Geisinger-AI vendor aim to reduce adverse events, avoid readmissions

Share:

Share on twitter
Share on linkedin
Share on facebook
Share on email
Health Data Management

Geisinger-AI vendor aim to reduce adverse events, avoid readmissions

Israel-based Medial EarlySign and Geisinger Health System have partnered to apply advanced artificial intelligence and machine learning algorithms to Medicare claims data to predict and improve patient outcomes.

 

An EarlySign-Geisinger proposal has been selected as one of 25 participants to advance to Stage 1 of a technology challenge from the Centers for Medicare and Medicaid Services to accelerate the development of AI and machine learning solutions for healthcare.

 

“Approximately 4.3 million hospital readmissions occur each year in the U.S., costing more than $60 billion, with preventable adverse patient events creating additional clinical and financial burdens for both patients and healthcare systems,” says David Vawdrey, Geisinger’s chief data informatics officer.

 

“Together with our partner EarlySign, we have forged a dynamic team that is rapidly developing novel solutions to achieve the Quadruple Aim of improving the patient experience of care, improving the health of populations, reducing cost and improving clinical care provider satisfaction,” adds Vawdrey.

 

The AI vendor and Danville, Penn.-based regional healthcare provider intend to develop models that predict unplanned hospital and skilled nursing facility admissions within 30 days of discharge and adverse events such as respiratory failure, postoperative pulmonary embolism or deep vein thrombosis, as well as postoperative sepsis before they occur.

 

According to EarlySign, its suite of outcome-focused software is able to uncover early signs of high-risk patient trajectories in existing lab results and ordinary electronic health record data collected during the course of routine care.

 

“Geisinger’s experience and substantial unified data architecture is the perfect complement to EarlySign’s proprietary data repository and suite of AI tools, enabling the rapid development and validation of effective machine learning models,” says Jeremy Orr, MD, CEO of EarlySign. “These models are designed to integrate seamlessly with current clinical workflows as a decision support tool that can help improve patient outcomes and decrease healthcare costs.”

 

The EarlySign-Geisinger proposal—along with 24 other participants—were selected for Stage 1 of the AI Health Outcomes Challenge out of more than 300 submissions. Participants in the competition will develop their algorithms using Medicare administrative claims data, including Medicare Part A (hospital) and Medicare Part B (professional services).

 

CMS has partnered with the American Academy of Family Physicians and the Laura and John Arnold Foundation and will award as much as $1.65 million for AI healthcare solutions in the challenge.

 

As many as seven participants will be awarded $60,000 each and selected to advance to Stage 2, where they will get the opportunity to further refine their algorithms and solutions using additional CMS data sets. The agency will announce the Stage 2 finalists in April 2020. Ultimately, in September 2020, a grand prize winner will receive $1 million, and the runner-up will receive $230,000.

 

Earlier this year, Geisinger’s Steele Institute for Health Innovation announced a multi-year partnership with EarlySign to develop and deploy a suite of machine learning-based solutions. At the time, the two organizations said they were initially focusing on leveraging EarlySign’s LGI-Flag, which analyzes clinical data to identify patients who will benefit from further evaluation for lower GI disorders associated with chronic occult bleeding.

 

 

Click here to read the original article

Share:

Share on twitter
Share on linkedin
Share on facebook
Share on email

Are you looking to solve high-burden disease challenges?