One of medicine’s most trusted diagnostic tools - the blood test - has been given new life thanks to a software algorithm. The piece of computer wizardry, developed by scientists at the Stanford University School of Medicine, means a single blood sample could help doctors spot transplant failures quicker, as well as the onset of cancers and genetic disorders.
The new technique involves running the algorithm against blood data taken from a microarray. The common lab device - sometimes called a DNA chip - allows doctors to distinguish short sequences of nucleic acids - the genetic material inside cells. However, danger signs contained within the sequences have gone undetected up to now because of the complexity of the data.
“Drawing blood is one of the most common diagnostic tests in clinical practice,” says one of the investigators, Atul Butte, MD, PhD, assistant professor of pediatrics and of medical informatics. “We’d love to be able to use microarrays to find changes in the blood that indicate trouble somewhere in the body.” However, a single sample contains dozens of cell types, at different levels of maturity or at different stages of activation, and it’s been impossible to get a clear picture.
But with the new algorithm that’s all changed. In tests, researchers looked at whole blood samples from 24 pediatric kidney-transplant patients. Fifteen of the 24 patients were experiencing symptoms of acute transplant rejection, while nine were in stable condition. When they analysed patients' whole blood samples using microarrays but without the new algorithm, the samples from both groups looked the same. But when they used the algorithm, they found hundreds of differences in the gene expression, and with this information, doctors saw which patients were rejecting their transplants and which were not.