in the scientific realm of new innovations is very limiting, and real researchers should ignore it entirely if at all possible if they hope to be productive.
cjm
Engineer turned medical student
Manufacturing in the United States is in trouble. That's bad news not just for the country's economy but for the future of innovation.
On Twitter
Become a Fan on Facebook
Subscribe to the Feed
sjmcm3
2 Comments
prior work in this field recalled
From when I was studying Comp. Sci. at Washington University in St. Louis, 1974-76, I recall a job interview and discussions of work at the University's Medical School with a portable recording ekg they'd developed for patients with a prior heart attack, which would then transmit its data via dialup modem to a computer at the med. school, to be analyzed to see whether a subsequent attack could be predicted by the waveform analysis. I think I recall that it proved a failure.
Reply
doctorcloud
2 Comments
Re: prior work in this field recalled
An interesting historical note, though I view this as clearly not relevant today (35 years later) for anything other than footnote or citation purposes. Failure is necessary in R&D, and the only way to learn how to move ahead. You learn way more from failure than from success.
cjm
Engineer turned medical student
Reply