CAN the right words convince someone to donate their blood? An initiative in New York has turned to machine learning to figure out who is most likely to give blood - and how to encourage them to do so more frequently.
The project is aimed at improving the turnout of African Americans, who are disproportionately less likely to donate or become regular donors. Though race is not relevant for standard blood transfusions, type B blood is more common in African American people. Also, ethnicity may help provide a match for blood transfusions to people with sickle cell disease, a condition that is seen more often in African Americans.
"Minorities provide blood that's needed for specific patient populations," says Beth Shaz, chief medical officer at the New York Blood Center. "With the development of this tool, we can create messages tailored for that individual."
To find out who to reach out to, the blood centre teamed up with Hindsait, an AI start-up in Englewood, New Jersey. Hindsait combed through more than a million donation records from the last 10 years to develop an algorithm that could identify telltale signs that someone might return to donate again. Criteria such as the number of days since their last donation, whether or not they were eligible to donate at the time, and their age were taken into account.
Starting on 1 February, the blood centre will use this data to choose who to contact and what to say – a strategy reminiscent of Barack Obama's 2012 presidential campaign, which sent different emails to prospective funders based on their age and gender. For example, younger people might receive text messages rather than emails. Messages to African Americans will emphasise the particular importance of blood donation for their community.
This article appeared in print under the headline "Big data aims to boost New York blood donations"
- New Scientist
- Not just a website!
- Subscribe to New Scientist and get:
- New Scientist magazine delivered every week
- Unlimited online access to articles from over 500 back issues
- Subscribe Now and Save
If you would like to reuse any content from New Scientist, either in print or online, please contact the syndication department first for permission. New Scientist does not own rights to photos, but there are a variety of licensing options available for use of articles and graphics we own the copyright to.
