High performance computing could prove both beneficial and life saving in health care analytics. A recent report from HPCwire’s Michael Feldman says that at Lund University and Skåne University in Sweden, researchers are building an HPC-based model of heart-transplant recipients and donors to improve survival times.
Called the “survival model,” it is designed to discover the optimal matches between heart transplant recipients and donors. Feldman explains, “It takes into account such factors as age, blood type (both donor and recipient), weight, gender, age, and time during a transplant when there is no blood flow to the heart. Just analyzing those six variables leads to about 30,000 distinct combinations to track.”
Using MATLAB—a high-level technical computing language and interactive environment for algorithm development, data visualization, data analysis, and numerical computation—and MathWorks libraries, the Lund researchers built their predictive artificial neural network (ANN) models. And, using donor and recipient data from two databases—the International Society for Heart and Lung Transplantation (ISHLT) registry and the Nordic Thoracic Transplantation Database (NTTD)—the ANN simulation predicts survival rates for heart transplant patients based on the suitability of the donor match.
The results from the simulations were used to pick out the best and worst donors for any particular recipient. The ultimate goal, Feldman notes of the research, is to “determine the mean survival times after transplantation for waiting recipients, so that doctors can make the best possible decision with regard to matches.” 10,000 patients that had already received transplants were critical in helping the researchers during the study.
The findings were significant: ANN models could increase the five-year survival rate by 5 to 10 percent, compared to the traditional selection criteria performed by practicing physicians. Perhaps more importantly, using a randomized trial based on preliminary results, approximately 20 percent more patients would be considered for transplantation under these models, said Dr. Johan Nilsson, Associate Professor in the Division of Cardiothoracic Surgery at Lund University.
Although the compute-intensive models used a nine-node Apple Xserve cluster and 64 CPUs to run the ANN simulation, the article points out that, “presumably with a late model HPC setup, they could cut the five-day turnaround time for the simulation even more, which would speed up the research even further.”
LTI’s High Performance Computing services integrate HPC tools with the way you do business. To learn more about LTI’s HPC capabilities, click here. Contact us to learn more about the platforms we have expertise in.