MetroHealth, CWRU Researchers Use AI to Improve Access to Clinics for Minorities
A study led by MetroHealth and Case Western Reserve University researchers shows that using Artificial Intelligence (AI) to predict the probability of no-show appointments in a busy clinic – followed up with personal outreach to those at-risk patients – resulted in improved show rates for patients, especially those who were Black.
Although patients receive appointment reminders through text messages and other means, researchers found that additional outreach proved beneficial because of the wide disparities in access to technology in various communities throughout Cleveland.
The AI model can potentially be used to improve access to care in other clinics and health systems. Results of the study are available in the Journal of General Internal Medicine.
“We used the AI technology to figure out who needed additional support or an alternative low-tech outreach solution,” said Yasir Tarabichi, MD, the study’s lead author and MetroHealth’s Medical Director of the Virtual Care Enterprise and Director of Clinical Research Informatics. “When we use automatic tools for reminders in a community with a huge digital divide, we are making assumptions those reminders are reaching everyone. That is not true. Minorities have less access to reliable internet and are less likely to use patient portals to engage with care. It is a complex problem we are trying to solve.”
Additional authors are MetroHealth’s Jessica Higginbotham, Principal, Department of Transformation and Optimization; Nicholas Riley, MD, PhD, Center for Clinical Informatics Research and Education; David Kaelber, MD, PhD, MPH, Vice President, Chief Medical Informatics Officer and Vice President of Patient Engagement Technologies; and Brook Watts, MD, formerly of MetroHealth and now with the University of Michigan. Drs. Tarabichi and Kaelber also hold appointments at Case Western Reserve’s School of Medicine – Associate Professor of Medicine, and Professor of Internal Medicine, Pediatrics and Population and Quantitative Health Sciences, respectively.
Using patient data, researchers built an AI model in Epic, MetroHealth’s electronic health record system, to predict the chances a patient would miss an appointment. The study targeted adult Internal Medicine patients who had a probable no-show rate of 15% or greater.
Between January and September of 2022, a random selection of those patients received phone calls from MetroHealth schedulers. If patients indicated barriers that may prevent them from showing for their appointments, schedulers offered resources such as transportation or telehealth options.
Black patients who received phone calls had a 36% reduction in no-show rates compared to those who did not receive a call. Although race and ethnicity were not included as variables in the design build, MetroHealth has a sizable Black patient population.
The reason for not calling everyone who had scheduled appointments boils down to limited human resources and the need to ensure equity.
“The fear was implementing a model that gave more opportunities to patients who were not in dire need of better access, which would widen disparity gaps,” said Dr. Tarabichi, adding that the AI allowed for the creation of a fair model that avoided that. “We want to provide an outreach mechanism that is fair and provides a level of equity. People at a higher risk for not showing up are the ones we are helping the most. Minority patients were more likely to pick up the phone when called, and we met them where they were.”
The study is significant because racial and ethnic disparities in missed appointments are common in safety-net health systems like MetroHealth. These disparities in access risk harming the very patients safety-net systems are designed to serve.
“This is an amazing example of using technology, in this case machine learning, to have our staff work smarter and not harder, to help close no-show disparities in our patient population to improve care,” Dr. Kaelber said.
Due to its success, MetroHealth’s Internal Medicine clinic continued using the Epic AI model to call potential no-show patients. And the model can be tailored for usage in other MetroHealth clinics – and possibly other health systems – to reach at-risk patients.
“Leveraging this technology with creation of a standardized telephone outreach approach and simple, streamlined documentation allows our front-end staff to do this work during their busy clinic day alongside their other duties. This is a win for the system and our patients,” Higginbotham said.
Dr. Tarabichi said it is important to remain focused on the big picture when using this type of technology.
“A lot of people think AI is going to instantly revolutionize health care, but it has to be put through paces, validated and tested,” he explained. “Models must be implemented in ways that do not make disparities worse. This study hopefully provides a roadmap for health care systems thinking about implementing AI.”
The research project was supported by the Clinical and Translational Science Collaborative of Cleveland, a collaborative among Case Western Reserve and its affiliated hospital systems, which includes MetroHealth.
Founded in 1837, MetroHealth is leading the way to a healthier you and a healthier community through service, teaching, discovery, and teamwork. Cuyahoga County’s public, safety-net hospital system, MetroHealth meets people where they are, providing care through four hospitals, four emergency departments, and more than 20 health centers and 40 additional sites. Each day, our 8,000 employees focus on providing our community with equitable health care–through patient-focused research, access to care, and support services–that seeks to eradicate health disparities rooted in systematic barriers. For more information, visit metrohealth.org.