Institute for Medical Engineering and Science (IMES)

Writing for Fortune, Prof. Elazer R. Edelman and Mike Mussallem of Edwards Lifesciences write that the backlog of deferred medical treatments caused by the Covid-19 pandemic and resulting long-term health consequences could impact public health for years. Edelman and Mussallem emphasize that “it is incumbent upon us to identify timely real-world evidence to elucidate the effects of policy changes so they can be adaptive and agile enough to provide access to critical interventions and procedures.”

A review led Prof. Marzyeh Ghassemi has found that a major issue in health-related machine learning models “is the relative scarcity of publicly available data sets in medicine,” reports Emily Sohn for Nature.

Researchers at MIT have found indoor humidity levels can influence the transmission of Covid-19, reports Dennis Thompson for US News & World Report. “We found that even when considering countries with very strong versus very weak Covid-19 mitigation policies, or wildly different outdoor conditions, indoor — rather than outdoor — relative humidity maintains an underlying strong and robust link with Covid-19 outcomes,” explains Prof. Lydia Bourouiba.

MIT researchers have found that relative humidity “may be an important metric in influencing the transmission of Covid-19,” reports Sophie Mellor for Fortune, “Maintaining an indoor relative humidity between 40% and 60% – a Goldilocks climate, not too humid, not too dry – is associated with relatively lower rates of Covid-19 infections and deaths,” writes Mellor.

A study by Prof. Emery Brown suggests that the combination of Covid-19 and anesthesia could prompt the human brain into a state of quiet that can last weeks or months, similar to how turtles quiet their neurons to survive winter, reports Carl Zimmer for The New York Times. The findings “might point to new ways to save people from brain damage: by intentionally putting people into this state, rather than doing so by accident.”

Research from Synlogic, a biotech company founded by Profs James Collins and Timothy Lu, has found that it’s the company’s engineered bacteria could provide some benefit to patients with a rare genetic disease, reports Emily Mullin for Wired. “Similar to how you might program a computer, we can tinker with the DNA of bacteria and have them do things like produce a drug at the right time and the right place, or in this case, break down a toxic metabolite,” says Lu.

Principal research scientist Leo Anthony Celi speaks with Associated Press reporter Maddie Burakoff about how pulse oximeters can provide inaccurate readings in patients of color. Celi highlights how oxygen levels can also be measured by drawing blood out of an artery in the wrist, the “gold standard” for accuracy, but a method that is a a bit trickier and more painful. 

Temporal thermometers may be less accurate than oral thermometers in detecting fevers among hospitalized Black patients, reports Jacqueline Howard for CNN. This “really reflects the much bigger systematic problem that we have now in the way we design, we innovate, we develop health products – not just medical devices but also medications and interventions,” says Principal Research Scientist Leo Anthony Celi. “We really need to step up in terms of making sure that the research we perform is more inclusive so that we avoid these unintended consequences of the technology that we develop.”

Researchers from MIT and Harvard have developed a “3D-printed ‘lab-on-a-chip’ that could detect Covid-19 immunity levels and Covid infections from saliva within two hours,” reports Ben Leonard and Ruth Reader for Politico.

Researchers from MIT and other institutions have developed a postcard-sized test that can detect a Covid-19 infection and the presence of antibodies resulting from an infection, reports Maddie Bender for the Daily Beast.  “What excites me about this diagnostic device is that it combines a high level of accuracy with a flexible design that could make it a major tool in our arsenal for addressing future pandemics,” explains Prof. James Collins.

Principal Research Scientist Leo Anthony Celi oversaw a study which found that people of color were given significantly less supplemental oxygen than white people because of inaccuracies in pulse oximeter readings, reports Nancy Lapid for Reuters. “Nurses and doctors make the wrong decisions and end up giving less oxygen to people of color because they are fooled [by incorrect readings from pulse oximeters],” says Celi.

A study co-authored by MIT researchers finds that algorithms based on clinical medical notes can predict the self-identified race of a patient, reports Katie Palmer for STAT. “We’re not ready for AI — no sector really is ready for AI — until they’ve figured out that the computers are learning things that they’re not supposed to learn,” says Principal Research Scientist Leo Anthony Celi.

Researchers at MIT and Harvard Medical School have created an artificial intelligence program that can accurately identify a patient’s race based off medical images, reports Tony Ho Tran for The Daily Beast. “The reason we decided to release this paper is to draw attention to the importance of evaluating, auditing, and regulating medical AI,” explains Principal Research Scientist Leo Anthony Celi.

During the AI Cures Conference, Prof. Regina Barzilay spoke with Food and Drug Administration senior staff fellow Amir Khan about how the agency intends to regulate artificial intelligence in medicine, reports Casey Ross for STAT.  “’My thinking is that models should be regulated based on their functionality, and not necessarily on the input data they use,” said Barzilay. 

The Boston Globe highlights Robert Buderi’s new book, “Where Futures Converge: Kendall Square and the Making of a Global Innovation Hub.” Buderi features the Future Founders Initiative, an effort by Prof. Sangeeta Bhatia, President Emerita Susan Hockfield and Prof. Emerita Nancy Hopkins aimed at increasing female entrepreneurship.