When Sharing Research Data Is Rare, This Novel Approach On Mapping Brain Tumors Brings Together 30 Centers
Researchers at the University of Pennsylvania and Intel are contributing the software to a massive project that will ultimately involve more than 15,000 patients in a first-time attempt to build a consensus model and help inform clinical decisions, Stat reports. Public health news is on schizophrenia, Parkinson's disease and fatty liver disease, as well.
Stat:
New Effort To Map Brain Tumors Puts An AI Approach To The Test
It’s a contradiction that’s long slowed the forward march of artificial intelligence in medicine: Machine learning models need to be trained on lots of diverse data from hospitals around the world — but those hospitals are often reluctant to ship out their data due to privacy concerns, legal issues, and a cautious culture. One promising way to get around that problem is a technique known as federated learning, which allows models to be trained without having to share data to a central server or in the cloud. Now, the approach is being put to the test in an ambitious project to build an AI system from thousands of brain tumor scans from several dozen hospitals and research institutions around the globe. (Robbins, 5/11)
Stat:
Research Sheds Light On Sex Imbalances In Schizophrenia, Lupus
There’s a clear sex bias in many diseases. Lupus, for instance, affects women nine times more often than it does men. Schizophrenia tends to be far more severe in males. But what’s behind the imbalance? A new paper in Nature helps unravel why some conditions might manifest themselves more commonly, or intensely, in one sex over another. And it suggests that new therapies might be developed with these sex-based molecular disparities in mind. (Keshavan, 5/11)
Stat:
Doctors Treat Parkinson’s With A Novel Brain Cell Transplant
A month before the scheduled surgery, the four researchers were ready to chaperone the brain cells on their 190-mile journey. They never anticipated they were in for “The Amazing Race”-meets-“ER.” It was after midnight on a late summer night in 2017, and they had less than eight hours to get the cells by ambulance, private plane, and another ambulance from Dana-Farber Cancer Institute in Boston to Weill Cornell Medical Center in Manhattan. If it took longer, the cells would almost certainly be DOA, and so might the researchers’ plan to carry out an experimental transplant surgery unprecedented in the annals of medicine: replacing the dysfunctional brain cells of a Parkinson’s disease patient with the progeny of an extraordinary type of stem cell. (Begley, 5/12)
Stat:
French Drug Maker Genfit Says NASH Drug Fails Late-Stage Clinical Trial
French drug maker Genfit said Monday that its lead drug, elafibranor, failed to improve outcomes for patients with the fatty liver disease NASH, according to an interim analysis of a late-stage clinical trial. “These results are highly disappointing,” Genfit CEO Pascal Prigent said in a statement. The company plans to review additional data and consult with regulators before determining if development of elafibranor should continue. (Feuerstein, 5/11)
