Florida State University researchers have received a grant from the National Library of Medicine of the National Institutes of Health to better predict health outcomes in pediatric organ transplants.
Michael Killian, an assistant professor in the College of Social Work, and Zhe He, an associate professor in the College of Communication and Information, will use the $395,200 grant to improve the prediction of patient and graft survival.
The project expands upon a one-year Precision Health Initiative Pilot Grant that was made possible with seed funding from the University of Florida Clinical and Translational Science Institute (UF CTSI) in partnership with Florida State.
“Our research will further our ability to predict post-transplant health outcomes using large datasets from pediatric heart, kidney and liver transplant recipients in the two largest centers in Florida,” He said. “We aim to identify high-risk patients and to support clinical care and decision-making within pediatric organ transplant centers. We are excited about this funding from NIH, which will move our collaboration forward and advance the field of organ transplantations.”
UF CTSI is a catalytic hub that expands collaboration and advances translational research. The institute was established in 2008 when UF received the state’s first Clinical and Translational Science Award (CTSA) from the National Institutes of Health.
Additional awards in 2015 and 2019 helped expand the partnership between UF and FSU and ultimately led to the creation of the UF-FSU CTSA hub.
Led by the National Center for Advancing Translational Sciences, the UF-FSU CTSA is part of a nationwide network of more than 50 CTSA hubs, all working to develop, demonstrate and disseminate advances in translational science, a field devoted to turning research discoveries into new approaches that improve health.
“The goal of CTSA generally is trying to develop innovative solutions that will improve the efficiency, quality and impact of turning scientific observations into interventions that will improve the health of individuals and the public,” said He, who serves as informatics lead for the UF-FSU CTSA hub.
The funding from the CSTA supported He and Killian’s pilot program in 2019. The researchers built machine learning models with data from a pediatric organ transplant center in Texas to predict hospitalizations of children who had kidney, liver and heart transplants up to five years post-transplant. The results demonstrated deep learning models as potentially useful tools in helping physicians and transplant teams to identify patients who are at greater risk of poor post-transplant outcomes.
With the support of this grant from the National Library of Medicine, the research team will develop machine learning models to predict health outcomes and adverse events among children who had solid organ transplantations. They will consider social determinants of health and psychosocial factors from clinical notes and combine them with other structured data including demographic, familial, medical, health and other post-transplant characteristics. Then they will apply machine learning and other techniques to predict post-transplant outcomes including organ rejection, graft loss and patient survival while ranking the risk factors that affect post-transplant outcomes in children.
“This project represents an important advancement in pediatric organ transplantation,” Killian said. “Data on the psychological and social determinants of the health and quality of life of these children are usually collected in large datasets or administrative record keeping, but lack more in-depth information on their social and psychological challenges during the posttransplant period. Instead, we will use text notes, assessments and evaluations completed by transplant social workers, psychologists and other multidisciplinary transplant team members to capture important experiences and challenges of patients and their families and bring this information into prediction of health outcomes.”
Killian added: “By working with Dr. He and with funding from NIH, we can bring this valuable information about the patient and family forward into model development and prediction of health outcomes. It’s been my dream for years to enrich our statistical work using psychosocial information which plays such a large role in clinical decision-making.”
The UF-FSU hub is supported by the National Center for Advancing Translational Sciences of the National Institutes of Health under University of Florida Clinical and Translational Science Awards UL1TR001427, KL2TR001429 and TL1TR001428.