Hospitals continue to grapple with clostridium difficile infections, caused by bacteria that are resistant to many common antibiotics and that kill about 30,000 Americans each year. However, machine learning can help predict patient risk in developing C. difficile much earlier than current methods of diagnosis. Using electronic health records for nearly 257,000 patients, researchers from Massachusetts General Hospital, MIT and Michigan Medicine have built hospital-tailored machine learning models that they contend are an improvement over a "one-size-fits-all" approach that ignores important factors specific to medical facilities. "When data are simply pooled into a one-size-fits-all model, institutional differences in patient populations, hospital layouts, testing and treatment protocols, or even in the way staff interact with the EHR can lead to differences in the underlying data distributions and ultimately to poor performance of such a model," says Jenna Wiens, assistant professor of computer science and engineering at U-M. "To mitigate these issues, we take a hospital-specific approach, training a model tailored to each institution." De-identified EHR data from 191,014 adult admissions to Michigan Medicine and 65,718 adult admissions to MGH were analyzed using separate machine learning algorithms tailored to each healthcare institution with different types of variables. "These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies," conclude the authors in an article appearing in the April issue of the journal Infection Control and Hospital Epidemiology.

Samsung Electronics Co. is joining the race to create the smartest digital assistant by acquiring Viv, a Silicon Valley start-up launched by the same entrepreneurs who sold Siri to Apple. The deal announced Wednesday provides Samsung with technology to compete against Google Inc., Amazon.com Inc., Microsoft Corp. and Apple Inc. in the increasingly important field of programming computers to learn and respond as if they were human. The specialty, also known as artificial intelligence, has hatched a flock of voice-activated digital concierges -- such as Siri, Amazon's Alexa, Microsoft's Cortana and Google's Assistant -- that work in personal computers, smartphones and Internet-connected speakers. Samsung plans to implant Viv into phones, televisions and a wide range of other devices. The South Korean company did not disclose how much it paid for the start-up.

The Burbank Police Department has suspended officer deployments based on "predictive policing" technology hailed by top brass as the future of crime-fighting after complaints from police officers. The shift comes as police departments across the country are increasingly using computer technology to help predict crime trends and deploy officers accordingly. Some law enforcement agencies have said the system has helped crack down on crime. But in Burbank, critics said the software's algorithm couldn't beat a veteran officer's intuition and knowledge of his or her patrol area. They also said the algorithm sometimes zeroed in on obvious areas where officers already know there's crime or silly locations, such as the police station, where people often show up to report crimes.