Health

Prof. Linda Griffith speaks with Science Friday host Flora Lichtman about her work studying endometriosis. “I did a lot of things in the regenerative medicine space. But I had an epiphany that there’s so many chronic and inflammatory disease that we don’t know how to treat so I started building models of human organs and tissues in the lab using what we called microfluidic chips,” Griffith explains. “When I got asked about endometriosis, it was actually a perfect application for this kind of approach because we really need to study the lesions very carefully in the lab in ways that is very hard to study in patients.” 

MIT researchers have developed a new AI tool, dubbed “DrugReflector,” aimed at speeding up the drug discovery process, reports William A. Haseltine for Forbes. The researchers used DrugReflector to test tested almost 9,600 drugs in different human cell types.“This system was 17 times more accurate than older computational methods and improved as it used honest lab feedback,” writes Haseltine. 

Writing for STAT, Senior Lecturer Guadalupe Hayes-Mota 08, SM '16, MBA '16 examines how the closure of local pharmacies across the country poses a significant public health risk, particularly for Americans in rural communities who, like Hayes-Mota’s father, “depend on their local pharmacy not only for medicine, but for survival.” Hayes-Mota emphasizes that “addressing this crisis requires three urgent steps: supporting underserved areas with targeted incentives and mobile or telepharmacy services, investing in the workforce through safe staffing and career pathways, and granting pharmacists provider status with expanded scope of practice.”

Prof. Alex Shalek and his colleagues developed a deep-learning model called DrugReflector aimed at speeding up the process of drug discovery, reports Heidi Ledford for Nature. “They used DrugReflector to find chemicals that can affect the generation of platelets and red blood cells — a characteristic that could be useful in treating some blood conditions,” explains Ledford. The researchers found that “DrugReflector was up to 17 times more effective at finding relevant compounds than standard, brute-force drug screening that depends on randomly selecting compounds from a chemical library.”

Prof. Linda Griffith speaks with Nature reporter Cassandra Willyard about her work developing lab-made organoids to help study the root causes of endometriosis. Griffith has been working to develop “a model of abnormal endometrial tissue that the researchers can use to test therapies for the condition,” writes Willyard. “Because blood vessels are crucial to maintaining this tissue, Griffith knew she wanted to include them. To do this, she and her colleagues placed the organoid on a microfluidic chip surrounded by cells that form blood vessels.” 

Financial Times reporter Melissa Heikkilä spotlights how MIT researchers have uncovered evidence that increased use of AI tools by medical professionals risks “leading to worse health outcomes for women and ethnic minorities.” One study found that numerous AI models “recommended a much lower level of care for female patients,” writes Heikkilä. “A separate study by the MIT team showed that OpenAI’s GPT-4 and other models also displayed answers that had less compassion towards Black and Asian people seeking support for mental health problems.” 

Prof. Rosalind Picard speaks with Bloomberg reporters Carol Massar and Tim Stenovec about technological advancements in wearable technology and how advances in the field could positively impact women’s healthcare. “The opportunities are huge for health with wearables and especially for women’s health,” says Picard. “There are so many conditions that are different for women than for men, and they’re not only vastly understudied but the kind of data is very under sampled.” 

Prof. Regina Barzilay speaks with Newsweek reporter Katherine Fung about the how hospitals around the world around increasingly adopting new technologies. “Countries with a centralized healthcare system, or centralized healthcare records, can do a much better job because they have so much data and so much ability to monitor what AI tools are doing," says Barzilay. 

Prof. Jonathan Gruber speaks with Newsweek reporter Jasmine Laws about the anticipated price increase in employer health benefit plans for the coming year. Due to higher costs, “some may stop taking up employer coverage altogether while others may move to less expensive plans,” explains Gruber. 

Beth Pollack, a research scientist in the Department of Biological Engineering, speaks with The Guardian’s Science Weekly hosts Madeleine Finaly and Ian Sample about her research on chronic fatigue syndrome (MF CFS) and other chronic illnesses. “There are a number of interesting treatments addressing the different aspects of immune disfunction with different immunomodulators,” says Pollack. 

Prof. Regina Barzilay speaks with Newsweek reporter Alexis Kayser about how new AI tools are implemented in health care settings. “You need to know how to safely bring it into the [health care] system," says Barzilay. "There is a new science, which is the science of implementation."

In an effort to develop non-invasive ways to treat depression, PTSD, brain tumors and other conditions, researchers from MIT Lincoln Lab are looking to better understand human consciousness, reports Steph Solis for Axios. “There's the goal to analyze how it could help understand or treat PTSD and mood disorders in veterans,” says Solis of the inspiration for this research, “and then there's the existential question that stumps neuroscientists — how does our human experience arise from brain activity?”

Interesting Engineering reporter Saoirse Kerrigan spotlights a number of MIT research projects from the past decade. MIT has “long been a hub of innovation and ingenuity across multiple industries and disciplines,” writes Kerrigan. “Every year, the school’s best and brightest debut projects that push the boundaries of science and technology. From vehicles and furniture to exciting new breakthroughs in electricity generation, the school’s projects have tackled an impressive variety of subjects.” 

In a new paper, Prof. Giovanni Traverso and his colleagues highlight the results of a clinical trial that showed “a pill taken just once a week, gradually releasing medicine from within the stomach, can greatly simplify the drug schedule faced by schizophrenia patients,” writes Dennis Thompson for HealthDay News. “These final-stage clinical trial results are the product of more than 10 years of research by Traverso’s lab.” 

MIT researchers have developed Boltz-2, an AI algorithm “that unites protein folding and prediction of small-molecule binding affinity in one package,” reports Laura Howes for Chemical & Engineering News. “The researchers say their new AI model approaches the level of accuracy achieved by traditional computational chemistry—such as methods involving free-energy perturbation calculations—but much more quickly and cheaply,” explains Howes.