Health sciences and technology

MIT researchers have found that “when an AI tool for radiologists produced a wrong answer, doctors were more likely to come to the wrong conclusion in their diagnoses,” report Daniel Payne, Carmen Paun, Ruth Reader and Erin Schumaker for Politico. “The study explored the findings of 140 radiologists using AI to make diagnoses based on chest X-rays,” they write. “How AI affected care wasn’t dependent on the doctors’ levels of experience, specialty or performance. And lower-performing radiologists didn’t benefit more from AI assistance than their peers.”

Bloomer Tech, a health tech startup founded by Alicia Chong Rodriguez SM ‘17, SM ’18, is working to “address the gender gap in health care, which has led to less clinical trial representation and fewer resources to diagnose and treat women with various diseases,” reports Steph Solis for Axios. The startup is prepared “to launch a clinical trial for bras that could help detect heart irregularities and other conditions that can lead to heart disease,” writes Solis.

Writing for Fast Company, Senior Lecturer Guadalupe Hayes-Mota '08, SM '16, MBA '16 shares methods to address the influence of AI in healthcare. “Despite these advances [of AI in healthcare], the full spectrum of AI’s potential remains largely untapped,” explains Hayes-Mota. “Systemic hurdles such as data privacy concerns, the absence of standardized data protocols, regulatory complexities, and ethical dilemmas are compounded by an inherent resistance to change within the healthcare profession. These barriers underscore the urgent need for transformative action from all stakeholders to fully harness AI’s capabilities.”

Senior Lecturer Guadalupe Hayes-Mota writes for Forbes about the ways AI is reshaping drug development. “In the next three years, we can anticipate a more streamlined, efficient and cost-effective drug development process, ultimately leading to faster access to life-saving drugs for patients worldwide,” Hayes-Mota writes. “This is not just an evolution; it is a revolution in healthcare powered by the intelligence of machines.”

Elemind Technologies, a neuro-tech startup founded by scientists from MIT and elsewhere, is developing, “an approach that redirects brain wave through non-invasive stimulation – using sound, light, touch and electric pulses –  to potentially address a range of neurological conditions in a more targeted ways than drugs,” reports Robert Weisman for The Boston Globe. 

Researchers from MIT and elsewhere have developed an AI model that is capable of identifying 3 ½ times more people who are at high-risk for developing pancreatic cancer than current standards, reports Felice J. Freyer for The Boston Globe. “This work has the potential to enlarge the group of pancreatic cancer patients who can benefit from screening from 10 percent to 35 percent,” explains Freyer. “The group hopes its model will eventually help detect risk of other hard-to-find cancers, like ovarian.”

Prof. Ron Weiss co-founded Strand Therapeutics, a biotech company developing mRNA therapies, reports Emily Mullin for Wired. “The notion is that genetic circuits can really have significant impact on safety and efficacy,” says Weiss. “This begins to really open up the door for creating therapies whose sophistication can match the underlying complexity of biology.”

Prof. Jonathan Weissman and his colleagues have developed a new tool for monitoring changes in human blood cells, which could one day help researchers predict disease risk, reports Megan Molteni for STAT. “The technology paves the way for a day in the not too distant future where it is conceivable that from a simple blood draw, a doctor could get a sense of what’s going on in that patient’s bone marrow,” writes Molteni, “picking up perturbations there that could help predict a diverse range of diseases.”

Carmen Martin-Alonso PhD '23 speaks with Zakiya Whatley on the Science podcast to discuss her recent research focused on developing new methods to improve liquid biopsies for cancer. “I think this is super, super promising for the field of oncology where having more sensitive ctDNA-based liquid biopsies could really transform patient management,” says Alonso. “And in the same way as radio label converse agents have transformed imaging, we think that priming agents could transform the utility of liquid biopsies.”

Alicia Chong Rodriguez SM ’17, SM ’18 founded Bloomer Tech, a health tech startup that aims to improve health care diagnostics for women using medical-grade data to develop new therapies and care models, reports Carol Eisenberg for The Washington Post. Rodriguez and her colleagues "developed, patented and tested flexible washable circuits to turn articles of clothing into devices that can relay reams of information to the wearer’s smartphone,” writes Eisenberg.

Popular Mechanics reporter Jill Waldbieser spotlights Prof. Hugh Herr and his work developing prosthetic limbs that integrate with their human hosts using a surgical technique that preserves the sensation in artificial limbs. “In the future, on the order of five years or so, we’ll be so good at this, we’ll completely restore the signals from the prosthetic to the brain and from the brain to the prosthetic, like the limb was never amputated,” says Herr.

Researchers at MIT and elsewhere developed an artificial intelligence predictive model that can be used to detect which strains of Covid-19 could become dominant and lead to a new wave of illness, reports Ruth Reader, Carmen Paun, Daniel Payne and Eric Schumaker for Politico. The model, “found three strong predictors of a dominant variant: the number of infections a strain causes in its first week relative to the number of times it appears in sequencing, the number of mutations in the spike protein, and the number of weeks since the current dominant variant began circulating,” they note.

Prof. Manolis Kellis speaks with Brian Bergstein of The Boston Globe’s “Say More” podcast about the potential influence of artificial intelligence on biological advances and medicine. “I would say there is no way to answer biological questions without computational science nowadays,” says Kellis. “The genome and all of the technologies that it enabled transformed biology into an information-based discipline.”

Postdoctoral associate Wen Shuhao and postdoctoral fellows Ma Jian and Lai Lipeng co-founded Xtalpi, a biotech startup that uses “artificial intelligence to find chemical compounds that could be developed into new drugs,” reports Zinnia Lee for Forbes. “By combining AI, quantum physics, cloud computing and robotic automation, Xtalpi said it helps increase the efficiency and success rate of identifying novel drug compounds,” writes Lee. “The company has recently expanded into discovering new chemical compounds for agricultural technology, cosmetics and other applications.”

Ashley Smart, associate director of the Knight Science Journalism Program, writes for Undark about the impact of commercialized genetic tests on research involving new genetic links. “Even among some researchers who are optimistic about using polygenic scores to screen for physical health conditions, there is one emerging application of polygenic scores that makes them uneasy: the prediction of risks for depression and other psychiatric conditions,” writes Smart.