To Fight Fatal Infections, Hospitals May Turn to Algorithms (scientificamerican.com)

The technology used by Facebook, Google and Amazon to turn spoken language into text, recognize faces and target advertising could help doctors combat one of the deadliest killers in American hospitals. From a report: Clostridium difficile, a deadly bacterium spread by physical contact with objects or infected people, thrives in hospitals, causing 453,000 cases a year and 29,000 deaths in the United States, according to a 2015 study in the New England Journal of Medicine. Traditional methods such as monitoring hygiene and warning signs often fail to stop the disease. But what if it were possible to systematically target those most vulnerable to C-diff? Erica Shenoy, an infectious-disease specialist at Massachusetts General Hospital, and Jenna Wiens, a computer scientist and assistant professor of engineering at the University of Michigan, did just that when they created an algorithm to predict a patient's risk of developing a C-diff infection, or CDI. Using patients' vital signs and other health records, this method -- still in an experimental phase -- is something both researchers want to see integrated into hospital routines. The CDI algorithm -- based on a form of artificial intelligence called machine learning -- is at the leading edge of a technological wave starting to hit the U.S. health care industry. After years of experimentation, machine learning's predictive powers are well-established, and it is poised to move from labs to broad real-world applications, said Zeeshan Syed, who directs Stanford University's Clinical Inference and Algorithms Program.

Comments

Dupe much?

[Bearhouse]

I know I'm getting old and forgetful, but did we not already have this story?

Although for sure it's news for nerds, a less exotic solution is proper hygene - studies have shown that simply cleaning the place regularly with bleach reduces infection considerably.

Of course, this is difficult in emergency wards, but in operating blocks (which are supposed to be sterile), bugs are regularly found...

Re:Dupe much?

[craigminah]

Exactly. AI is the cool thing but washing of hands and sterilization of surfaces is effective.

Re: Dupe much?

[Anonymous Coward]

I think we did, but Slashdot has been "blanking" on loading certain stories over the last couple of days. Probably some new anti ad blocking mobile-based technique messing up.

A better alternative exists.

[Gravis Zero]

Right now, we have the problem of antibiotic resistance. Fun fact, one of the avenues being looked at before the discovery of antibiotics was the use of bacteriophages. Bacteriophage (aka phage) are actually just complex viruses that I think are better described as being molecular memetic robots. These tiny memebots bump into bacterium, inject their genome into the bacterium's cytoplasm which starts the replication of more tiny memebots before finally exploding out.

Finding the right bacteriophage is the difficult part but this can easily be assisted by robotic trial and error. However, the bigger issue is actually regulatory because these are actually highly complex molecular machines that we don't really understand. I think when we get past the regulatory issue (eventually it won't be an option) that enough focus on understanding bacteriophages will exist and we'll reverse engineer them. At which point we'll be able to design our own molecular robots and we'll lay waste to all the microbes that irk us.