Goto

Collaborating Authors

Results


COVID-19 smartphone app can tell if you're an asymptomatic carrier - by the way you cough - Study Finds

#artificialintelligence

As millions of people worldwide battle the symptoms of COVID-19, a group of "silent patients" may not even know they're sick and spreading the virus. Asymptomatic people, by definition, have no physical symptoms of the illnesses they carry. Researchers at the Massachusetts Institute of Technology (MIT) however, say they may be showing symptoms after all -- in the sound of their cough. Their study has created an artificial intelligence program that can identify if someone has coronavirus by the way their coughing sounds. Researchers programmed their AI model with thousands of different recorded coughs from both healthy and sick volunteers.


Investigators Use AI to Develop Risk Score for COVID-19 Patients

#artificialintelligence

Researchers at Massachusetts General Hospital are using artificial intelligence to get a better handle on COVID-19 patients. The new AI-based score considers multiple factors to predict the prognosis of individual patients with COVID-19 seen at urgent care clinics or emergency departments. The tool can be used to rapidly and automatically determine which patients are most likely to develop complications and need to be hospitalized. The impetus for the study began early during the U.S. epidemic when Massachusetts experienced frequent urgent care visits and hospital admissions. While working as an infectious diseases physician and as part of the MGH Biothreats team, Gregory Robbins, MD, recognized the need for a more sophisticated method to identify outpatients at greatest risk for experiencing negative outcomes.


UMD Center for Machine Learning Announces 2020 Class of Rising Stars

#artificialintelligence

The University of Maryland Center for Machine Learning will host four female researchers this fall as part of a program that encourages and supports underrepresented doctoral candidates whose scientific work is focused on machine learning. Diana Cai, Irene Chen, Mahsa Ghasemi and Nan Rosemary Ke (pictured clockwise from top left) were recently selected as this year's Rising Stars in Machine Learning based on their novel research, academic accomplishments and exceptional work experience. The Rising Stars program, launched by the center last year, is focused on supporting upper-level graduate students from disadvantaged or underrepresented groups as they pursue new scientific discoveries and academic opportunities in machine learning. This year's cohort--who hail from Princeton University, the Massachusetts Institute of Technology, the University of Texas at Austin and the University of Montreal--were chosen from a competitive pool of 17 applicants. "After extensive review, we chose these four candidates based on their record of excellence in research and scholarship," said Soheil Feizi, assistant professor of computer science and a core faculty member in the Center for Machine Learning.


NVIDIA AI Model Accurately Predicts Oxygen Needs for COVID-19 Patients

#artificialintelligence

Researchers at NVIDIA and Massachusetts General Brigham Hospital have developed an artificial intelligence (AI) model that determines whether a person showing up in the emergency room with COVID-19 symptoms will need supplemental oxygen hours or even days after an initial exam. The original AI model, named CORISK, was developed by scientist Dr. Quanzheng Li at Mass General Brigham. It combines medical imaging and health records to help clinicians more effectively manage hospitalizations at a time when many countries may start seeing the second wave of COVID-19 patients. To develop an AI model that doctors trust and that generalizes to as many hospitals as possible, NVIDIA and Mass General Brigham embarked on an initiative called EXAM (EMR CXR AI Model) the largest, most diverse federated learning initiative with 20 hospitals from around the world. In just two weeks, the global collaboration achieved a model with .94


Face-mask recognition has arrived--for better or worse

#artificialintelligence

Critics of mask recognition also think that this new technology could be prone to some of the same pitfalls as facial recognition. Many of the training datasets used for facial recognition are dominated by light-skinned individuals. In 2019 Joy Buolamwini, a researcher at the Massachusetts Institute of Technology's Media Lab, and the AI Now Institute's Deborah Raji investigated the accuracy of commercially available datasets used by major tech companies. When they checked the performance of recognition systems using an algorithm trained with the standard datasets, and then using a new set of faces with much more racial and ethnic balance, the researchers found that the algorithm was less than 70 percent accurate in identifying new faces.


Massachusetts suspends Boston-based coronavirus testing lab Orig3n after nearly 400 false positives

Boston Herald

The state has suspended Boston-based COVID-19 testing lab Orig3n Laboratory after it produced nearly 400 false positive results. Public health officials became aware in early August of an "unusually high positivity rate" among the lab's test results and requested that Orig3n stop testing for the virus as of Aug. 8. Specimens were sent to an independent lab to be retested as part of a state Department of Public Health investigation, and the results showed at least 383 false positives. On Aug. 27, the state Department of Public Health notified Orig3n of "three significant certification deficiencies that put patients at immediate risk of harm," according to a DPH spokeswoman. They included the failure of the lab's director to provide overall management, issues with the extraction phase of testing, and a failure to meet analytic requirements such as documenting the daily sanitizing of equipment used for coronavirus testing. A statement of deficiency was issued on Sept. 4. The lab must now respond with a written plan of correction by Sept. 14, "and if action is not taken it can face sanctions," DPH said.


Massachusetts families struggle with remote and hybrid learning decisions amid COVID fears

Boston Herald

Students and parents across the state said they struggled with remote learning, but are fearful to return to school buildings amid the coronavirus pandemic, placing the stress of uncertainty upon families as fall approaches. "I think it is cruel and mean to think that students should be in a room at their seat without any physical touch for hours," said Jay'dha Rackard, 12, who attends Helen Davis Leadership Academy. Her mother, Janina Rackard, said she decided to keep her daughter home for remote learning this school year, "I feel like our children are being treated like Petri dishes." School shutdowns and remote learning models from the spring took a toll on students and parents, families said during a Thursday virtual press conference hosted by the Massachusetts Education Justice Alliance. "Remote learning probably came at the worst possible time in my life," said Chelsea High School senior Victoria Stutto. She said her father died shortly after school was shut down.


Coronavirus US: Boston Dynamics' robot dog detects symptoms

Daily Mail - Science & tech

A hospital in Massachusetts has found another job for Spot, Boston Dynamics' dog-like robot: Doctor. The yellow-and-black quadruped has been proven able to take patients' vital signs from a distance of over six feet. That could allow healthcare workers to keep a safe distance from patients who may be infected with the coronavirus or other contagion. So far, Spot has only been tested on healthy patients at Harvard Medical School's Brigham and Women's Hospital - the next step would be to try it out in an emergency room setting. Researchers at MIT say they've developed cameras that allow Spot, Boston Dynamics' dog-like robot, to take vital signs from more than six feet away.


MIT's machine learning designed a COVID-19 vaccine that could cover a lot more people

#artificialintelligence

There are currently 25 vaccines to fight COVID-19 in clinical evaluation, another 139 vaccines in a pre-clinical stage, and many more being researched. But many of those vaccines, if they are at all successful, might not produce an immune response in portions of the population. That's because some people's bodies will react differently to the materials in the vaccine that are supposed to stimulate virus-fighting T cells. And so just figuring out how much coverage a vaccine has, meaning, how many people it will stimulate to mount an immune response, is a big part of the vaccine puzzle. With that challenge in mind, scientists at Massachusetts Institute of Technology on Monday unveiled a machine learning approach that can predict the probability that a particular vaccine design will reach a certain proportion of the population.


A.I. Is Not Going to Magically Deliver a Coronavirus Vaccine

#artificialintelligence

In late February, a paper appeared in the journal Cell with encouraging news regarding one of the world's most persistent public health problems. Researchers at Massachusetts Institute of Technology and Harvard University had used artificial intelligence to identify a chemical compound with powerful antibiotic properties against some of the world's most drug-resistant strains of bacteria -- a welcome discovery in a world where 700,000 people die every year from drug-resistant infections. It was the first time an antibacterial compound had been identified this way. The researchers named it halicin, in honor of the computer HAL in the film 2001: Space Odyssey. While the global need for new antibiotics to treat drug-resistant infections is as pressing as it was at the start of the year, the world's attention has been diverted by the novel coronavirus pandemic, and the hunt for a vaccine that can halt Covid's spread.