Penn Medicine AI assists global consortium's COVID-19 data model: 4 notes

A consortium of research scientists is using Penn Medicine AI software to power a COVID-19 data model that is pooling information from around the world and accelerating clinical discoveries.

Four details:

1. The consortium includes 96 hospitals from around the world and has collected data on more than 27,000 COVID-19 patients who had 187,000 laboratory tests.

2. The consortium, which includes faculty from the Perelman School of Medicine at the University of Pennsylvania, worked to create the model and shared analytics framework that will aggregate information from disparate EHRs.

3. Consortium members will have access to PennAI, a free self-service machine-learning tool that the health system's Institute for Biomedical Informatics developed. Each site can use PennAI software to generate machine-learning models to predict COVID-19 outcomes.

4. The standardized model for data input will allow members to more easily analyze large data sets and detect trends and patterns as the virus evolves. Penn Medicine did this on a smaller scale by standardizing information from its EHR using logical observation identifiers, names and codes and shared units of measurement to identify abnormal trends in blood-clotting, liver function and white blood cell counts among COVID-19 patients.

"Our ability to rapidly respond to a global pandemic was made possible by years of institutional investments in health information technology and biomedical informatics expertise and infrastructure," said Jason Moore, PhD, director of the Institute for Biomedical Informatics and professor of informatics, in a Penn Medicine news release. "We are seeing the value of electronic health records and artificial intelligence in real time."

More articles on health IT:
Defense Health Agency launches AI project for cancer detection
NYU Langone, Facebook set out to develop AI-powered 5-minute MRI scan
Healthcare provider and payer execs point to AI, robotics as next industry disruptors: report

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Content

Featured Webinars

Featured Whitepapers