Northwell website patterns predict COVID-19 caseload

Northwell Health announced today that it has developed a predictive tool that can anticipate a spike in COVID-19 cases at its hospitals by mining user data patterns from its Northwell.edu website. With the pandemic still raging worldwide, Northwell plans to give away the source code to other health systems.

The two-week advance warning system was created this summer by the customer insights group, in collaboration with information technology and clinical teams in the wake of the COVID-19 surge that struck New York State's largest health system last spring. Northwell Health treated nearly 85,000 COVID-19 patients, including 16,000 hospitalized patients between March and Labor Day – more than any health system in the U.S., the system said.

WHAT'S THE IMPACT?

Northwell's new digital dashboard collects 15 different indicators from its website and feeds them into a machine learning algorithm to recognize patterns in website traffic, which includes everything from emergency department wait time searches to physician page clicks. The result is a rolling two-week forecast that has closely mirrored caseload to date and is expected to help clinical teams prepare for future surges.

These indicators – which are anonymized for privacy – create a composite characteristic of each day's web traffic, which translates into the "public mood" of the website. The COVID-19 prediction algorithm dashboard launched at the beginning of September and joined a number of other systems that Northwell uses to track the number of patients and types of symptoms that go through the health system.

The predictive model works, the system said, because of the traffic volume of its website (more than 20 million page views since the first week of March) coupled with the geographic concentration of its 19 hospitals, 800 outpatient facilities and 52 urgent care centers across New York City, Long Island and Westchester. Its numbers have been fact-checked and correlate closely with the number of cases seen systemwide.

Being able to anticipate the next COVID-19 surge has potentially huge implications for staffing, supplies and patient handling, and could make room for the expected influx of cases. Northwell said it has made significant investments in protective gear, life-saving equipment, testing and the physical expansion of facilities as the first wave hit in the spring. Taking those lessons and plugging in the ability to see another wave coming could flatten the curve before it becomes a wave.

Health systems interested in learning more about Northwell's COVID-19 prediction algorithm can do so here.

THE LARGER TREND

Northwell is no stranger to using technology to address the coronavirus pandemic. In a HIMSS20 Digital presentation from April, Dr. Zenobia Brown, medical director and vice president of population health management at Northwell, said the system has deployed some new technology, but has also reimagined technology it had already been using to better tackle pandemic-related challenges.

On the ambulatory care side, Northwell has been using tech to connect the community to existing information and resources, with a focus on delivering the current information and guiding users through the material. A dedicated resource center on the system's website has been channeling people to the content that will be the most effective, and guiding patients to information that is the most appropriate for their specific situation.

According to Johns Hopkins data, there had been 7,191,519 cases of COVID-19 in the U.S. as of Wednesday morning, with 206,005 deaths, the most of any nation. New York has been the hardest hit in terms of the death count, which stands at 33,144.

Twitter: @JELagasse
Email the writer: jeff.lagasse@himssmedia.com