Researchers have developed a new artificial intelligence-based algorithm that can help predict which Covid-19 patients have a higher risk of developing acute kidney injury (AKI) requiring dialysis.

According to an official release, preliminary reports have suggested that acute AKI is common in patients with Covid-19.

Researchers at the Icahn School of Medicine at Mount Sinai have developed a model based on machine learning using data from more than 3,000 hospitalised patients with Covid-19.

The model has been trained to predict AKI that requires dialysis.

“Only information gathered within the first 48 hours of admission was included, so predictions could be made when patients were admitted,” the report said.

The model showed high accuracy (AUC of 0.79) and features that are important for prediction, including blood levels of creatinine and potassium, age, and vital signs of heart rate and oxygen saturation.

"A machine learning model using admission features had good performance for prediction of dialysis needs. Models like this are potentially useful for resource allocation and planning during future Covid-19 surges," said co-author Lili Chan, MD, MS. "We are in the process of deploying this model in our healthcare systems to help clinicians better care for their patients."

AKI is one of the risks that Covid-19 patients face. For instance, a study published in the Journal of the American Society of Nephrology last month found that coronavirus positive patients who are hospitalised may face kidney damage or acute kidney injury (AKI).

The study noted that Covid-19 patients can face increased levels of soluble urokinase receptor (suPAR), an immune-derived pathogenic protein that is strongly predictive of kidney injury.

Results from the current study are to be presented online during ASN Kidney Week 2020 Reimagined.

Related Topics
comment COMMENT NOW