RenalytixAI plc, an artificial intelligence-enabled in vitro diagnostics company, focused on optimizing clinical management of kidney disease to drive improved patient outcomes and lower healthcare costs, announced that results of a clinical validation study have undergone peer-review and have been accepted for publication in the American Society of Nephrology Journal, Kidney360.
Recommended AI News: CommerceBlock Introduces Cloud Storage Integration For Mainstay Attestation Service
The published manuscript titled, “Validation of a machine-learning-derived prognostic test (KidneyIntelX) integrating biomarkers and EHR data to predict longitudinal-kidney outcomes,” is available through the Early Access format of the American Society of Nephrology journal.
The study provides details of the primary analysis and numerous sub-analyses which demonstrate robust performance of the KidneyIntelX test in the two clinical contexts. These validation results complement the multi-center validation study in patients with prevalent diabetic kidney disease previously reported (https://www.medrxiv.org/content/10.1101/2020.06.01.20119552v3).
Recommended AI News: Fujitsu And NetApp Introduce Data Management Infrastructure For HPC
The primary objective of this validation study was to demonstrate if the KidneyIntelX artificial intelligence-enabled algorithm was able to predict which patients are at highest risk of adverse kidney outcomes with more accuracy than the existing standard of care. The optimized KidneyIntelX assay, combining sTNFR1, sTNFR2 and KIM-1 together with clinical data from electronic health records, achieved a PPV of 62%in the top 15% highest risk of the T2D population vs. 46% as classified by the clinical model (p<0.01 for comparison). Likewise, in the Apolipoprotein L1 high-risk (APOL1) genotype cohort, the PPV of KidneyIntelX was 62% in the top 15% highest risk of APOL1-HR population vs. PPV of 39%, as classified by the clinical model, (p<0.01 for comparison). The study included 871 patients with Type 2 diabetes and 498 patients of African Ancestry with APOL1 high-risk genotypes (i.e., one copy of the genetic risk variant on both chromosomes).
Better risk stratification tools are needed to facilitate the application of novel treatments for DKD and CKD in patients with relatively preserved kidney function. Earlier identification of high-risk patients should allow for the improved ability to slow progressive decline in kidney function before patients reach late stages of CKD and need a kidney transplant or dialysis.
Recommended AI News: Azure DevSecOps Jumpstart Now Available In The Microsoft Azure Marketplace
Comments are closed, but trackbacks and pingbacks are open.