A new validation study regarding the Klinrisk model—a machine-learning tool developed to predict the risk of chronic kidney disease (CKD) progression—has been conducted by Boehringer Ingelheim and Carelon Research. The novel artificial intelligence (AI) model was able to predict disease progression in over 80% of participants at all stages of disease over a five-year period, based on data from a diverse population of over four million adults in the USA.
Presenting the data at the American Society of Nephrology (ASN) Kidney week meeting, Mohamed Eid, vice president of clinical development and medical affairs at Boehringer Ingelheim said that “effective disease-modifying therapies rarely reach the people with CKD 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 risk of CKD progression, which could assist with earlier diagnosis and treatment”.
The data used for the validation study was provided by Carelon Research from a diverse population of adults in the USA that were enrolled in commercial, Medicare and Medicaid insurance plans, and were used to assess the Klinrisk model and whether it was able to predict the risk of CKD progression. The data conveyed that it was able to do so in 80–83% of individuals over two years, and in 78–83% of individuals over five years, depending on the insurance provider. The model’s predictions were also correct for 81–87% of individuals when urinalysis data was available.
“The model is a useful tool to help identify people with high-risk CKD early, before kidney function is lost,” said Navdeep Tangri, scientific founder of Klinrisk. “We look forward to advancing this model as we aim to bring it to physicians in the USA.”
Mark Cziraky, president of Carelon Research, added that “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.”