A new tool uses the details of a person’s medical records to assess how likely they are to catch COVID-19 and die

Technology correspondent
@rowlsmanthorpe

At 1, England will add another 7 million people to the screening list after it is determined that COVID-19 is a potentially serious risk

You have been identified by a new algorithm that takes multiple factors into account and will receive a letter from the NHS in the coming days

Some have already received a coronavirus sting, but the 800 or so000 who failed to do so will be placed on the vaccine’s priority list

This algorithm simply uses the details of your medical records to assess how likely you are to catch COVID-19 and die

This information will be reviewed and given a score of 100: A high score means you are more likely to get COVID-19 and die A low score means you are less likely

The people with the highest scores will be added to the screening list and prioritized for vaccination

Whether you get one of the higher scores depends on your personal characteristics such as age, gender, or ethnicity, as well as your weight compared to your height

Older people are known to be more susceptible to COVID-19 Men are more vulnerable, so they score higher, the same goes for ethnicity

Other factors that will increase your score include whether you smoke, are homeless, or whether you are taking certain types of medication

For example, some cancer patients were not included in the first screening list. This algorithm can go through the NHS database, select these people, and then mark them for vaccination

Poverty is known to be linked to more severe consequences of COVID-19, and this algorithm includes a measure of disadvantage based on your zip code

A whole range of measures are being taken, including unemployment, car and home ownership, and household overcrowding Then the poverty in your region is calculated

For this you will receive a score that will be used in your final score when it is calculated at the end

You may be wondering exactly how these results are calculated. That’s a much bigger question: Suffice it to say, this is extremely difficult math

Fortunately, all the details of the model are published so that people who understand the math can go through it, and if you aren’t, you can get an idea for yourself using this online calculator that uses the algorithm, to estimate your score based on the information you give him

There are concerns, of course, but before we dive into these, it is worth pausing to reflect on how startlingly complicated this is

The algorithm is not just trying to predict who will die of COVID-19 if they catch it, which we unfortunately know all too much about by now, it tries to predict who will catch COVID-19 in the first place

Unless the Oxford University scientists who developed it invented time travel at the same time, the results will inevitably be inaccurate, especially since it does not include some factors that clearly put you at a higher risk of contracting COVID-19, such as cast

As a result, there is a high likelihood that some people will jump into the queue at actually low risk

After the chaos caused by trying to algorithmically mark last year’s high school graduation, the idea of ​​an inaccurate algorithm selecting people to be vaccinated could send chills down your spine

But if we only focus on its drawbacks, we might overlook its advantages: its ability to process more data than a human could ever be

Algorithms are not inherently bad, they are just tools – and like any tool, they can be used badly or well. This could help the NHS select people at risk from the population, but it’s only as good as the data that is enter the NHS

Perhaps the biggest challenge is not doing it, but explaining it to patients who receive (or don’t receive) an invitation as a result

© 2021 Sky UK

Shield

World News – UK – COVID-19: How Oxford University’s Algorithm Decides Who Should Be Shielded

Source: https://news.sky.com/story/covid-19-how-the-oxford-university-algorithm-decides-who-should-be-shielding-12220116