With limited supplies of COVID-19 vaccines now available,states are scrambling to decidewho should be the first to take the blows. But in many cases, this issue is resolved on the basis of loosely labeled groupings of populations at risk, such as “the elderly” or “essential workers”. While it might sound simple, this approach is shortsighted, as it disregards the incrediblycomplex mix of factorsthat put people at greater health risk and has been shown to lead to increased hospitalization and death rates from COVID-19.
Accurate determination of health risks should be the foundation of a successful vaccination effort. Otherwise, scarce resources will be wasted on those who need them least while blocking access to vaccines for the most vulnerable.
How should states accurately identify those most at risk? They must have a way not only to analyze basic demographics, but also to take into account underlying health conditions, social and environmental determinants of health, and the latest research into the mechanisms of the coronavirus.
For this difficult but critically important task, States must heed the adviceprimary care physicians and researcherswho work tirelessly to solve this public health challenge. Many of them say the best tool available to us is machine learning.
Machine learning harnesses all available data and can detect important hidden patterns that would otherwise go unnoticed and alert us to the increased needs of people who might otherwise fall through the cracks. I saw this firsthand in arecent projectinvolving my data science company, Cogitativo, and insurer Blue Shield of California. As the pandemic began, Blue Shield of California stepped up and sought to provide personalized health advice and support services to its members most vulnerable to COVID. The insurer hired us to identify these vulnerable members.
Cogitativo has built a machine learning platform that brings together factors on an individual’s health history (specifically, whether the individual has a specific high-risk underlying condition) combined with social, environmental conditions. and the most up-to-date medical literature on COVID-19 and other infectious diseases. These factors predict the risk of having adverse health effects from COVID-19 infection.
Many of the results were surprising. For example, the risk scoring tool found that people who did not live near a grocery store were at increased risk of ending up in hospital, on a ventilator, or even dying from COVID-19. Another finding was that people who had experienced serious mental health issues were at higher risk. Based on this and other information, Blue Shield of California has provided various services to its members, including free food delivery, drug delivery, telemedicine, and home clinic visits.
The lesson from our project in California was clear: relying only on age or making a judgment that employees in a particular industry are at greater risk will lead to neglect and unnecessary or worse endangerment of populations. vulnerable.
This imperfect approach to allocating scarce vaccine supplies could exacerbateinequalities that have already devastated communities of colorduring the pandemic. Latinxes and African Americans in the United States werethricemore likely to contract the virus and twice as likely to die from the virus than the corresponding white populations. We cannot, for example, ignore an important risk factor such as housing density, which is much higher in urban communities. The vaccine distribution effort must play a role in reducing these disparities and not in their widening.
Failure to prioritize the most vulnerable for immunization will result in preventable deaths. As someone who has suffered the loss of their family to preventable health events, I call on States to act now to strengthen their vaccine distribution strategies. The virus breaks in again. In recent weeks, hospitalizations in the United States have skyrocketedrecords, daily reported cases explodedold previous records, and there wasthree consecutive days of more than 2,500 deathsfor the first time. In addition, public health officialsWarningthat some of the darker days of the pandemic are ahead.
States must use the most advanced technological tools at their disposal. Machine learning provides a fair, accurate, and rapid ability to allocate our valuable vaccine supplies. Using science and data-driven decision making can help ensure states reach the right people at the right time – and that no American is left behind.
Gary Velasquez is the co-founder and CEO of Cogitativo, a data science company.
More opinion of Fortune:
- Big Pharma’s new CEOs must step up efforts to erase inequalities in access to medicines
- Can Joe Biden unite America? The answer lies in his past
- With COVID raging, why do we still play college basketball?
- Companies that talk about diversity are more likely to walk
- How Biden can prevent China from getting its hands on sensitive military technology