Original article was published by on artificial intelligence
- A $3.2 million grant from NIH will support researchers in using artificial intelligence to improve outcomes for heart transplant patients.
Researchers from the Perelman School of Medicine at the University of Pennsylvania, Case Western Reserve University, Cleveland Clinic, and Cedars-Sinai Medical Center will use the four-year grant to determine the likelihood of cardiac patients accepting or rejecting a new heart.
A patient’s body rejecting the donor organ is one of the most significant risks of a heart transplant. The body’s immune system may see the donor heart as a foreign object and try to reject it, which can then damage the organ. Rejections occur in 30 to 40 percent of patients during the first year after transplant.
However, the current rejection grading standard has poor diagnostic accuracy, as well as a limited ability to determine the mechanism of rejection. These limitations expose patients to risks of both over- and under-treatment.
Using artificial intelligence, researchers will analyze cardiac biopsy tissue images to distinguish potential cardiac rejection grades and detect patterns of immune cells that reveal the mechanism of rejection.
With improved diagnostic accuracy, providers may be able to recognize serious rejection earlier, leading to reduced rates of infection and other complications of immune-suppressing drugs taken by transplant patients. This could also help develop more precise, targeted medications. Going forward, the team expects to be able to predict how patients will do in the long-term, allowing for fewer biopsies of the heart.
Penn Medicine, Case Western, Cleveland Clinic, and Cedars-Sinai will provide digitized images of biopsies from patients who have already had transplants. Researchers will then apply AI techniques to the dataset to see whether the initial biopsy images could have more accurately predicted which patients would accept or reject the new heart.
The research team will also compare the relative performance of the AI analysis against human pathologists to compare their accuracy in identifying serious rejection. Previous research has shown that computers were more accurate than human clinicians in diagnostic ability. But the research team believes that AI will not replace their human counterparts.
“Computer-aided tissue diagnostics will serve as a decision support tool for pathologists, consistently and efficiently identifying subtle features that will increase the value of the diagnostic procedure and ultimately improve patient outcomes,” said Kenneth B. Margulies, MD, a professor of cardiovascular medicine at Penn.
This assertion matches what seems to be the general consensus among leaders in healthcare. A recent study published in JAMA Network Open showed that machine learning tools could help enhance the accuracy of breast cancer screenings when combined with assessments from human radiologists.
“Based on our findings, adding AI to radiologists’ interpretation could potentially prevent hundreds of thousands of unnecessary diagnostic workups each year in the United States. Robust clinical validation is necessary, however, before any AI algorithm can be adopted broadly,” said Dr. Christoph Lee, professor of radiology at the University of Washington School of Medicine and co-first author of the paper.
Researchers from the National Cancer Institute (NCI) have also explored the potential for AI to act as a companion tool for providers. A team recently developed a fully automated dual stain test to improve cervical cancer screenings.
“This is what we call an assisted evaluation. It keeps the observer, or whoever is doing the slide assessment in the process, but it uses the power of AI to accelerate the process and make sure that cells are not missed. This could be a transitional phase towards the full implementation of the automated approach,” Nicolas Wentzensen, MD, PhD of NCI’s Division of Cancer Epidemiology and Genetics, told HealthITAnalytics.
With the grant from NIH, researchers from Penn, Case Western, Cleveland Clinic, and Cedars-Sinai will accelerate further innovation in artificial intelligence and clinical decision support.
“This research is focused on a critical component of heart transplantation—improving patient outcomes. Unfortunately, the number of patients with end-stage heart failure is increasing. But research like this is another step in the right direction for improving survival and quality of life for heart failure patients,” said Margulies.