AI Patient Navigator Can Boost Colonoscopy Adherence

A conversational artificial intelligence patient navigator was successful at re-engaging patients in colonoscopy screening, essentially doubling the colonoscopy completion rate in patients from underserved communities who had previously missed or avoided an appointment, a new analysis found. 

Colorectal cancer (CRC) disparities among people of color in the United States are well documented, Alyson Moadel, PhD, told the audience during a press briefing ahead of today’s presentation at the American Society of Clinical Oncology (ASCO) 2024 annual meeting. 

Compared with White people, Black individuals have a 20% higher incidence of CRC and are 40% more likely to die from the disease. In addition, cases of early-onset CRC are rising more rapidly in Hispanic and Latinx populations than in other racial/ethnic groups, explained Moadel, deputy director of community engagement and cancer health equity at Montefiore Einstein Comprehensive Cancer Center, New York City. 

Despite active outreach by professional patient navigators at Montefiore — which primarily serves people from communities of color and low-income households — 59% of 3276 patients either canceled or did not show up for their colonoscopy in 2022. Only 21% of this group completed the procedure.

This led Moadel and her team to test the ability of the MyEleanor AI patient navigator to re-engage 2400 English- and Spanish-speaking patients who were nonadherent with colonoscopy appointments. 

The MyEleanor AI navigator called patients to discuss rescheduling, assess barriers to colonoscopy uptake, offer live transfers to clinical staff to reschedule appointments, and provide procedure preparation reminder calls.

The AI navigator followed this patient-friendly script: “I’m Eleanor, the automated care assistant for your team at Montefiore. I am calling today because we noticed that you missed your most recent colonoscopy appointment, and we would like to help you reschedule it at the end of this call.”

What’s “very exciting,” said Moadel, is that more than half — 57% (1368 of the 2400 patients) — actually had a conversation with MyEleanor, some lasting up to 9 minutes. 

Of the patients who engaged with the AI navigator, 58% (789 of 1368) accepted live transfer to a staff member to reschedule their appointment, and 25% of these patients completed their colonoscopy screening. 

The no-show completion rate nearly doubled from 10% to 19%, and patient volume for colonoscopies increased by 36%. 

Patients also reported barriers to screening, which included transportation (38%), no perceived need (36%), time constraints (36%), lack of prompting from their doctor (33%), medical mistrust (32%) as well as concerns about findings from the screening (28%) and cost (27%).

Moadel said next steps include measuring the impact of MyEleanor on patient navigator burden, patient satisfaction, and cost savings, and testing it in other screening programs such as lung and breast.

Using AI to Deliver More Equitable Cancer Care

“Overall, this quality improvement initiative is a truly innovative means of increasing cancer screening,” Fumiko Chino, MD, with Memorial Sloan Kettering Monmouth, in Middletown, New Jersey, told the briefing. “It really offloads the work from an overburdened healthcare workforce by leveraging AI to optimize the outreach capacity to vulnerable populations.”

Chino, who wasn’t involved in the project, said this work “delivers on the promise of technology to facilitate better, more efficient, more equitable cancer care, and I really anticipate that it will ultimately improve cancer outcomes.”

A key aspect to highlight, said Chino, is that the patients who conversed with MyEleanor were on average in their 50s, and three-fourths were Black, Latinx, or Hispanic, “so the intervention really did work in the population at highest risk for screening gaps.”

Chino said it’s important to note that this was a quality improvement project, not a randomized control trial, and the AI navigator will need to be continually re-evaluated over time and tested in other populations.

The study had no specific funding. Moadel reports no relevant financial relationships. Several authors have relationships with the AI-enabled care management company MyndYou, which provides the MyEleanor AI navigator.