GNS Healthcare Blog

GNS Healthcare Blog

When Personalized Medicine Becomes Personal: Using AI to Fight Migraines


Imagine living with pain every day—when a four or five on a ten-point scale is a good day and eight or nine amounts to about a third of your days. Imagine not being able to do the thing you love – travel - because of noises, lights, smells, weather, and sleeping conditions. No more visits to the beach because of heat and bright sunlight. Cancelled plans, countless visits to doctors and emergency rooms, and trying to exist in a controlled environment of low light and minimal noise.

That’s the life my sister lives – a life trying to cope with chronic migraines. And it breaks my heart.

My sister's story is not uncommon. It is a way of life for millions of people every day. In the U.S. alone, more than 38 million people suffer from migraines - two to three million enduring chronic cases. Almost five million people are hit with at least one migraine attack a month and for more than 11 million people, migraines cause moderate to severe disability. The World Health Organization ranks migraines as the 19th most common reason for disability. The disease is three times as likely to impact women than men, with an 18 percent to 6 percent higher prevalence respectively.1

In addition to the social and personal pain is the economic impact. The costs of the condition are staggering.  One study estimates the cost of lost work days in the U.S. to be between $5.6 billion and $17.2 billion a year. People who suffer from migraines use two and a half times the amount of prescription drugs and have six times as many diagnostic tests and services. The average monthly healthcare costs for migraine sufferers is $145 versus $89 for non-sufferers.2


Causes and effective treatments have been elusive

No one has been able to pin down the exact biological causes of migraines, but a common belief is that the disease is a neurobiological disorder – an illness of the nervous system that’s caused by biological factors like genetics and metabolism.3

According to the Mayo Clinic, treatments for migraines fall into two broad categories: pain relieving medications and preventive medications. Pain relievers include acetaminophen, triptans that help blood vessels constrict and block pain pathways, ergots for pain lasting more than 48 hours, anti-nausea medications, opioids, and glucocorticoids. Preventive medications include cardiovascular drugs like beta blockers, anti-depressants, anti-seizure drugs and Botox.4

Watching my sister try to carry on with her professional and personal life while suffering chronic pain has been disheartening to say the least. But there is hope that relief may be on the way for her and other sufferers.  


Therapy breakthrough provides hope

The FDA has recently approved a new drug which helps prevent migraines by targeting a protein called CGRP. Several other pharma companies are close behind with additional treatments that should help those suffering from this debilitating disease.5

Two obstacles stand in the way of progress however. First, the potential demand for new treatments may far outpace the supply of new drugs. My sister has experienced this first hand and has been unable to obtain new drugs. The potential market for these drugs could be much larger than anticipated, as migraine often goes undiagnosed. Some reports estimate that 60 percent of women and 70 percent of men suffering from the condition have never been diagnosed with migraines.6

The second challenge is expected to come from insurance companies who are hesitant to approve reimbursement for the medication, which is priced at close to seven thousand dollars a year or $575 for each monthly dose. Simply being diagnosed by a physician is often not enough to access the newly approved drugs. Patients often have to keep a detailed diary, go through step therapy and ultimately fight for approval.


AI and causal learning can help

Fortunately, more pharma companies are now leveraging AI and machine learning to help overcome these obstacles. This is particularly important as companies grapple with forecasting demand for newly developed therapies.

Causal machine learning, a powerful form of AI, is poised to make a real impact in areas like migraine where there is still much to understand about the disease. By developing causal disease models, biopharma is better able to analyze clinical trial results and extract value from data that often is inconclusive or riddled with confounding factors. These models can identify which patients respond to treatment and explain the crucial cause-and-effect relationships within the data. The result is often the identification of biomarkers for those patients who benefit in relation to the population as a whole.

By better stratifying "homogeneous" populations into subpopulations of patients, pharma can more accurately define the inclusion and exclusion criteria for later phase trials. This allows them to recruit the right patients, increasing the probability of success and providing insights into how the drug will perform in the real world.

Once the drug is in the hands of physicians and patients, real-world data is generated and holds the key to understanding its effectiveness. Analyzing this real-world evidence enables biopharma to further refine subpopulations for whom the drug is beneficial as well as potentially discover new indications for its use. These discoveries can also help develop new treatments for those who do not respond to the original drug.

Developing a comprehensive understanding of the disease and characterizing patients who are likely to benefit, allows bippharma companies to better anticipate demand and provide the therapy for those who need it. Leveraging AI to analyze all the data from the health system level to the biology level will also provide insurance companies with evidence of efficacy which should accelerate reimbursement approval.

We have the data. We have ability to collect more data. We have the technology. Now we need to move the needle to ensure people like my sister are not living according to their pain scale but can receive treatment based on their individual biology. The benefits are admittedly personal, but also universal.


[1] Migraine Statistics, website presented by Health Union

[2] ibid

[3] What Causes Migraines, The Medical Journal, 2014

[4] Migraine, Patient Care & Health Information, Mayo Clinic website

[5] FDA Approves Amgen’s Migraine Drug, by Ellie Kincaid, Forbes, May 17, 2018.

[6] Misdiagnoses and Misconceptions About Migraine, Migraine Awareness Group: A National Understanding for Migraineurs website.

Subscribe to the GNS Newsletter

Recent Posts: