Northwell Health Gives Away Predictive Algorithm Correlating Web Traffic with Actual COVID-19 Cases

Northwell Health Gives Away Predictive Algorithm Correlating Web Traffic with Actual COVID-19 Cases TrialsiteN

Northwell Health, New York State’s largest healthcare system, developed a first-of-its-kind predictive tool that actually anticipates spikes in COVID-19 cases at its many hospitals by mining user data patterns from its Northwell.edu website. The two-week advance warning system, created just over the summer by the healthcare system’s customer insights group in collaboration with information technology and clinical teams after the health system (and all of New York) was impacted heavily during the first wave of the pandemic. Overall, Northwell Health has treated 85,000 COVID-19 patients, including 16,000 hospitalized patients between March and Labor Day last year—more than any health system in the United States. The advanced warning source code will be given away to other health systems gratis.

The App: Help Prepare for Future Surges

By collecting 15 different indicators from the Northwell.edu website, the source code fees the data into a machine learning algorithm to recognize patterns in website traffic, including data, such as emergency department wait time searchers to physician page clicks. This results in a rolling two-week forecast that to date has closely mirrored real world case load. The hypothesis: this app can help clinical teams prepare for future surges.

How does it Work?

The Northwell.edu indicators, randomized for privacy, create a composite characteristic of each day’s web traffic, which translates into the “public mood” of the website. Launched back in September, 2020, the COVID-19 prediction algorithm dashboard is combined with a number of other innovative systems the health system’s personnel use to track the number of patients and types of symptoms that go through the health system.

According to their press release this algorithm works because its’ predictive model is based on over 20 million pageviews since the first week of March combined with geographic concentration of its 19 hospitals, 800 outpatient facilities and 52 urgent care centers across New York City, Long Island and Westchester. Teams here have fact checked output which correlate closely with the number of cases seen systemwide.

Executive Point of View

Ramon Soto heads marketing and communications for the sprawling New York-based health system. In a recent press release, Mr. Soto, senior vice president and chief marketing and communications officer, shared, “We found a very strong relationship with website activity to in-facility COVID-19 patient two weeks later. This is an important development in the fight against COVID-19 and Northwell wants to share this game-changing tool, with the world.”

While Eric Cruzen, MD, chief medical informatics office of the Emergency Medicine Service Line at Northwell health and chairman of the Emergency Department at Lennox Greenwich Village in Manhattan shared “COVID-19 has really pushed us forward in the usage of real-time data.” Dr. Cruzen’s role and responsibility leads him to “worry most about an uptick in viral syndrome presentation in our emergency departments, from fevers to low oxygen levels We see those numbers in real time. I also pay attention to laboratory testing and because our health system is so large we can draw real conclusions from the data. But we have to be proactive instead of reactive. The new dashboard is predictive and it is amazing. We use every day to keep our finger on the pulse of the community.”

Download the Northwell Code

If you are interested in learning more about Northwell’s COVID-19 prediction algorithm, follow the link here.