Health sciences and technology

Researchers at MIT and Massachusetts General Hospital have developed “Sybil” – an artificial intelligence tool that can predict the risk of a patient developing lung cancer within six years, reports Mallika Marshall for CBS Boston. 

MIT researchers have developed a new AI tool called Sybil that could help predict whether a patient will get lung cancer up to six years in advance, reports Pranshu Verma for The Washington Post.  “Much of the technology involves analyzing large troves of medical scans, data sets or images, then feeding them into complex artificial intelligence software,” Verma explains. “From there, computers are trained to spot images of tumors or other abnormalities.”

Researchers from MIT and Harvard have developed “a new type of electrically conductive hydrogel ‘scaffold’ that could eventually be used to create a soft brain-computer interface (or BCI) that translates neural signals from the brain into machine-readable instructions,” reports Adam Bluestein for Fast Company.

Researchers from MIT and Mass General Hospital have developed “a deep learning model named ‘Sybil’ that can be used to predict lung cancer risk, using data from just a single CT scan,” writes Sai Balasubramanian for Forbes. “Sybil is able to predict a patient’s future lung cancer risk to a certain extent of accuracy, using the data from just one LDCT [low-dose computed tomography scan],” writes Balasubramanian.

Harry McNamara PhD ’19, David Heller ’18, and Shara Ticku co-founded C16 Biosciences, a biotechnology company that uses synthetic biology to address environmental concerns, reports John Cumbers for Forbes. The company “wants to replace conflict palm oil with a sustainable alternative made in yeast using precision fermentation,” writes Cumbers.

Rosina Samadani ’89, MS ’92 co-developed EyeBox, an algorithm-based non-invasive diagnostic test for concussions, reports Geri Stengel for Forbes. “Patients watch a video, and the device watches their eyes for 220 seconds with a very high-quality, high-frequency infrared camera that measures eye movements and provides a score based on those eye movements,” explains Stengel. “The score is correlated with the absence or presence of a concussion.”

Prof. Robert Langer and his colleagues write for Physics Today about how physics could help contribute to predicting tissue behaviors and accelerate the regeneration of human tissues and organs. “The physics of tissue engineering in general and of bioprinting in particular is a relatively new field that could provide numerous opportunities for tissue and organ fabrication and regeneration,” they write.

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.

Researchers from MIT and Boston Children’s Hospital are working on developing new technology that could help predict and identify diseases through audio recordings of a patient’s voice, reports Jim Morelli for Boston 25 News. “It’s almost like being Sherlock Holmes to voice, taking voice as a signal and trying to understand what’s going on behind it,” said Satrajit Ghosh, a principal research scientist at the McGovern Institute. “And can we backtrack from voice and say this is ‘Disorder A’ versus ‘Disorder B’?” 

CNBC reporter Catherine Clifford spotlights C16 Biosciences, a startup co-founded by MIT alumni that is developing a palm oil alternative called Palmless. “What we are building is a platform technology that can produce all different kinds of microbial oils,” explains David Heller ’18, co-founder and head of operations at C16 Biosciences. “It’s definitely possible that we’re able to make other kinds of vegetable oil replacements in the future.” 

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. 

Forbes reporter Marija Butkovic spotlights Alicia Chong Rodriguez MS ’18, Founder and CEO of Bloomer Tech, for her work in building a cardiovascular disease and stroke database that can generate non-invasive digital biomarkers. “We envision a world where the future of AI in healthcare performs the best it can in women,” says Chong Rodriguez. “We also have created a digital biomarker pipeline where our digital biomarkers can explain, influence, and even improve health outcomes for women.”

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 are working with the Staten Island Performing Provider System to develop an algorithm that can predict who in the system is at risk for an opioid overdose, reports Maddie Bender for the Daily Beast. “In preliminary testing, Conte’s team and MIT Sloan researchers found their model was highly accurate at predicting overdoses and fatal overdoses, even with delays in the data of up to 180 days,” writes Bender.