New Algorithm Identifies COVID-19 Patients Who Will Require Intensive Care or Ventilation With 90% Accuracy

A new algorithm can predict how many patients will need intensive COVID-related healthcare.

The innovative algorithm developed by researchers from the University of Copenhagen (Copenhagen, Denmark) will help alleviate pressure whenever hospitals are confronted by new waves of COVID. It could provide valuable knowledge when it comes to prioritizing caregivers and ventilators in individual hospitals, and save lives. The algorithm can predict the course of COVID patients' illnesses in relation to how many of them will be highly likely or unlikely to require intensive care or ventilation. This is important for the allocation of staff across hospitals.

Illustration

The new algorithm is based on health data from 42,526 patients who tested positive for the coronavirus between March 2020 and May 2021. It uses individual patient data, including information about a patient’s gender, age, medications, BMI, whether they smoke or not, blood pressure and more. This allows the algorithm to predict how many patients, within a one-to-fifteen day time frame, will need intensive care in the form of, for example, ventilators and constant monitoring by nurses and doctors.

Traditionally, researchers have used regression models to predict COVID-related hospital admissions. However, these models haven’t taken individual disease histories, age, gender and other factors into account. In fact, the algorithm provides extremely accurate predictions for the likely number of intensive care patients for up to 10 days.

As such, our algorithm has the potential save lives," explained Stephan Lorenzen, a postdoc at the University of Copenhagen’s Department of Computer Science. "We make better predictions than comparable models because we are able to more accurately map the potential need for ventilators and 24-hour intensive care for up to 10 days. Precision decreases slightly beyond that, similar to that of the existing algorithmic models used to predict the course of illness in COVID cases."

Related Links:
University of Copenhagen