By combining a range of public and private information, a small startup claims to be able to predict COVID-19 hot spots at the neighborhood level in one week – with 92% accuracy.
Driving the news: The startup, Data Driven Health, made a version of its flu and COVID prediction model available for free on Wednesday, offering data for the neighborhood level.
Stay on top of the latest market trends and economic insights with Axios Markets. Sign up for free
Why does it matter: Assuming the company’s flemish model is consistently accurate, governments and healthcare systems can use this data to define policies and allocate resources, while individuals can use them to assess the personal risk of planned outings.
How it works: Fludemic receives a variety of data on a daily basis using a combination of clinical data, socioeconomic indicators and factors such as mask policy and mobility trends.
Yes but: Although the model is considered 92% accurate in detecting hot spots, it is somewhat less accurate when looking at sparsely populated areas or predicting death rates.
Between the lines: The company started working on a flu prediction model last year, but quickly switched to COVID-19 as soon as the pandemic began.
-
While neighborhood data is being made publicly available, Data Driven Health has a premium product aimed at governments and healthcare systems that uses more types of data and offers forecasts down to the block level.
The big picture: Others used a combination of technology and data to map disease. Google, for example, had a flu tracker that aimed to predict flu trends using search queries. This effort was ended in 2015 amid criticism. More recently, smart thermometer maker Kinsa has detected flu outbreaks.
What is the next: In the long run, the company hopes to be able to update its models even more frequently, as well as address other types of health problems.
Did you like this article? Get more from Axios and subscribe to Axios Markets for free.