AI Can Help Improve Clinical Attendance Among Minority Patients

Led by MetroHealth and Case Western Reserve University (CWRU) researchers and published in the Journal of General Internal Medicine, new research indicates a high level of success associated with using artificial intelligence (AI) to determine the chances of appointment no-show rates among residents of various Cleveland-based communities, including minority groups. 

Healthcare disparities and varying degrees of access to social determinants of health (SDOH) resources can result in patients struggling to attend appointments. For instance, text messages commonly serve as appointment reminders; however, technological disparities often hinder this process.

To counter these issues, researchers used AI to take a more proactive approach to determine the chances of missed appointments.

 “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, in a press release. “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.”

Focusing on adult internal medicine patients with a likely no-show rate of 15 percent or higher, MetroHealth and CWRU researchers used patient data to build an AI model in MetroHealth's Epic EHR system. Following this, they conducted a trial between January and September 2022 that included a portion of the study population receiving phone calls from MetroHealth schedulers. For those who noted that certain factors would prevent them from traveling to appointments, MetroHealth extended options for telehealth or transportation.

They found that Black patients who received phone calls had no-show rates that were 36 percent lower than those who did not receive any calls.

“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 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.”

Following the successful results, MetroHealth’s internal medicine clinic has continued using the Epic AI model to call patients who appear likely to be no-shows.

As AI use in healthcare grows, researchers are finding new ways to leverage its capabilities.

For example, a survey from the Health Management Academy in March showed that many C-suite executives used AI for back office and clinical operations.

Researchers noted that staffing insufficiencies are on the rise, leading many organizations to turn to AI technology. Their data indicated that just under half of survey respondents were using AI for workforce issues at the time, and the remainder of the population was considering its use for this reason.