Boehringer Ingelheim Pharmaceuticals, along with Carelon Research, has carried out a validation study of a new artificial intelligence (AI)-driven tool for chronic kidney disease (CKD).

Known as the Klinrisk model, the tool is intended for predicting the risk of CKD progression at all stages of the disease.

It leverages machine learning for assessing risk using sex, age and routinely collected laboratory data, such as chemistry and metabolic panels, complete blood cell counts and urinalysis.

This model achieved an accuracy of over 80% in forecasting CKD progression over five years using data from a diverse population of more than four million adults in the US.

The validation study utilised data supplied by Carelon Research, encompassing a diverse group of 4.6 million American adults who were enrolled in commercial, Medicare and Medicaid insurance plans.

Depending on the insurance provider, the model could accurately forecast CKD progression in 80%-83% of individuals within a two-year timeframe and in 78%-83% of individuals over five years.

On the availability of urinalysis data, it correctly predicted CKD progression in 81-87% of individuals over a two-year period and in 80-87% of individuals over five years.

Boehringer Ingelheim Pharmaceuticals cardio-renal-metabolism and respiratory medicine clinical development and medical affairs vice-president Mohamed Eid said: “This model may have the potential to help healthcare professionals better identify patients at risk of CKD progression using simple lab results.

“Physicians need novel tools to evaluate the risk of CKD progression, which could assist with earlier diagnosis and treatment.”