Dividing CKD stage 3 into G3a and G3b could better predict the prognosis of IgA nephropathy

Machine-learning enhancement of urine dipstick tests for chronic kidney disease detection

OBJECTIVE

Screening for chronic kidney disease (CKD) requires an estimated glomerular filtration rate (eGFR, mL/min/1.73 m2) from a blood sample and a proteinuria level from a urinalysis. We developed machine-learning models to detect CKD without blood collection, predicting an eGFR less than 60 (eGFR60 model) or 45 (eGFR45 model) using a urine dipstick test.

MATERIALS AND METHODS

The electronic health record data (n = 220 018) obtained from university hospitals were used for XGBoost-derived model construction. The model variables were age, sex, and 10 measurements from the urine dipstick test. The models were validated using health checkup center data (n = 74 380) and nationwide public data (KNHANES data, n = 62 945) for the general population in Korea.

RESULTS

The models comprised 7 features, including age, sex, and 5 urine dipstick measurements (protein, blood, glucose, pH, and specific gravity). The internal and external areas under the curve (AUCs) of the eGFR60 model were 0.90 or higher, and a higher AUC for the eGFR45 model was obtained. For the eGFR60 model on KNHANES data, the sensitivity was 0.93 or 0.80, and the specificity was 0.86 or 0.85 in ages less than 65 with proteinuria (nondiabetes or diabetes, respectively). Nonproteinuric CKD could be detected in nondiabetic patients under the age of 65 with a sensitivity of 0.88 and specificity of 0.71.

DISCUSSION AND CONCLUSIONS

The model performance differed across subgroups by age, proteinuria, and diabetes. The CKD progression risk can be assessed with the eGFR models using the levels of eGFR decrease and proteinuria. The machine-learning-enhanced urine-dipstick test can become a point-of-care test to promote public health by screening CKD and ranking its risk of progression.

Efficacy and Safety of Renin-Angiotensin Aldosterone System Inhibitor in Patients with IgA Nephropathy: A Meta-Analysis of Randomized Controlled Trials

BACKGROUND

Angiotensin converting enzyme inhibitor (ACEI) and angiotensin receptor blocker (ARB) as the commonly used renin-angiotensin aldosterone system inhibitor are widely used in patients with IgA nephropathy (IgAN), but the effect is controversy. In this study, we used a meta-analysis to evaluate the efficacy and safety of ACEI and/or ARB for the patients with IgAN.

METHODS

Two investigators independently searched the PubMed, EMBASE, the Cochrane Library, EBSCO, and Wiley databases without language restrictions. We collected the clinical randomized controlled trials (RCTs) on "ACEI and/or ARB for the patients with IgAN" published before December 31, 2018, and performed data extraction and quality analysis on the included studies, and analyzed data using RevMan 5.2 software.

RESULTS

A total of 10 RCTs (635 patients) were included in our analysis. Alone use of ACEI (MD=-0.75, 95%CI: -1.28-0.21, P=0.006) or ARB (MD=-0.56, 95%CI: -0.82-0.30, P< 0.001) or a combination of ACEI and ARB (MD=-0.63, 95%CI: -0.87-0.38, P<0.001) significantly reduced the levels of proteinuria in patients with IgAN. However, whether using ACEI or ARB alone or in combination with ACEI and ARB, there was no significant effect on serum creatinine, 24-creatinine clearance and glomerular filtration rate in patients with IgAN.

CONCLUSION

The use of ACEI and ARB significantly reduces the levels of proteinuria in patients with IgAN, but more large-sample RCTs with long-term follow-up are needed for confirming our results and guiding clinical treatment.

Clinical features and CKD-related quality of life in patients with CKD G3a and CKD G3b in China: results from the Chinese Cohort Study of Chronic Kidney Disease (C-STRIDE)

Background

This study aimed to compare clinical features and health-related quality of life (HRQoL) in the Chinese chronic kidney disease (CKD) 3 population and determined the necessity of the subdivision of CKD3 in Chinese patients with CKD.

Methods

Participants with stage 3 CKD (18–74 years of age) were recruited at 39 clinical centers located at 28 cities in 22 provinces of China. The sociodemographic status, medical history, anthropometric measurements, and lifestyle behaviors were documented at entry, and blood and urine samples were collected. The estimated glomerular filtration rate was calculated using the CKD-EPI creatinine equation. The HRQoL was evaluated using the kidney disease quality-of-life instrument. A linear regression model was used to estimate the association between HRQoL and CKD stages (G3b vs G3a).

Results

The levels of intact parathyroid hormone, systolic blood pressure, uric acid, and high-density lipoprotein cholesterol were statistically significantly higher, whereas the levels of serum bicarbonate and hemoglobin were statistically significantly lower in the G3b group compared with the G3a group. Compared with CKD G3a group, the proportions of subjects with hyperuricemia and anemia were significantly higher in CKD G3b group (61.4% vs. 52.0% and 26.4% vs. 17.9%, respectively, P< 0.01). The HRQoL scores in “physical functioning (PCS)”, “symptoms and problems”, “effects of the kidney disease” and “burden of the kidney disease” were statistically significantly lower in the CKD G3b group compared with the CKD G3a group (90.88 ± 11.05 vs. 89.30 ± 11.52, 88.29 ± 11.94 vs. 86.49 ± 13.45, 55.86 ± 26.40 vs. 52.10 ± 27.64, 46.56 ± 8.16 vs. 44.51 ± 9.22, respectively, P< 0.01). Further, CKD G3b was associated with a lower score of physical functioning compared with G3a (regression coefficient =−1.12 [95%CI: −2.23, −0.16]).

Conclusions

The preliminary results of this study suggested that modest differences existed in many important clinical features and KDQoL between patients with G3a and G3b CKD in a Chinese population. Also, a significant association between CKD3 subdivision of the disease and PCS was detected. Although further work is needed, we can speculate based on these results the CKD3 subdivision may be clinically meaningful for Chinese patients with CKD.

Electronic supplementary material

The online version of this article (doi: 10.1186/s12882-017-0725-0) contains supplementary material, which is available to authorized users.

Establishing the presence or absence of chronic kidney disease: Uses and limitations of formulas estimating the glomerular filtration rate

The development of formulas estimating glomerular filtration rate (eGFR) from serum creatinine and cystatin C and accounting for certain variables affecting the production rate of these biomarkers, including ethnicity, gender and age, has led to the current scheme of diagnosing and staging chronic kidney disease (CKD), which is based on eGFR values and albuminuria. This scheme has been applied extensively in various populations and has led to the current estimates of prevalence of CKD. In addition, this scheme is applied in clinical studies evaluating the risks of CKD and the efficacy of various interventions directed towards improving its course. Disagreements between creatinine-based and cystatin-based eGFR values and between eGFR values and measured GFR have been reported in various cohorts. These disagreements are the consequence of variations in the rate of production and in factors, other than GFR, affecting the rate of removal of creatinine and cystatin C. The disagreements create limitations for all eGFR formulas developed so far. The main limitations are low sensitivity in detecting early CKD in several subjects, e.g., those with hyperfiltration, and poor prediction of the course of CKD. Research efforts in CKD are currently directed towards identification of biomarkers that are better indices of GFR than the current biomarkers and, particularly, biomarkers of early renal tissue injury.