computer science


Computer Scientists Have ‘Moral Obligation’ To Lead Health Care Research, MIT Prof. Says

For the past couple of days, I’ve been tagging along at my husband’s annual work retreat, a gathering on the Cape of big thinkers from MIT’s Computer Science and Artificial Intelligence Lab.

This year, health is on the agenda.

Among those pushing for more research related to health care is John Guttag, a professor in the department of electrical engineering and computer science whose current work focuses on applying advanced computational techniques to medicine. (We featured his recent studies on computational biomarkers that predict heart-attack deaths here.) Guttag told me he believes computer scientists (including those at MIT) have a “moral obligation” to undertake far more research in the areas of health and medicine, indeed, they should lead the way with work that has real-world applications.

In his talk yesterday (which I didn’t attend, but Guttag kindly recounted) he essentially issued a challenge to his colleagues:

Over the next decades, computer science can contribute more to improved healthcare than any other discipline…It is simply unacceptable to be a leading academic computer science research lab without being a leader in research at the intersection of healthcare and computer science.

He added that there’s a lingering perception among computer scientists that their highly technical research shares little common ground with the all-too-real world of health care. “There is often a tension between application pull and technology push,” Guttag said in a followup email. “Academic computer scientists have an easy time applauding new computing techniques, but often struggle at deciding whether novel applications of computing constitute legitimate C.S. research.”
Continue reading

Computer-Derived Markers Help Predict Risk Of Heart-Attack Death

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