Algorithm for addiction

HUMMELSTOWN, Pa.—As heroin and other opioid-oriented epidemics leave thousands of overdoses in their wake, Prescient Medicine, a predictive health intelligence company, has developed a new tool called LifeKit Predict which is based on genetic factors playing a significant role in prescription opioid addiction.

The test was developed out of the results of research in the study, “Multi-variant Genetic Panel for Genetic Risk of Opioid Addiction,” published in a recent issue of Annals of Clinical & Laboratory Science.

The study first described genetic variations between opioid-addicted and non-addicted populations, with the goal of developing a predictive algorithm to determine opioid addiction risk. The algorithm produced an addiction risk score that is based on 16 single nucleotide polymorphisms, or genetic mutations, in the brain reward pathways, and was developed using 37 patients with prescription opioid or heroin addiction and 30 age- and gender-matched non-addicted patients. This became the basis for the predictive model.

“Our first step included a collaboration with AutoGenomics Inc., which thoroughly researched the scientific literature to identify and better understand the genes associated with the brain reward pathways,” states Dr. Keri Donaldson, lead author of the recently published study and founder and CEO of Prescient Medicine.

“Using those data, we identified candidate genes to act as markers and then validated that those genes had predictive value in a 67-patient study,” Donaldson says. “These findings confirmed what previously published data have shown—that there is a strong genetic component to opioid addiction and, with the right tools, an individual’s risk of opioid dependency can be predicted.”

Using the outcome of the initial study, researchers then conducted a second study where they evaluated 138 patient samples to assess the efficacy of the panel. These data showed that LifeKit Predict can identify—with 97-percent certainty—that an individual has a low likelihood of becoming addicted to opioids. The test also showed an 88-percent likelihood of predicting that an individual has an increased risk for opioid addiction.

In the United States alone, opioid-related hospitalizations cost about $20 billion annually, not to mention other societal costs—and it is estimated that as many as 650,000 people will die over the next 10 years from opioid overdoses.

“The idea that we can predict whether someone will become opioid-dependent based on the things we think we know about an individual’s life or lifestyle, some might argue, is part of the reason we’re in the midst of the biggest public health epidemic in U.S. history,” Donaldson says.

“We think only certain types of people who lead certain types of lifestyles are the ones who will become opioid addicts. But, unfortunately, what this crisis has taught us is that no one is immune, and that opioid addiction is indeed, multifactorial. So, while factors like environment and lifestyle play a role, so do genetics.”

The association between genetics and risk of drug or alcohol addiction or dependency is not new.

Genetic predisposition to addiction is well-established and can be traced back to the 1950’s or 1960’s, Donaldson says. What is new, however, is “with the technology we now have, we can use machine learning or automated intelligence (AI) to identify how these genes may contribute to addiction risk.”

While Donaldson concedes that getting results from a reliable test for predicting addiction will not stop the addict from using, he believes LifeKit is a beginning toward making a dent in the opioid epidemic.

“LifeKit Predict aims to prevent addiction before it starts by evaluating the genes we’ve identified that are involved in the brain reward pathways,” he says. “While this test helps us better understand how genetics might impact individual opioid addiction risk, it is just one of many factors.”

“While the use of predictive, personalized medicine to determine opioid addiction risk is still a relatively new science, I am incredibly encouraged by the data and the potential of genetic tools like LifeKit Predict to help prevent opioid abuse and ultimately save lives,” says Dr. Joseph Garbely, medical director and vice president of medical services at Caron Treatment Centers.

Dr. Forest Tennant, a physician at the Veract Intractable Pain Clinic in West Covina, Calif., who collaborated with AutoGenomics on this research, adds: “Test results show that many of the genetic mutations identified in this test panel—namely receptors and transporters—are present in most chronic pain patients and are helpful in identifying those subjects at risk for addiction. This test panel should become an indispensable tool in pain management and addiction risk assessment.”

Yale University professor Joel Gelertner, an expert in genetics and addiction, has expressed concerns in at least one media story about LifeKit, however. He noted the small sample size studied, and was skeptical that the reported predictive power of the kit would hold up when applied to larger datasets.