Comparing four methods for predicting septic shock in children hospitalized with sepsis, Johns Hopkins researchers have found a newer machine-learning approach superior to an older one as well as to two conventional methods.
The top performer, the open-source XGBoost (for eXtreme Gradient Boosting), supplied accurate early predictions that, in clinical practice, would have given critical-care teams nearly nine hours to intervene preventively.
The researchers used data from more than 6,100 past patients of Johns Hopkins’s pediatric ICU to train and test the model retrospectively… Continue reading.
Complementing the acclaimed talent already assembled on its scientific leadership team, bioprinting startup BIOLIFE4D announced the addition of Raimond Winslow, Ph.D. whose vast expertise will help the company deliver on its mission to 3D bioprint a viable human heart suitable for transplant.
Winslow’s new role at BIOLIFE4D comes in addition to the leadership positions he holds at Johns Hopkins University where he is Founding Director of the Institute for Computational Medicine, and the Raj and Neera Singh Professor of Biomedical Engineering.
He earned a B.S. in electrical engineering from Worcester Polytechnic Institute and a Ph.D. in biomedical engineering from Johns Hopkins. He concluded his training at the Institute for Biomedical Computing and Department of Neurology within Washington University in St. Louis. He joined the faculty of Johns Hopkins in 1991 as an assistant professor, became an associate professor in 1994 and a full professor in 2000… Continue reading.