Abstract 066: Association Between Nocturnal Blood Pressure Dipping Magnitude And Chronic Kidney Disease Risk Among Patients With Controlled Office Blood Pressure

Although abnormal diurnal blood pressure (BP) patterns are associated with adverse cardiorenal outcomes, their risks are yet unquantified by BP dipping magnitude. We assessed chronic kidney disease risk across nocturnal BP dipping spectrum among patients with controlled hypertension without prior advanced kidney disease. Ambulatory BP measurements were collected from 995 middle-aged patients with controlled office BP (<140/90 mmHg). The magnitude of dipping was defined as the difference between daytime and nighttime systolic BP divided by daytime systolic BP. Accordingly, patients were categorized as extreme-dipper (≥20%) dipper (10-<20%), non-dipper (0-<10%), or reverse-dipper (<0%). We cross-sectionally analyzed continuous and categorical associations of dipping with albuminuria (urine albumin-to-creatinine ratio ≥30 mg/g) and decreased estimated glomerular filtration rate (<60 ml/min/1.73m 2 ), adjusting for office/ambulatory BP, antihypertensive class, body mass index, total cholesterol, fasting glucose, socioeconomic status, and health behavior. The participants (mean age 60.2 years; 52.9% male) consisted of 13.5% (134 of 995) extreme-dippers, 43.1% (429 of 995) dippers, 34.7% (345 of 995) non-dippers, and 8.7% (87 of 995) reverse-dippers. In reference to dippers, odds ratios (95% confidence interval) for albuminuria were 1.73 (1.04-2.60) in reverse-dippers, 1.67 (1.20-2.32) in non-dippers, and 0.62 (0.38-1.04) in extreme-dippers; this reflects significantly lower risk (0.77, 0.55-0.95) per 10% dipping. Likewise, persons presenting reduced and reverse-directional dipping were at higher risk for decreased estimated glomerular filtration rate: reverse-dippers 2.02 (1.06-3.84); non-dippers 1.98 (1.07-3.08); extreme-dippers 0.69 (0.20-1.17), with lower risk (0.74, 0.22-1.02) per every 10%. In short, monitoring nocturnal BP patterns may identify chronic kidney disease risk otherwise overlooked based on office BP.

Chronic Kidney Disease Risk of Isolated Systolic or Diastolic Hypertension in Young Adults: A Nationwide Sample Based‐Cohort Study

Background Hypertension among young adults is common. However, the effect of isolated systolic hypertension (ISH), isolated diastolic hypertension (IDH), or systolic and diastolic hypertension (SDH) among young adults on chronic kidney disease (CKD) development is unknown. Methods and Results From a nationwide health screening database, we included 3 030 884 participants aged 20 to 39 years who were not taking antihypertensives at baseline examination in 2009 to 2010. Participants were categorized as having normal blood pressure (BP), elevated BP, stage 1 IDH, stage 1 ISH, stage 1 SDH, stage 2 IDH, stage 2 ISH, and stage 2 SDH. The primary outcome was incident CKD. A total of 5853 (0.19%) CKD events occurred. With normal BP as the reference, multivariable‐adjusted hazard ratios (HRs) (95% CIs) for CKD were 1.14 (95% CI, 1.04–1.26), elevated BP; 1.19 (95% CI, 1.10–1.28), stage 1 IDH; 1.24 (95% CI, 1.08–1.42), stage 1 ISH; 1.39 (95% CI, 1.28–1.51), stage 1 SDH; 1.88 (95% CI, 1.63–2.16), stage 2 IDH; 1.84 (95% CI, 1.54–2.19), stage 2 ISH; 2.70 (95% CI, 2.44–2.98), stage 2 SDH. The HRs for CKD were attenuated in the patients who were antihypertensive and began medication within 1 year of medical checkup than in those without antihypertensives. Conclusions Among Korean young adults, those with elevated BP, stage 1 IDH, stage 1 ISH, stage 1 SDH, stage 2 IDH, stage 2 ISH, and stage 2 SDH were associated with a higher CKD risk than those with normal BP. The CKD risk in ISH and IDH groups was similar but lower than that in the SDH group. Antihypertensives attenuated the risk of CKD in young adults with hypertension.

Application of Machine Learning in Chronic Kidney Disease Risk Prediction Using Electronic Health Records (EHR)

Chronic kidney disease (CKD) is a disorder in which the kidneys are weakened and become unable to filter blood. It lowers the human ability to remain healthy. The field of biosciences has progressed and produced vast volumes of knowledge from electronic health records. Heart disorders, anemia, bone diseases, elevated potassium, and calcium are the very prevalent complications that arise from kidney failure. Early identification of CKD can improve the quality of life greatly. To achieve this, various machine learning techniques have been introduced so far that use the data in electronic health record (EHR) to predict CKD. This chapter studies various machine learning algorithms like support vector machine, random forest, probabilistic neural network, Apriori, ZeroR, OneR, naive Bayes, J48, IBk (k-nearest neighbor), ensemble method, etc. and compares their accuracy. The study aims in finding the best-suited technique from different methods of machine learning for the early detection of CKD by which medical professionals can interpret model predictions easily.

THE CHRONIC KIDNEY DISEASE RISK ANALYSIS IN PATIENTS WITH ARTERIAL HYPERTENSION AND COEXISTENT HYPERURICEMIA

The aim: Is the analysis of chronic kidney disease risk in patients with arterial hypertension and coexistent hyperuricemia. Materials and methods:We observed 40 patients with arterial hypertension and coexistent hyperuricemia (I group), 35 – with arterial hypertension (II group) and 30 practically healthy people (control). The duration of hypertension was 4,3 ± 2,31 years and 4,0 ± 2,11 years (p = 0,9247) for I and II group respectively, of hyperuricemia – 4,1 ± 0,35 years for I group. Categories of albuminuria (А1, А2, А3) and glomerular filtration rate (G1, G2, G3A, G3B, G4, G5) were determined in all observed patients. Clinical, anthropometric, biochemical, immunoassay, statistical (SPSS 21, Graph Pad) methods were used. Results:The categories of albuminuria and glomerular filtration rate in patients from the I group demonstrated that A1G1 was confirmed in 3 persons, A1G2 – 5, A2G1 – 7, A2G2 – 20, A1G3A – 1, A1G3B – 1, A2G3A – 2, A2G3B – 1. Among patients from the II group category A1G1 was defined in 7, A1G2 – 2, A2G1 – 16, A2G2 – 10 persons. The percent of low chronic kidney disease risk was on 5,7 % higher in hypertensive persons comparable with comorbid persons. High and very high risk was confirmed in 10 % persons from I group and nobody from the ІІ group. Conclusions:Chronic kidney disease risk is increased in patients with arterial hypertension and coexistent hyperuricemia. This indicates an association between elevated uric acid levels and chronic kidney disease progression.