Using Data to Identify Potential Upcoming COVID-19 Surges

A recent study conducted by investigators from Kaiser Permanente describes a potential way that health systems would be able to employ routine clinical data to identify the onset of an upcoming surge in COVID-19 cases 6 weeks in advance.

Results from the study were published in the journal BMJ Open.

“Over the course of 2020, COVID-19 surprised us at nearly every turn, making longer-term predictions of its impact on our patients, health system, and communities extremely challenging,” Vincent Liu, lead author on the study said. “At the same time, shorter-term predictions — looking only 1 to 3 weeks out — left little time to respond adequately.”

For the study, the team of investigators tested dozens of data elements that they gathered from an electronic heath record system to try and find any elements which may point to an impending increase in COVID-19 hospital admissions.

The team also looked at seasonal surges in cases of influenza since 2015. They eventually ended up with 10 indicators and determined how many weeks of lead time they would be able to provide health systems and community officials.

They called the framework the COVID-19 HotSpotting Score (CHOTS) and it included 4 major variables and 6 minor variables. These variables included: cough and cold calls, relevant subject headers from patient emails, positive COVID-19 test rates, and current COVID-19 hospital census.

Findings from the study showed that CHOTS allowed the investigators to identify an upcoming surge in COVID-19 cases as much as 6 weeks in advance.

The team believes that public health officials and health systems could use this information to boost local testing, expand contact tracing, adjust policy measures and prepare for the anticipated surge.

“The development of CHOTS is an inspiring example of how Kaiser Permanente’s integrated care delivery system and robust research capabilities can come together to provide the greater community with vital public health tools,” Stephen Parodi, a co-author on the study said. “What is even more impressive is that this work was carried out while our medical centers were caring for large numbers of COVID-19 patients. Our researchers worked alongside operational leaders to better prepare our management of future surges.