New algorithm predicts Covid complication risk

An algorithm that can accurately predict the risk of developing severe complications due to Covid-19, including hospitalisation and death, has been developed by Dutch researchers.

The algorithm can be applied to identify persons with highest risks from data in the electronic health records of general practitioners.

The Covid algorithm performed well to predict the risk of severe complications of Covid-19 in the first and second waves of Covid-19 infections in the Netherlands, the team from VU University Medical Center Amsterdam (VUmc) wrote in the peer-reviewed British Medical Journal. The algorithm was developed from a training data set comprising 70 per cent of the patients and validated in the remaining 30 per cent.

Potential predictor variables included age, sex, chronic co-morbidity score based on risk factors for Covid-19 complications, obesity, neighbourhood deprivation score, first or second Covid-19 wave, and confirmation test. The team collected information from a database of Covid-19 diagnoses and co-morbidities in the country.

Some 264 general practitioner practices reported 6,074 Covid-19 cases between April 10, 2020, and January 21, 2021. About 291 patients had severe complications, 181 of these were hospitalised, while 59 were treated in a nursing home and 51 died. According to the researchers, the algorithm can be used to identify persons at especially high risk of developing severe complications based on medical records, which could help prioritise these persons for vaccination. However, they added the caveat that "the regression estimates can and need to be adjusted for future predictions".