$2.8M NIH Grant to Support Development of Kidney Transplant AI
University of Florida Health researchers will use the funding to evaluate how artificial intelligence may help clinicians better predict kidney transplant outcomes.
Source: Getty Images
By - Researchers at University of Florida (UF) Health have been awarded a $2.8 million grant from the National Institutes of Health (NIH) to develop an artificial intelligence (AI)-based clinical decision support system to help improve kidney transplant outcomes.
As part of the five-year project, the research team will examine how AI models could assist with diagnosis, prediction, and care management for kidney transplant patients. In particular, one of the tools being developed will leverage patient data and analysis of kidney tissue samples to predict transplant outcomes.
The ability to accurately forecast outcomes has the potential to address some of the significant issues impacting transplant care: the availability of organs and organ rejection. The press release indicates that in the case of kidney transplants, the number of needed kidneys far outstrips the supply.
The AI tool could aid care teams in identifying which patients are likely to experience a successful first-time transplant, which may lead to improved outcomes and reduce the number of organ rejections.
Such a model could have the capacity to assess massive amounts of data while streamlining the process of evaluating biopsy slides, which would allow clinicians to focus their time and energy on more important aspects of patient care.
“Our challenge is to develop a system that gives doctors the most consistent medical information so they can make the best, most informed decisions,” said Pinaki Sarder, PhD, an associate professor of AI in the UF College of Medicine’s department of medicine and associate director of imaging for UF’s Intelligent Critical Care Center.
The AI system will integrate demographic and medical data from both kidney recipients and donors with high-resolution biopsy images, which will be analyzed and used to flag injuries or other issues with the donor kidneys in question.
Researchers will determine the model’s effectiveness by comparing its performance in predicting future kidney function to existing tools utilized by clinicians for the same purpose.
“At the end of the study, we’re going to know whether predicting future kidney function is better with AI than it is with existing clinical methods — or if it’s about the same,” Sarder explained.
The press release notes that the research is likely to be valuable to clinicians in that it will provide access to robust datasets of kidney transplant biopsy imaging, which could lead to better, more informed care for kidney transplant patients.
Other institutions are also undertaking research to evaluate AI’s potential in organ transplant care.
In a recent interview with HealthITAnalytics, Rohan Goswami, MD, a transplant cardiologist at Mayo Clinic in Florida, and Byron Smith, PhD, a biostatistician involved in transplant research at Mayo Clinic in Minnesota, discussed the challenges clinicians face in improving transplant outcomes and how the health system’s research into AI aims to address these hurdles.
