“We set out to create a custom AI predictive model that could be evaluated, tracked, improved and implemented to pave the way for more inclusive and effective population health strategies.” — Reshma Gupta

Creating the BE-FAIR model

To create the system-wide BE-FAIR model, UC Davis Health brought together a team of experts from the health system’s population health, information technology and equity teams.

Over a two-year period, the team created a nine-step framework that provided care managers with predicted probabilities of potential future hospitalizations or emergency department visits for individual patients.

Patients above a threshold percentile of risk were identified, and, with primary care clinician guidance, determined if they could benefit from program enrollment. If appropriate, staff proactively contacted patients, provided needs assessments and began pre-defined care management workflows.

Responsible use of AI

After a 12-month period, the team evaluated the model’s performance. They found the predictive model underpredicted the probability of hospitalizations and emergency department visits for African American and Hispanic groups. The team identified the ideal threshold percentile to reduce this underprediction by evaluating predictive model calibration.

“As healthcare providers we are responsible for ensuring our practices are most effective and help as many patients as possible,” said Gupta. “By analyzing our model and making small adjustments to improve our data collection, we were able to implement more effective population health strategies.”

Studies have shown that systematic evaluation of AI models by health systems is necessary to determine the value for the patient populations they serve. 

“The BE-FAIR framework ensures that equity is embedded at every stage to prevent predictive models from reinforcing health disparities.” — Hendry Ton

“AI models should not only help us to use our resources efficiently — they can also help us to be more just,” added Hendry Ton, associate vice chancellor for health equity, diversity, and inclusion. “The BE-FAIR framework ensures that equity is embedded at every stage to prevent predictive models from reinforcing health disparities.”

Sharing the framework

The use of AI systems has been adopted by health care organizations across the United States to optimize patient care.
About 65% of hospitals use AI predictive models created by electronic health record software developers or third-party vendors, according to data from the 2023 American Hospital Association Annual Survey Information Technology Supplement.

“It is well known that AI models perform as well as the data you put in it — if you are taking a model that was not built for your specific patient population, some people are going to be missed.” — Jason Adams

“It is well known that AI models perform as well as the data you put in it — if you are taking a model that was not built for your specific patient population, some people are going to be missed,” explained Jason Adams, director of data and analytics strategy. “Unfortunately, not all health systems have the personnel to create their own custom population health AI predictive model, so we created a framework healthcare leaders can use to walk through and develop their own.”

The nine step framework of the BE-FAIR model is outlined here.

A ribbon cutting was held today for UC Davis Comprehensive Cancer Center’s first-ever mobile mammography clinic. The MobileMammo+ bus will serve marginalized and hard-to-reach rural communities to increase access to breast cancer screening.

“When people can’t come to us — we will go to them,” said cancer center Director Primo “Lucky” Lara Jr. “The tragic news is that while breast cancer rates are lower in rural areas, deaths from breast cancer are much higher. This is due to lower screening rates.”

The MobileMammo+ bus will be parked at the UC Davis Health Elk Grove Clinic for several days a week and then travel to Federally Qualified Health Centers to serve communities throughout the region the rest of the week. In the future, MobileMammo+ may visit non-clinical locations such as churches and social service agencies.

Research lab on wheels

Services on the 45-foot-long clinic-on-wheels include mammograms, multilingual care and health education. The mobile clinic also serves as a data collection hub for health equity research led by Diana Miglioretti, breast cancer researcher and UC Davis biostatistics division chief. She also co-leads the cancer center’s Population Sciences and Health Disparities program.

“More than 30% of people are inadequately screened for breast cancer and rates are even lower among marginalized communities,” Miglioretti said. “The mobile mammography service helps us gather crucial data for health equity research, which will help us tailor our cancer prevention programs and deepen our understanding of breast cancer in diverse populations.”

Over a five-year period, data collected on MobileMammo+ will help build a repository of long-term data on breast cancer screening, diagnosis and treatment.

“The idea is to develop effective, individualized care by leveraging leading-edge genomics and AI (artificial intelligence) to predict breast cancer risk in underserved women,” Miglioretti said.

Increasing access to breast cancer screening

Patients in many rural and urban communities struggle to access preventive health care due to barriers including transportation, insurance, language differences and distance to a provider or clinic.

The project will draw on expertise from Shadi Aminololama-Shakeri, chief of breast radiology at UC Davis Health. Also involved is Laura Fejerman, a leading researcher of breast cancer in Latinas and co-director of the cancer center’s Women’s Cancer Care and Research Program. Fejerman is associate director for the cancer center’s Office of Community Outreach and Engagement and co-director of the Latinos United for Cancer Health Advancement initiative.

“We want to build and implement a multi-faceted program to improve cancer screening and diagnosis that incorporates traditional and innovative approaches that will lead to more effective and personalized strategies for underserved communities,” Fejerman said.

Bringing mammogram screening to communities

Staffed with a certified breast imaging technologist, MobileMammo+ will perform services that mirror the radiology expertise at UC Davis Health clinics. “This will allow us to offer state-of-the-art 3D mammography to under-resourced and remote communities,” Aminololama-Shakeri said.

Offered on board will be breast cancer screening education, outreach and navigation services to increase screening participation and patient navigation to ensure that follow-up diagnostic imaging and breast cancer treatment are received, if indicated.

“We hope to screen nearly 5,000 women a year,” said Alyssa Reed, senior program manager for MobileMammo+.

Reed, a breast cancer survivor, stresses the importance of early detection. Mammograms can correctly identify about 87% of breast cancers in women.

“We know that the earlier breast cancer is caught, the greater the chances of successfully treating that cancer,” Reed said.

Screening for other cancers in the future

Cervical cancer screenings also may soon be available on MobileMammo+ through human papillomavirus (HPV) self-testing.

“The cancer center is seeking additional funding to conduct a study on the mobile mammography bus that uses HPV testing kits to increase cervical cancer screening rates,” said Julie Dang. She is executive director of the cancer center’s Office of Community Outreach and Engagement and conducts studies focused on HPV-related cancers.

HPV vaccinations and colorectal cancer FIT tests may also be brought on board as MobileMammo+ expands in future years.

When people can’t come to us — we will go to them.” — UC Davis Comprehensive Cancer Center Director Primo “Lucky” Lara Jr.

Funding for MobileMammo+

Initial funding for MobileMammo+ came from a settlement award that arose from a class-action lawsuit against Wyeth Pharmaceuticals. The lawsuit alleged that Wyeth misrepresented the benefits and risks of its hormone replacement therapy medication for women.

When money remains after eligible class members receive their claim payments, courts can distribute those residual funds to charitable causes. The proposed mobile mammography service was one of the recipients of those surplus Wyeth settlement funds.

Funding is key for multiplying the impact of MobileMammo+

Expansion of the mobile mammography service depends upon philanthropic support as well as grants.

“There is so much more we would like to do to increase access to cancer screenings and save lives,” said Miglioretti. The mobile service, she added, may be able to perform other types of cancer screenings down the road.