AI and live network data offer reliable 14-day Covid-19 admissions forecast

A breakthrough trial across Swedish hospitals, led by Ericsson, Telia and Sahlgrenska University Hospital, has leveraged AI and mobile network data to deliver an accurate forecasting model of near-term COVID-19 patient admissions 14 to 21 days into the future.

Forecasting the daily number of near-term COVID-19 admissions has been a vital part of hospital planning this past year. In a recent breakthrough trial, Ericsson has partnered with Telia and Sahlgrenska University Hospital to develop an innovative way to reliably predict the number of near-term COVID-19 admissions as far as 14 to 21 days into the future. The forecasting accuracy has been evaluated by the hospital planning experts and confirmed to provide significant value.

The data-driven insights model leverages Ericsson’s AI modeling technologies together with hospital admission data and anonymized, aggregated mobile crowd movement data from Telia. This has been a key information source in informing the forecasting models at both Sahlgrenska University Hospital and Södra Älvsborgs Hospital in Västra Götaland, Sweden.

To create the insight models, Ericsson’s leading AI experts first developed and tuned predictive models through a training phase, to identify how each predictive model performed across various forecasting windows. Once the best performing predictive models and settings were identified by AI experts and Sahlgrenska University Hospital, Ericsson’s experts then retrained the models using all data, producing a reliable 14- to 21-day COVID-19 admissions forecast, which could be delivered every week. The predictive models are also tuned to consider external factors such as vaccination data.

The forecast indicators produced throughout the trial have been considered, combined and weighed against multiple other sources of information to form the basis of the hospitals’ COVID-19 prognoses. Other relevant indicators are the fraction of positive PCR-tests, the change in commute patterns (using data from the Västtrafik transport authority) and the change in the overall mobility in heavy-traffic areas such as shops and offices.

The collaboration between the partners began in September 2020. The initiative was then expanded to include the local municipality Region Västra Götaland and Södra Älvsborgs Hospital in spring 2021.

Thomas Brezicka, Chief Medical Officer, Sahlgrenska University Hospital, says: ”The collaboration has enabled the development of a reliable tool for short term prediction of admissions to the hospital due to COVID-19 and has been vital for our planning of effective resource allocation to ensure that all patients receive the care needed.”

Kristofer Ågren, Head of Data Insights, Telia, says: “I’m very proud to see how our data and insights can be used to provide support to Sahlgrenska University Hospital and other hospitals, ultimately ensuring a better healthcare experience for patients. It’s technology at its very best!”

Peter Laurin, Head of Managed Services, Ericsson, says: “In this past year, our hospitals and healthcare resources have been stretched to their very limits, and it’s been important that we join to support in every way we can. This trial has demonstrated the lasting impact that disruptive technologies such as AI can have across our societies. We have been proud to partner in this trial contributing with our AI tools and expertise.”

 

Read more about how Ericsson is using AI to enable more intelligent networks.