German pharmaceutical company Boehringer Ingelheim and US-based healthcare research company Carelon Research have completed the validation study of the Klinrisk model.

Klinrisk is an artificial intelligence (AI) and machine learning (ML)-driven tool designed to predict the risk of chronic kidney disease (CKD) progression in all stages of the disease.

The validation study was conducted using data from a diverse population of more than four million adults in the US.

In the study, the Klinrisk model showed more than 80% accuracy in predicting CKD progression over a five-year period, according to the German pharmaceutical company.

Boehringer Ingelheim Pharmaceuticals cardio-renal-metabolism and respiratory medicine clinical development and medical affairs vice president Mohamed Eid said: “Effective disease-modifying therapies rarely reach the people with chronic kidney disease who are most likely to need them, due to limited recognition of early-stage disease.

“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.”

The Klinrisk model was designed to predict the risk of CKD progression, which is defined as either a 40% decline in estimated glomerular filtration rate (eGFR) or kidney failure.

It evaluates the risk using age, sex and routinely collected laboratory data, including complete blood cell counts, chemistry and metabolic panels and urinalysis.

The study required at least one serum creatinine measurement and excluded patients with less than one year of follow-up with continuous insurance enrollment after initial data was collected.

Carelon provided data from a diverse population of 4.6 million US adults in commercial, Medicare and Medicaid insurance plans for the validation study of the Klinrisk model.

The model accurately predicted CKD progression in 80 to 83% of people over a period of two years and in 78 to 83% of participants over five years, based on the insurance provider.

With urinalysis data, the model precisely predicted CKD progression in 81 to 87% of individuals over a period of two years and 80 to 87% of individuals over five years.

Klinrisk scientific founder Navdeep Tangri said: “The model is a useful tool to help identify people with high-risk CKD early before kidney function is lost. We look forward to advancing this model as we aim to bring it to US physicians.”

Carelon Research president Mark Cziraky said: “As this model requires only demographic information and routine laboratory data, it may have the potential for broad application in a clinical setting to help identify individuals at risk of CKD progression. Earlier identification of CKD risk could help to inform and improve care decisions.”