PHDA Publications

Interested in learning more about some of the innovative methods that PHDA teams have developed and the results they have achieved? Take a look at a few new recent publications below to catch up on the latest from three teams developing data-driven solutions for healthcare.

Jonathan Elmer, Bobby L. Jones, Daniel S. Nagin. Comparison of parametric and nonparametric methods for outcome prediction using longitudinal data after cardiac arrest, Resuscitation, 28 Jan 2020.  

Drs. Daniel Nagin and Jonathan Elmer lead the PHDA project “Real-Time Tool to Predict Clinical Outcomes After Cardiac Arrest.” Their recent publication in the journal Resuscitation shows that group-based trajectory modeling achieved high sensitivity for predicting outcomes of patients who were comatose following cardiac arrest while maintaining a low rate of false positives. Learn more about Drs. Nagin and Elmer and their project here.

Alexander Ruesch, Samantha Schmitt, Jason Yang, Matthew A Smith, Jana M Kainerstorfer. Fluctuations in intracranial pressure can be estimated non-invasively using near-infrared spectroscopy in non-human primates, Journal of Cerebral Blood Flow and Metabolism, 27 Nov 2019.

 Dr. Jana Kainerstorfer, PhD, leads the PHDA project “Non-Invasive Intracranial Pressure Monitoring,” in which her team is harnessing an optical technique called near-infrared spectroscopy (NIRS) to measure factors related to blood flow in the brain that are altered in diseases such as diabetes, Parkinson’s disease, and after traumatic brain injury and stroke. Dr. Kainerstorfer’s team describes validation of their technique in non-human primates in their recent publication. Learn more here.

Dooman Arefan, Aly A. Mohamed, Wendie A. Berg, Margarita L. Zuley, Jules H. Sumkin, Shandong Wu. Deep learning modeling using normal mammograms for predicting breast cancer risk, Medical Physics, 17 Oct. 2019.

Dr. Shandong Wu, who leads the PHDA project “PI (PathImage) Predictor,” and his team recently described new findings in Medical Physics. The team evaluated the performance of two deep learning modeling approaches on their ability to predict short-term breast cancer risk using information from normal mammogram images. Learn more about Dr. Wu and his work to develop models to guide breast cancer treatment here.