Health care

In an article for The Wall Street Journal, Benjamin Powers highlights Affectiva and Koko, two MIT startups developing AI systems that respond to human emotions.

Boston Globe reporter Jessie Scanlon spotlights Prof. Regina Barzilay’s work developing machine learning systems that can identify patients at risk of developing breast cancer. Barzilay is creating “software that aims to teach a computer to analyze mammogram images more effectively than the human eye can and to catch signs of cancer in its earliest phases.”

Smithsonian reporter Randy Rieland writes that MIT researchers have developed a machine learning model that can detect speech and language patterns associated with depression. The researchers note that the system is intended to assist, not replace clinicians. “We’re hopeful we can provide a complementary form of analysis,” explains Senior Research Scientist James Glass.

Popular Science reporter Rob Verger highlights how an MIT spinout and MIT researchers are developing tools to detect depression. “The big vision is that you have a system that can digest organic, natural conversations, and interactions, and be able to make some conclusion about a person’s well-being,” says grad student Tuka Alhanai.

Forbes contributor Howard Gleckman highlights a study by Prof. Amy Finkelstein that shows only five percent of Medicare spending goes toward end-of-life costs. Gleckman writes that the study supports the argument that “using spending in the last year of life as a proxy for futile care is deeply flawed—because we are very bad at predicting who is going to die and who is not.”

Prof. Amy Finkelstein speaks with Lisa Mullins of WBUR’s All Things Considered about winning a MacArthur grant for her work examining health economics. Finkelstein explains that the goal of her work is to “reduce the amount of rhetoric in health care policy discussion and increase the amount of evidence.”

Boston Globe reporter Michael Levenson writes that Profs. Amy Finkelstein and Lisa Parks have been selected as recipients of the MacArthur “genius grant.” Finkelstein notes that the award will allow her to take more risks with her research, while Parks plans to use the award to “strengthen MIT’s Global Media Technologies and Cultures Lab and deepen the university’s ties to Africa, where she does research,” Levenson explains.

Profs. Amy Finkelstein and Lisa Parks have been named MacArthur Fellows, reports Joe Barrett for The Wall Street Journal. Barett explains that Finkelstein “conducts studies in the economics of health care; among her findings is that Medicaid expansion increases self-reported health and financial security, but also increases use of the emergency room and has no significant impact on many measures of physical health.”

As part of the InCube entrepreneurial challenge, a team of MIT students is living in a glass cube for five days as they work on developing a better ambulance, reports Andy Rosen for The Boston Globe. Gene Keselman, executive director of the MIT Innovation Initiative, explains that the glass cube offers passersby a glimpse at what “the entrepreneurial journey looks like.”

A study co-authored by Prof. Amy Finkelstein finds that bundling Medicare payments for procedures such as hip and knee replacements reduces the use of post-acute care by about 3 percent, reports Austin Frakt for The New York Times. Finkelstein explains that she examined the use of post-acute care as “it is an area where there is concern about overuse.”

In an article for Quartz about how robots are being used to help care for the elderly, Corinne Purtill highlights Prof. Sherry Turkle’s work on the impact of using machines to satisfy the human need for emotional connection. Putrill cites Turkle’s argument that using machines creates a new relationship where we “feel connected although we are alone.”

MIT researchers have developed a model that can help detect depression by analyzing an individual’s speech patterns, reports Kaveh Waddell for Axios. Waddell explains that the researchers, “trained an AI system using 142 recorded conversations to assess whether a person is depressed and, if so, how severely.”

MIT researchers have developed a new system that can detect depression by examining a patient’s speech and writing, reports John Biggs for TechCrunch. Biggs writes that the system could “help real therapists find and isolate issues automatically versus the long process of analysis. It’s a fascinating step forward in mental health.”

MIT researchers have found that reducing payments to long-term care hospitals could save the U.S. health care system around $5 billion a year, reports Margot Sanger-Katz for The New York Times. “The history of long-term care hospitals suggests the industry will always innovate ahead of you, and you may actually have to roll up your sleeves and find these pockets of waste,” explains Prof. Amy Finkelstein.

MIT researchers have developed a machine learning system that could reduce the number of chemotherapy and radiotherapy treatments that glioblastoma patients receive, reports the Xinhua News Agency. The system “finds an optimal treatment plan, with the lowest possible potency and frequency of doses that should still reduce tumor sizes,” Xinhua explains.