Banner
  • Revenue Cycle Management
  • COVID-19
  • Reimbursement
  • Diabetes Awareness Month
  • Risk Management
  • Patient Retention
  • Staffing
  • Medical Economics® 100th Anniversary
  • Coding and documentation
  • Business of Endocrinology
  • Telehealth
  • Physicians Financial News
  • Cybersecurity
  • Cardiovascular Clinical Consult
  • Locum Tenens, brought to you by LocumLife®
  • Weight Management
  • Business of Women's Health
  • Practice Efficiency
  • Finance and Wealth
  • EHRs
  • Remote Patient Monitoring
  • Sponsored Webinars
  • Medical Technology
  • Billing and collections
  • Acute Pain Management
  • Exclusive Content
  • Value-based Care
  • Business of Pediatrics
  • Concierge Medicine 2.0 by Castle Connolly Private Health Partners
  • Practice Growth
  • Concierge Medicine
  • Business of Cardiology
  • Implementing the Topcon Ocular Telehealth Platform
  • Malpractice
  • Influenza
  • Sexual Health
  • Chronic Conditions
  • Technology
  • Legal and Policy
  • Money
  • Opinion
  • Vaccines
  • Practice Management
  • Patient Relations
  • Careers

HIMSS23: AI in action

Article

How AI is helping measure and manage health disparities

HIMSS crowd Courtesy of HIMSS | © Lotus Eyes Photography

Courtesy of HIMSS | © Lotus Eyes Photography

When ChristianaCare, a three-hospital network in Delaware, needed to close health disparities, it turned to artificial intelligence to help. They had a diverse patient population and had observed health disparities in outcomes and wanted to address the problem, said Yuchen Zhang, a data scientist at the health system, who presented at HIMSS23 in Chicago.

ChristianaCare started with gathering race/ethnicity data, started community outreach, and put a focus team in primary care offices to help people get enrolled in assistance program. But data was lacking on health disparities among different outcomes and resources were stretched thin.

The challenge was to develop one metric that would measure all the disparities that could change outcomes. The goal was to have quality of care be consistent regardless of race, gender, ethnicity, geography, language, payer, or socioeconomic status. They wanted to make sure quality of care should not be able to be predicted by any of the previous factors.

The team at ChristianaCare built a machine-learning model that looked at various health equity factors and produced data to show how likely it was for each patient to have an adverse outcome.

Once the data was accumulated, they had to decide with primary care practices to focus on. They looked at the expected outcomes compared to actual outcomes, then identified the practices that perform better and share the learnings. The health system allocated additional resources to help underperforming practices improve, such as adding texting system between the primary care office and the patients to improve communication.

By measuring the data and taking actions, ChristianaCare was able to improve outcomes across all racial groups. Surprisingly, the gap between White and Black patients increased, even while Black outcomes also improved.

Zhang said it shows that some interventions are more effective than others. For example, the texting system helped, but more Black patients did not have a smart phone than Whites, so the lack of a device limited how effective the program could be for Black patients.

Related Videos
Kyle Zebley headshot
Kyle Zebley headshot
Kyle Zebley headshot
Michael J. Barry, MD
Hadi Chaudhry, President and CEO, CareCloud
Claire Ernst, JD, gives expert advice