AI applications bring veterinary data to the CVM community


Human medicine has long been able to use artificial intelligence to harness patient data to augment the work of clinicians and researchers. Now, thanks to an effort by the College of Veterinary Medicine (CVM) Information Technology team, these tools will soon be available to faculty, staff and students for animal research.

“The college has a wealth of contemporary and historical clinical data that we have long wanted to use more effectively for research, teaching and practice,” said Dr. Lorin D. Warnick, Ph.D. ’94, Austin O Hooey Dean of Veterinary Medicine. “This recent work by the Information Technology team is a major achievement towards that goal.”

Established as a goal of CVM’s strategic plan, college faculty and administration are committed to improving the ability to analyze clinical, research, and business data.

“Right now in the veterinary industry, a lot of data is still siloed,” said Scott Ross, assistant director of application development and integration. “We are trying to solve this problem in the long term.”

The mission was led by Dr. Meg Thompson, associate dean of hospital operations and director of Cornell University Hospital for Animals (CUHA). Very few veterinary institutions have developed comprehensive, searchable databases for daily use in the clinic, classroom, and laboratory.

“We’re trying to answer some really interesting questions,” Ross said. “We would like to move the needle in veterinary medicine towards more evidence-based decision-making. Thanks to Dr. Thompson, the college is beginning to realize the power of the data contained in many of its applications.

Thompson has established strategic partnerships with industry leaders, including ezyVet, while allowing the technology team to focus on innovative solutions rather than operational concerns.

The data used for these apps includes everything from the 1.4 million clinical cases recorded by the CUHA and veterinary specialists at Cornell University, some dating back to the early 1970s – to the 14.2 million diagnostic tests that the Animal Health Diagnostic Center has documented since 2000. It also includes 90 terabytes of pathology slides that were digitized during the pandemic to allow veterinary pathologists to view tissue samples remotely. The project also integrated administrative data from the human resources and accounting platforms.

The first step with these multi-million datasets was to do “data positioning,” which means “massage it into something usable by people,” Ross said. Next, the team, including software developers Steve Halasz and Daniel Sheehan, coded three apps to make them easy to use:

  • Case finding: Launched in June 2020, this digital app allows faculty, staff and students to perform a Google-like search of the millions of clinical cases recorded since the 1970s using a variety of keywords, including diseases, breeds and owners’ names – instantly pulling results that show major issues, medications, labs, diagnosis and more.
  • Case experience: Launched in September 2021, this app provides a comprehensive dashboard of all clinical cases seen by any clinician or student in the hospital, allowing a per-person breakdown of species and races, diseases, medications and procedures, and case processing times. This is especially useful for students in their clinical rotations and specialist trainees, who can then view and track the extent of their clinical experiences in a single view. It allows both faculty and students to identify potential skills gaps and track progress, and will contribute to the college’s commitment to a competency-based curriculum.
  • Cohort builder: Scheduled for release in 2022, this application will identify patient groups for research projects using heterogeneous datasets, accurately identifying relevant patients and associated data, thereby improving the quality of studies and research. For example, a clinician-researcher who wants to study the success of a surgical technique in a certain group of dogs would normally spend hours manually researching past cases, recording individual data fields in a spreadsheet, and then to analyze the results of each case. Cohort Builder does this automatically, extracting all relevant cases, so researchers can build a large sample size for their analysis.

“For all clinical research that involves searching medical records, especially retrospective cohort studies, this type of technology is extremely useful,” said Dr. Robert Goggs, associate professor of emergency and critical care. “We are always looking to maximize the number of patients we can include in our studies while ensuring that we obtain comprehensive, high-quality data. Using AI to tap into the wealth of our collective health records to help answer research questions is a huge time saver.

Going forward, Ross said, the team hopes to leverage human resources and administrative data for other types of analytics and continue building apps that tap into the college’s wealth of information.

“We are excited to put these tools in the hands of our faculty, staff and students to make their daily lives easier,” Ross said.

Lauren Cahoon Roberts is Director of Communications at the College of Veterinary Medicine.


Comments are closed.