Three third-year students at the Harvard School of Dental Medicine have created an interactive mapping tool that makes a massive federal Medicaid dataset usable for researchers and policymakers, according to the Harvard Gazette.

Clark Morgan, Kenny Liu, and Samat Borbiev — all D.M.D. candidates set to graduate in 2028 — developed CHOMP (Claims History of Oral Healthcare Medicaid Procedures) after the U.S. Department of Health and Human Services released a Medicaid claims dataset spanning 2018 to 2024 in February 2026. The agency had touted the data as a tool for exposing fraud, but the students saw an opportunity to use dental claims within the dataset to reveal gaps in care and differences in oral health access across the country.

“We realized there was a great deal of dental information in the data that could be used to highlight true needs and dental care,” Morgan told the Gazette. “We could take this massive dataset that usually would cost thousands and thousands of dollars and create a public tool for researchers and policymakers.”

The raw dataset contained 227 million rows of claims, and the students initially faced the challenge of turning that volume of information into something useful. As they explored the data, they discovered it included more detailed dental information than they had expected, including dental procedure codes that allowed them to categorize care by type — diagnostic, preventive, restorative — and by dental specialty.

“There were a couple weeks where we were just playing around with tons of data,” Liu said. Discovering that the dataset included dental procedure codes, he said, was unexpected.

To make the data usable, the students realized they needed to add provider location information. They merged the federal claims data with the National Plan and Provider Enumeration System, a federal provider registry, to connect claims with geographic information based on the first three digits of providers’ ZIP codes.

“Our completed dataset is a merger of many different datasets,” said Liu. “We input both geographic information and information from the providers themselves by merging a national provider identity registry. Without that merged step it would be a huge barrier to people using the initially released federal data.”

Liu then reached out to friends with computer science experience to help code the data and turn it into a geographic information system-based visualization. The team sought guidance from Dr. Hawazin Elani, an associate professor in oral health policy and epidemiology at the dental school, who helped refine CHOMP into a tool suitable for health policy and population-level research. Elani and her research team helped incorporate more granular geographic information, including county-level measures, and linked the claims with other national datasets to provide greater context. She also connected the students with additional Harvard resources to further develop the site.

“When the students first showed me what they had built, I was impressed by the scale of the work and the originality of the idea,” Elani told the Gazette. “They had taken an enormous, difficult-to-use federal dataset and created a way to see patterns in dental care that would otherwise remain buried in millions of claims. What makes CHOMP so useful for researchers is that it turns those data into something that can be explored geographically and connected with other national data. Researchers can compare communities and states, and identify policy-relevant questions that would have been much harder to recognize from the raw claims alone.”

The resulting interactive tool allows users to explore Medicaid dental care by year, procedure, specialty, geography, reimbursement, and other contextual characteristics. Once the data were visualized geographically, disparities that were hard to see in a spreadsheet became immediately visible. The students were struck by differences in Medicaid reimbursements across states, with some covering different populations and different procedures.

“I am upset by the fact that the difference in care provided between states can be so drastic,” Morgan said. He pointed to the map and clicked on orthodontics, showing claims from state to state — some states displayed none. “I think of the person who lives right on the other side of the state line who can’t access that care. They’re just as deserving, but they can’t get care because of differing criteria in their state.”

Borbiev noted that the tool makes disparities visually obvious. “Using CHOMP, you can see the treatments that are offered, and you can see very clearly, ‘Oh, this state seems to be doing quite well in these areas of care and this state is not,’” he said.

The students built CHOMP as an open-source tool and envision it being expanded upon. Morgan said the site is intended as “the first iteration of a larger project.”

“By transforming this massive dataset into digestible, actionable insights at the local, state, and national level, we hope this tool and the corresponding framework to organize the data can be useful for policymakers, providers, researchers, and all others interested in improving oral and systemic health,” he said.

All three students plan to pursue oral surgery after graduation, but developing CHOMP has given them a broader view of the factors outside the operatory that can determine the care their patients can receive.

“Beyond your professional expertise, you have all these external factors that impact the treatment you can provide,” Liu said. “I believe very strongly that you should advocate for your patients. And to me, this is a form of patient advocacy.”