Abstract
Chronic Kidney Disease (CKD) represents a slowly progressive disorder that is typically silent until late stages, but early intervention can significantly delay its progression. We designed a portable and scalable electronic CKD phenotype to facilitate early disease recognition and empower large-scale observational and genetic studies of kidney traits. The algorithm uses a combination of rule-based and machine-learning methods to automatically place patients on the staging grid of albuminuria by glomerular filtration rate (“A-by-G” grid). We manually validated the algorithm by 451 chart reviews across three medical systems, demonstrating overall positive predictive value of 95% for CKD cases and 97% for healthy controls. Independent case-control validation using 2350 patient records demonstrated diagnostic specificity of 97% and sensitivity of 87%. Application of the phenotype to 1.3 million patients demonstrated that over 80% of CKD cases are undetected using ICD codes alone. We also demonstrated several large-scale applications of the phenotype, including identifying stage-specific kidney disease comorbidities, in silico estimation of kidney trait heritability in thousands of pedigrees reconstructed from medical records, and biobank-based multicenter genome-wide and phenome-wide association studies.
Highlights
Chronic Kidney Disease (CKD) is associated with a high burden of comorbidities and increased mortality[1,2]
We defined 1136 cases as patients seen by a nephrologist in the Columbia CKD clinic, and 1214 controls as healthy women without knowledge in nephrology to define CKD cases and controls using a known CKD diagnosis undergoing a prenatal visit at Columbia laboratory measurements in combination with diagnosis and University during the same time interval as the cases
Any patient with relevant Electronic health records (EHR) data is dataset, the sensitivity, specificity, positive predictive values (PPV) and NPV of the algorithm staged based on eGFR (G-stage) and albuminuria (A-stage)
Summary
Chronic Kidney Disease (CKD) is associated with a high burden of comorbidities and increased mortality[1,2]. Due to the increasing prevalence, and high costs of renal replacement therapies, CKD already represents one of the most expensive health problems in developed countries[3]. In the United States, an estimated 13.6% of adults have CKD1 and more than 726,331 Americans have endstage kidney disease (ESKD), being dialysis-dependent or having received a kidney transplant[4]. 1.5 times greater in Asian Americans than in Whites/Europeans. Inherited factors, such as APOL1 polymorphisms[5,6] and other genetic factors[7,8], are likely contributing to these disparities. Unlike most other disease states, the onset of kidney disease is often asymptomatic, and the diagnosis is based solely on blood and/
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call