Hospital-acquired infections kill about 90,000 people every year in the United States and account for half of all major in-hospital medical complications. “If you find these outbreaks and act on them, you can cut down on the number of infections,” says Stephen E. Brossette, president of Birmingham, AL-based MedMined and pathology resident and researcher at the University of Alabama, Birmingham. “Finding them is the problem.” Hospital infection-control staff typically hunt for outbreaks by thumbing through hundreds of pages of results from every test for microbes performed by their hospital labs. In such an ocean of data, only the largest and most conspicuous outbreaks get caught.
To catch what humans miss, Brossette is using computers that comb through these vast data sets. When he was a graduate student at UAB, he and Associate Professor Stephen A. Moser developed a tool called the Data Mining Surveillance System (DMSS) that sniffs out patterns in medical data that are too subtle or complex for humans to detect. When MedMined recently used DMSS to crunch 11 months’ worth of lab data from a 600-bed tertiary-care medical center in Alabama, the system identified 41 suspected outbreaks; subsequent inspection of patients’ charts revealed that 97 percent actually had hospital-acquired infections. During that same period, the medical center’s infection control staff had flagged only nine suspected outbreaks, just three of which turned out to be real.
MedMined currently uses DMSS to analyze lab data from five U.S. hospitals. The technology has already gained attention from, among others, the Centers for Disease Control and Prevention (CDC). “[The CDC] has always been keenly interested in accurate ways of detecting health care-associated infections,” says Lance R. Peterson, director of the CDC’s Prevention Epicenter at Northwestern Memorial Hospital and professor of pathology and medicine at Northwestern University. “In the future [the MedMined approach] has the potential to develop into a national surveillance method for detecting food-borne infectious disease outbreaks-and perhaps even more,” Peterson says.
Keep Reading
Most Popular

The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.

These materials were meant to revolutionize the solar industry. Why hasn’t it happened?
Perovskites are promising, but real-world conditions have held them back.

Why China is still obsessed with disinfecting everything
Most public health bodies dealing with covid have long since moved on from the idea of surface transmission. China’s didn’t—and that helps it control the narrative about the disease’s origins and danger.

A quick guide to the most important AI law you’ve never heard of
The European Union is planning new legislation aimed at curbing the worst harms associated with artificial intelligence.
Stay connected

Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.