Issue link: https://beckershealthcare.uberflip.com/i/952761
29 DATA INFORMATICS AND ANALYTICS Harvard Spinout Creates AI Coach to Field Patient Questions Between Medical Visits By Jessica Kim Cohen M emora Health, a startup based in the Harvard Innovation Labs at Cambridge, Mass.-based Harvard University, developed an artificial intelligence-powered virtual coach to answer patients' questions, AmericanInno reported. Here are four things to know about the startup. 1. The virtual coach, named Felix, supports patients who develop follow-up questions about their condi- tion or treatment after returning home from a hospital visit. Memora Health co-founder and CEO Nisarg Patel told AmericanInno Felix is "built to talk [to a patient via text message] the way a nurse would talk with a patient over the phone." 2. Mr. Patel, a fourth-year doctor of dental medicine candidate at the Harvard Medical School and the Har- vard School of Dental Medicine, both based in Boston, co-founded Memora Health with two recent graduates from Atlanta-based Georgia Institute of Technology. Mr. Patel developed the idea for the startup after no- ticing many patients who regularly visited the hospital didn't have the support system to manage a chronic condition at home. "They were even given the term 'frequent flyers,'" he said. 3. Memora Health sells the virtual coach to private practices and hospital departments, which in turn offer the service to patients, primarily by adding the Felix phone number to discharge papers so patients are able to text the line directly. The virtual coach also integrates with the organization's EHR system to ensure Felix has access to relevant patient information. 4. Memora Health is working on paid pilot programs with Boston-based Brigham and Women's Hospital and Atlanta-based Grady Memorial Hospital. n 2 Ways AI is Helping Fight the Flu This Season and Those to Come By Julie Spitzer R esearchers are using artificial intelli- gence and machine learning to find better ways to protect people from this year's particularly aggressive flu season, according to NBC News. As of Feb. 17, 21,279 Americans experienced flu-related hospitalizations and 97 children had died, in part because this year's flu vac- cine is less than 40 percent effective. How could AI better prepare the U.S. for flu seasons to come? Here are two ways. 1. Forecasting. Flu forecasts help researchers track outbreaks, tackle vaccine shortages and update the public, Roni Rosenfeld, PhD, a machine learning expert at Pitts- burgh-based Carnegie Mellon University, told NBC News. Dr. Rosenfeld and his team are applying machine learning techniques to si through historical data on how the flu spread in past years. "We make an underlying assumption that this year is going to be, in some senses, sim- ilar to a past year," Dr. Rosenfeld told NBC News. But he thinks the data could also offer insights into the flu's impact on individual counties or cities. "When we track and forecast a flu in regions like the Southeast or New England, there's not a single epidemic going on," he said. "At the local level, the flu hits different cities and counties in different ways and at different times. ey could really use a much more specific and customized assessment of what's going on." 2. Improving vaccines. Each year, the CDC characterizes about 2,000 strains of the influenza virus in order to identify which specific viruses are likely to dominate. is helps researchers develop targeted vaccines. However, because flu viruses mutate rapidly, the strain of the flu could change and leave the vaccine less effective. Richard Webby, PhD, a virologist at St. Jude Children's Research Hospital in Memphis, Tenn., worked with a team of researchers to study how machine learning could examine the specific flu mutations that led to the 2009 swine flu outbreak. He said this study could be applied to the ordinary seasonal flu virus, too. According to NBC News, scientists are using Dr. Webby's machine learning study to help pinpoint viruses' antigenic properties, or their molecular structures and how they affect the body's immune system. "e most important piece of information that we have is antigenic information on these viruses that are circulating," Dr. Webby told NBC News. Scientists are attempting to "train machine learning algorithms to predict what impact various mutations might have on the antigenicity of the virus," meaning they are using the tech to find the right vaccine. n