Health leaders discuss the ways Arizona is addressing health equity through data collection on race and ethnicity


Hannah Saunders


A key aspect of identifying and reducing health disparities is data collection, which is an area of focus for Arizona healthcare leaders. State health officials met at the 2023 Arizona State of Reform Health Policy Conference last month to discuss improvements to data collection across the state.

Siman Qaasim works as the assistant director for policy and intergovernmental affairs at the Arizona Department of Health Services (ADHS). She said it’s important to understand how health departments—including public health departments—collect population data, and to refine it to understand health conditions at local levels. 

“What I would love to see, and we work a little bit on it on our Data Advisory Committee that we have at the department, which is to really champion the collection of data, more nuanced race and ethnicity [data], and of course SOGI data—that’s sexual orientation, gender identity, and expression data. We need that data to figure out who is experiencing what.”

— Qaasim

ADHS’ data analytics section lead, Wesley Kortuem, discussed how artificial intelligence is being utilized to enhance health equity. Kortuem said the department is working with a software called Tamr that allows ADHS to extract data and to use a machine—which they are learning to train—in order to recognize when an individual in one database is the same as an individual in a separate database. 

“Having the machine learning in place, that allows us to bring both datasets in—multiple datasets, actually—and then we can tell the machine what the scheme of the two tables are and give it certain variables—address, city, state, zip [code], race, ethnicity, name, all of these things, whatever we have—and then let the machine look at these different records and try to pair them up,” Kortuem said. 

The pairs can then be looked at and determined if they are the same individual in the separate databases. Regardless, Kortuem said the machine learns something as a result. This process must be continued until the machine is fully trained to make that distinction of individuals.

Kortuem explained how from there, a master person index can be created, which would identify each individual in each siloed dataset. An additional modernization initiative stemmed from evident areas of improvement during the COVID-19 pandemic. 

“We’re making improvements all the way from where the data is being entered, to the final analysis, so, we get the data from a lot of sources—death certificates and so on,” Kortuem said. 

Matthew Isiogu, chief revenue officer of Contexture (the major health information exchange in Arizona and Colorado), noted how important it is for individuals to have numerous options when submitting identifying data about themselves. 

He said he was in a meeting earlier this year where the team looked at race and ethnicity data from all hospitals and health systems. Isiogu said that when looking at the individual level, the team noticed how some selected more than one race, and that the option to select multiple races is the data standard. On the other hand, this data standard may not be the way hospital paperwork, for example, is designed, which may force individuals to choose between one race option or another. 

“I think we are at a really critical time when there’s interest across sectors to do this work,” Isiogu said. “State agencies are being very creative to come up with funding opportunities and strategic alignment across agencies, but it’s just as important—if not more important—that when we are making these decisions, the structure, the data about governments of that data, that we have a diversity of perspectives and representation at the table.”