London researchers score two breakthroughs in prenatal health care

Article content

Two breakthrough discoveries by London researchers in prenatal care will use AI-led technology to allow early diagnosis of rare diseases and identify birth disorders.

Researchers at the London Health Sciences Centre (LHSC) and the Lawson Health Research Institute are using cutting-edge technology and artificial intelligence to help diagnose more than 100 genetic diseases once difficult to identify.

Article content

One of the findings uses a technology called EpiSign, which applies AI to track marks – found on a deep layer of the patient’s DNA – which is responsible for turning genes on or off with a simple blood test.

That allows doctors to provide earlier and more accurate diagnoses for expectant patients, resulting in improved disease management of birth disorders and the identification of malformations in baby embryos.

“It also has the potential to lead to health system cost savings since many patients spend years and even decades being tested to rule out other potential diseases with similar symptoms,” Dr. Bekim Sadikovic, a Lawson scientist at LHSC, said in a news release.

Research by the same team using EpiSign has also developed another use for the technology.

It can help to diagnose a group of disorders called fetal valproate syndrome, caused by prenatal exposure to toxic levels of medication used to treat bipolar disorder and migraines or to control seizures in the treatment of epilepsy.

Left undiagnosed, that can result in brain development disorders in infants, including learning, communication and motor disorders, autism and intellectual disabilities.

Article content

It’s the first time the technology has been used to assist in the diagnosis of a disease caused by environmental factors rather than genetics. This research highlights how environment—such as lifestyle, including diet, exercise, and exposure to toxins—and genes can influence disease, Sadikovic said.

“These studies demonstrate that in addition to being able to identify genetic diseases, we can also now identify diseases that are not known to be caused by genes,” he said.

As for its AI aspect, this technology feeds on information collected from patients’ blood samples and turns it into algorithms that can map and diagnose more than 150 conditions.

With more than 4,000 known genetic diseases that can present similar characteristics, the technology can avoid multiple tests for patients and even speed up the diagnosis, Sadikovic said.

The research could also improve the diagnosis of cancer, which remains difficult for patients with leukemia, who have to go through multiple tests, the technology is able to assist with tailored and better therapy.

Although it’s an “immediate goal,” Sadikovic said it will still take a few years before these technologies can be used for cancer diagnosis.

Article content

“We’re hoping that as we learn more about these …. (genetic) patterns in different types of diseases that we can use this information to perhaps reverse these patterns and ultimately treat and manage these diseases,” Sadikovic said, who works with the global EpiSign Discovery Research network, currently studying and developing the technology to map more than 700 rare disorders.

The London research was published Wednesday in two medical journals, the American Journal of Human Genetics and Genetics in Medicine.

bbaleeiro@postmedia.com
@BeaBaleeiro

Article content