The British government intends to employ AI systems in the review of possible safety concerns for Covid-19 vaccinations. The government of the UK has plans to be ready for a mass vaccination campaign, whenever the vaccines become available, by this coming Christmas. In order for this complex task to be carried out safely and effectively, those who receive the injections must be monitored for potential side effects, something better done with AI.
As cases of the coronavirus spike around the United States, and the globe, heading into the winter season, scientists remain hard at work trying to deliver a vaccine as quickly as possible. A vaccine for Covid-19 will be the result of long work weeks and billions of dollars invested by governments around the globe. However, the first vaccines to be delivered to the public may be less effective and potentially come with more side effects than a typical vaccine, owing to the sheer speed at which the vaccines have been produced.
Vaccine experts warn that come spring, the vaccine situation could be fairly confusing. There could easily be several vaccines to choose from, with varying levels of effectiveness. Moreover, some of the vaccines may suddenly be withdrawn from the market due to the discovery of side effects. According to Dr. Gregory Poland via the New York Times, the Vaccine Research Group director at the Mayo Clinic, it is yet to dawn on many people the complexity and confusion that could happen within the first quarter of 2021. How efficient governments are at managing the rollout of vaccines will have substantial impacts on how soon the pandemic is contained and how soon life returns to normal.
In order to better manage this potentially chaotic and confusing situation, the UK government is employing AI algorithms to track the appearance of any side effects in those initially receiving the vaccines. The vaccines will have gone through extensive testing for both safety and efficacy by the time they are approved for general usage by the UK’s medical regulators. Despite this, the UK government is still operating with caution, aiming to catch signs of potentially harmful side effects as soon as they appear.
According to Fortune, the primary medical regulation body of the UK, the Medicines and Healthcare Product Regulatory Agency (MHRA), is concerned that the current methods of identifying adverse reactions to medical drugs aren’t equipped to handle the upcoming situation. The system could be too slow to report potential safety concerns, overwhelmed by the number of events it must track.
In order to improve the efficiency of the “adverse events” reporting process, the MHRA is using AI to automate many portions of the side-effect detection and reporting system. The MHRA has given approximately 2 million dollars to Genpact, a business process outsourcing firm. Genpact will be tasked with designing machine learning algorithms intended to take in reports regarding side effects and identify any major safety issues. The machine learning algorithms are likely to be classification systems based upon various features of the side-effect reports, like headaches or tiredness. Healthcare providers collect reports of adverse events, gathering data such as the patient’s age and sex, the brand name of the vaccine, time and date of administration, symptoms, medical test outcomes, and laboratory results. These reports are sent to agencies like the MHRA with collect them in databases.
As reported by the Financial Times, the MHRA stated that with typical vaccination campaigns there are somewhere between 50,00 to 100,000 concerning side effects for every 100 million doses of the vaccine, given a six-to-twelve month vaccination timeline.
The use of machine learning algorithms by Genpact and the MHRA to monitor for vaccine side effects is just one example of a larger trend of employing AI to check for possible drug side effects.
According to Healthcare It News, the MHRA says that they are not currently anticipating any specific safety issues relating to Covid-19 vaccines and that the vaccines will have the general safety profile of other, similar vaccines. Explained the MHRA:
“The purpose of the AI tool we are introducing as part of our Yellow Card system is to help us rapidly evaluate such reports after approval, and not as part of the approval process. A COVID-19 vaccine will only be deployed once it has been proven to be safe and effective through robust clinical trials and approved for use by the appropriate licensing authority.”
- Researchers Mimic Sea Slug Strategies in Quantum Material
- Do Conversational Agents Like Alexa Affect How Children Communicate?
- Hobbling Computer Vision Datasets Against Unauthorized Use
- Faisal Ahmed. Co-Founder & CTO at Knockri – Interview Series
- The Shortcomings of Amazon Mechanical Turk May Threaten Natural Language Generation Systems