TY - JOUR
T1 - Medical records-based chronic kidney disease phenotype for clinical care and “big data” observational and genetic studies
AU - Shang, Ning
AU - Khan, Atlas
AU - Polubriaginof, Fernanda
AU - Zanoni, Francesca
AU - Mehl, Karla
AU - Fasel, David
AU - Drawz, Paul E.
AU - Carrol, Robert J.
AU - Denny, Joshua C.
AU - Hathcock, Matthew A.
AU - Arruda-Olson, Adelaide M.
AU - Peissig, Peggy L.
AU - Dart, Richard A.
AU - Brilliant, Murray H.
AU - Larson, Eric B.
AU - Carrell, David S.
AU - Pendergrass, Sarah
AU - Verma, Shefali Setia
AU - Ritchie, Marylyn D.
AU - Benoit, Barbara
AU - Gainer, Vivian S.
AU - Karlson, Elizabeth W.
AU - Gordon, Adam S.
AU - Jarvik, Gail P.
AU - Stanaway, Ian B.
AU - Crosslin, David R.
AU - Mohan, Sumit
AU - Ionita-Laza, Iuliana
AU - Tatonetti, Nicholas P.
AU - Gharavi, Ali G.
AU - Hripcsak, George
AU - Weng, Chunhua
AU - Kiryluk, Krzysztof
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85104344566&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85104344566&partnerID=8YFLogxK
U2 - 10.1038/s41746-021-00428-1
DO - 10.1038/s41746-021-00428-1
M3 - Article
AN - SCOPUS:85104344566
SN - 2398-6352
VL - 4
JO - npj Digital Medicine
JF - npj Digital Medicine
IS - 1
M1 - 70
ER -