Researchers at Tufts Medical Center in the US have developed a model that can accurately predict the short-term risk of kidney failure in patients with moderate to severe chronic kidney disease.

The model includes factors such as age, sex, estimated glomerular filtration rate, albuminuria, serum calcium, serum phosphate, serum bicarbonate and serum albumin.

Results from a validation study have shown that the new model was more accurate in predicting short-term risk of kidney failure compared to a simpler existing model that included age, sex, estimated glomerular filtration rate and albuminuria.

To develop the prediction model and validate it, researchers analysed laboratory data from two independent groups of Canadian patients with moderate to severe chronic kidney disease who were referred to nephrologists between April 2001 and December 2008.

The development group included 3,449 patients (386 with kidney failure) and the validation group included 4,942 patients (1,177 with kidney failure).

According to the study authors, the model uses routinely available laboratory data and can predict the short-term risk of kidney failure with accuracy.

In addition, it could be easily implemented in a laboratory information system or an electronic health record.