A genetic and clinical risk factor algorithm to aid in identifying new cases of chronic kidney disease from the general population
Kim, S.; Ioannidis, J.; Rodwell, G.
Show abstract
One of the biggest challenges in treating chronic kidney disease (CKD) is that 80 - 90% of people with this disease are undiagnosed, and thus do not access healthcare promptly. The problem arises because early stage CKD has no overt symptoms and the current policy is to perform diagnostic tests (e.g. glomerular filtration rate and urinary albumin to creatinine ratio) only when accompanied by risk factors such as old age, hypertension and diabetes. Genetic testing may be useful to identify those most likely to have CKD and who therefore may benefit from screening. This work describes the development of an algorithm termed RICK (for RIsk for Chronic Kidney disease) that employs a polygenic risk score for CKD plus clinical risk factors to identify people at risk. In data from the UK biobank, those in the top decile of RICK have a 4.4-fold increased risk of CKD, and about 34% of all those with CKD are included in this decile. Using RICK to selectively test those in the general population with highest risk may help in early identification of CKD and thereby facilitate early access to renal healthcare. Lay SummaryOne of the biggest challenges in renal health is that 80 - 90% of people with Chronic Kidney Disease (CKD) are undiagnosed, and thus do not access healthcare promptly. The problem arises because early stage CKD has no overt symptoms and the current policy is to perform diagnostic tests (e.g. glomerular filtration rate and urinary albumin to creatinine ratio) only when accompanied by risk factors such as old age, hypertension and diabetes. This work describes the development of an algorithm termed RICK (for RIsk for Chronic Kidney disease) that employs a genetic test for CKD plus clinical risk factors to identify people at risk and who therefore may benefit from screening. Those in the top ten percentile of RICK have a 15-fold increased risk of stage 3 CKD. Diagnostic testing of the top decile would capture about 43% of the undiagnosed stage 3 CKD cases. Thus, using RICK to selectively test those with highest risk could have an immense impact on renal health by facilitating early identification of CKD and thereby enabling access to healthcare.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- External validation of six clinical models for prediction of unknown chronic kidney disease in a German population 97%
- Trajectories of atherosclerotic cardiovascular disease risk scores as a predictor for incident chronic kidney disease 94%
- Comparison of the prevalence and associated factors of chronic kidney disease diagnosed by serum creatinine or cystatin C among young people living with HIV in Uganda 94%
Similar papers in this journal
- The prevalence of chronic kidney disease in Australian primary care: analysis of a national general practice dataset 97%
- ATP-citrate lyase as a therapeutic target in chronic kidney disease: a Mendelian Randomization analysis 96%
- A functional landscape of chronic kidney disease entities from public transcriptomic data 93%
Similar papers in this journal
- Comparison of low eGFR prevalence and prediction for mortality using 2009 and 2021 CKD-EPI equations in Mexican adults 95%
- Circulating Plasma Biomarkers in Biopsy-Confirmed Kidney Disease: Results from the Boston Kidney Biopsy Cohort 94%
- Impaired incretin homeostasis in non-diabetic moderate-severe CKD 93%
Similar papers in this journal
- Prognostic Utility of Total Kidney Volume for Chronic Kidney Disease Risk Prediction: An Observational and Mendelian Randomization Study 97%
- HBA Copy Number and Kidney Disease Risk among Black Americans: a Longitudinal Cohort Study 95%
- Clonal hematopoiesis of indeterminate potential contributes to accelerated chronic kidney disease progression 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.