Dataset Information

Improving accuracy of estimating glomerular filtration rate using artificial neural network: model development and validation.

ABSTRACT:

Background

The performance of previously published glomerular filtration rate (GFR) estimation equations degrades when directly used in Chinese population. We incorporated more independent variables and using complicated non-linear modeling technology (artificial neural network, ANN) to develop a more accurate GFR estimation model for Chinese population.

Methods

The enrolled participants came from the Third Affiliated Hospital of Sun Yat-sen University, China from Jan 2012 to Jun 2016. Participants with age < 18, unstable kidney function, taking trimethoprim or cimetidine, or receiving dialysis were excluded. Among the finally enrolled 1952 participants, 1075 participants (55.07%) from Jan 2012 to Dec 2014 were assigned as the development data whereas 877 participants (44.93%) from Jan 2015 to Jun 2016 as the internal validation data. We in total developed 3 GFR estimation models: a 4-variable revised CKD-EPI (chronic kidney disease epidemiology collaboration) equation (standardized serum creatinine and cystatin C, age and gender), a 9-variable revised CKD-EPI equation (additional auxiliary variables: body mass index, blood urea nitrogen, albumin, uric acid and hemoglobin), and a 9-variable ANN model.

Results

Compared with the 4-variable equation, the 9-variable equation could not achieve superior performance in the internal validation data (mean of difference: 5.00 [3.82, 6.54] vs 4.67 [3.55, 5.90], P = 0.5; interquartile range (IQR) of difference: 18.91 [17.43, 20.48] vs 20.11 [18.46, 21.80], P = 0.05; P30: 76.6% [73.7%, 79.5%] vs 75.8% [72.9%, 78.6%], P = 0.4), but the 9-variable ANN model significantly improve bias and P30 accuracy (mean of difference: 2.77 [1.82, 4.10], P = 0.007; IQR: 19.33 [17.77, 21.17], P = 0.3; P30: 80.0% [77.4%, 82.7%], P < 0.001).

Conclusions

It is suggested that using complicated non-linear models like ANN could fully utilize the predictive ability of the independent variables, and then finally achieve a superior GFR estimation model.

SUBMITTER: Li N

PROVIDER: S-EPMC7063770 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving accuracy of estimating glomerular filtration rate using artificial neural network: model development and validation.

Li Ningshan N Huang Hui H Qian Han-Zhu HZ Liu Peijia P Lu Hui H Liu Xun X

Journal of translational medicine 20200310 1

<h4>Background</h4>The performance of previously published glomerular filtration rate (GFR) estimation equations degrades when directly used in Chinese population. We incorporated more independent variables and using complicated non-linear modeling technology (artificial neural network, ANN) to develop a more accurate GFR estimation model for Chinese population.<h4>Methods</h4>The enrolled participants came from the Third Affiliated Hospital of Sun Yat-sen University, China from Jan 2012 to Jun ...[more]

PMID: 32156297

Similar Datasets

Project description:BackgroundAccurate evaluation of glomerular filtration rates (GFRs) is of critical importance in clinical practice. A previous study showed that models based on artificial neural networks (ANNs) could achieve a better performance than traditional equations. However, large-sample cross-sectional surveys have not resolved questions about ANN performance.MethodsA total of 1,180 patients that had chronic kidney disease (CKD) were enrolled in the development data set, the internal validation data set and the external validation data set. Additional 222 patients that were admitted to two independent institutions were externally validated. Several ANNs were constructed and finally a Back Propagation network optimized by a genetic algorithm (GABP network) was chosen as a superior model, which included six input variables; i.e., serum creatinine, serum urea nitrogen, age, height, weight and gender, and estimated GFR as the one output variable. Performance was then compared with the Cockcroft-Gault equation, the MDRD equations and the CKD-EPI equation.ResultsIn the external validation data set, Bland-Altman analysis demonstrated that the precision of the six-variable GABP network was the highest among all of the estimation models; i.e., 46.7 ml/min/1.73 m(2) vs. a range from 71.3 to 101.7 ml/min/1.73 m(2), allowing improvement in accuracy (15% accuracy, 49.0%; 30% accuracy, 75.1%; 50% accuracy, 90.5% [P<0.001 for all]) and CKD stage classification (misclassification rate of CKD stage, 32.4% vs. a range from 47.3% to 53.3% [P<0.001 for all]). Furthermore, in the additional external validation data set, precision and accuracy were improved by the six-variable GABP network.ConclusionsA new ANN model (the six-variable GABP network) for CKD patients was developed that could provide a simple, more accurate and reliable means for the estimation of GFR and stage of CKD than traditional equations. Further validations are needed to assess the ability of the ANN model in diverse populations.

Project description:IntroductionGlomerular filtration rate (GFR) is typically estimated with equations that use biomarkers such as serum creatinine and/or cystatin-C. The impact of these different biomarkers on GFR estimates in glomerular disease patients is unclear. In this study, we compared the different GFR estimating equations in the Cure Glomerulonephropathy (CureGN) cohort of children and adults with glomerular disease.MethodsAll available cystatin-C measurements from CureGN study participants were matched to same-day serum creatinine measurements to estimate GFR. To explore the strength of agreement between eGFR values obtained from the "Under 25" (U25) and Chronic Kidney Disease Epidemiology Collaboration (CKD-Epi) equations, we used intraclass correlation coefficients. Multivariable linear mixed effects models were used to determine which factors were independently associated with differences in eGFR values.ResultsA total of 928 cystatin-C measurements were matched to same-day serum creatinine measurements from N = 332 CureGN study participants (58% male, 69% White/Caucasian, 20% Black/African American). Among 628 measurements collected while study participants were under 25 years old, there was moderate agreement (0.731) in serum creatinine versus cystatin-C U25 equations. Models showed that higher eGFR values were associated with larger differences between the two equations (p < 0.001). Among 253 measurements collected while study participants were at least 18 years old, there was excellent agreement (0.891-0.978) among CKD-Epi equations using serum creatinine alone, cystatin-C alone, or the combination of both. Younger age was associated with larger differences between CKD-Epi equations (p = 0.06 to p = 0.016).ConclusionExcellent agreement between CKD-Epi equations indicates continued use of serum creatinine alone for GFR estimation could be appropriate for adults. In contrast, only moderate agreement between U25 equations indicates a need for more frequent measurement of cystatin-C among children and young adults, especially as eGFR increases.

Project description:BackgroundEstimates of glomerular filtration rate (GFR) that are based on serum creatinine are routinely used; however, they are imprecise, potentially leading to the overdiagnosis of chronic kidney disease. Cystatin C is an alternative filtration marker for estimating GFR.MethodsUsing cross-sectional analyses, we developed estimating equations based on cystatin C alone and in combination with creatinine in diverse populations totaling 5352 participants from 13 studies. These equations were then validated in 1119 participants from 5 different studies in which GFR had been measured. Cystatin and creatinine assays were traceable to primary reference materials.ResultsMean measured GFRs were 68 and 70 ml per minute per 1.73 m(2) of body-surface area in the development and validation data sets, respectively. In the validation data set, the creatinine-cystatin C equation performed better than equations that used creatinine or cystatin C alone. Bias was similar among the three equations, with a median difference between measured and estimated GFR of 3.9 ml per minute per 1.73 m(2) with the combined equation, as compared with 3.7 and 3.4 ml per minute per 1.73 m(2) with the creatinine equation and the cystatin C equation (P=0.07 and P=0.05), respectively. Precision was improved with the combined equation (interquartile range of the difference, 13.4 vs. 15.4 and 16.4 ml per minute per 1.73 m(2), respectively [P=0.001 and P<0.001]), and the results were more accurate (percentage of estimates that were >30% of measured GFR, 8.5 vs. 12.8 and 14.1, respectively [P<0.001 for both comparisons]). In participants whose estimated GFR based on creatinine was 45 to 74 ml per minute per 1.73 m(2), the combined equation improved the classification of measured GFR as either less than 60 ml per minute per 1.73 m(2) or greater than or equal to 60 ml per minute per 1.73 m(2) (net reclassification index, 19.4% [P<0.001]) and correctly reclassified 16.9% of those with an estimated GFR of 45 to 59 ml per minute per 1.73 m(2) as having a GFR of 60 ml or higher per minute per 1.73 m(2).ConclusionsThe combined creatinine-cystatin C equation performed better than equations based on either of these markers alone and may be useful as a confirmatory test for chronic kidney disease. (Funded by the National Institute of Diabetes and Digestive and Kidney Diseases.).

Project description:ImportanceThere is increasing concern that continued use of a glomerular filtration rate (GFR) estimating equation adjusted for a single racial group could exacerbate chronic kidney disease-related disparities and inequalities.ObjectiveTo assess the performance of GFR estimating equations across varied patient populations.Data sourcesPubMed, Embase, Web of Science, ClinicalTrials.gov, and Scopus databases were systematically searched from January 2012 to February 2023.Study selectionInclusion criteria were studies that compared measured GFR with estimated GFR in adults using established reference standards and methods. A total of 6663 studies were initially identified for screening and review.Data extraction and synthesisFollowing Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 2 authors independently extracted data on studies that examined the bias and accuracy of GFR estimating equations. For each outcome, a random-effects model was used to calculate pooled estimates. Data analysis was conducted from March to December 2023.Main outcomes and measuresThe primary outcomes were bias and accuracy of estimated GFRs in Black vs non-Black patients, as well as in individuals with chronic conditions. Bias was defined as the median difference between the measured GFR and the estimated GFR. Accuracy was assessed with P30 (the proportion of persons in a data set whose estimated GFR values were within 30% of measured GFR values) and measures of heterogeneity.ResultsA total of 12 studies with a combined 44 721 patients were included. Significant heterogeneity was found in the bias of various GFR estimation equations. Race-corrected equations and creatinine-based equations tended to overestimate GFR in Black populations and showed mixed results in non-Black populations. For creatinine-based equations, the mean bias in subgroup analysis was 2.1 mL/min/1.73 m2 (95% CI, -0.2 mL/min/1.73 m2 to 4.4 mL/min/1.73 m2) in Black persons and 1.3 mL/min/1.73 m2 (95% CI, 0.0 mL/min/1.73 m2 to 2.5 mL/min/1.73 m2) in non-Black persons. Equations using only cystatin C had small biases. Regarding accuracy, heterogeneity was high in both groups. The overall P30 was 84.5% in Black persons and 87.8% in non-Black persons. Creatinine-based equations were more accurate in non-Black persons than in Black persons. For creatinine-cystatin C equations, the P30 was higher in non-Black persons. There was no significant P30 difference in cystatin C-only equations between the 2 groups. In patients with chronic conditions, P30 values were generally less than 85%, and the biases varied widely.Conclusions and relevanceThis systematic review and meta-analysis of GFR estimating equations suggests that there is bias in race-based GFR estimating equations, which exacerbates kidney disease disparities. Development of a GFR equation independent of race is a crucial starting point, but not the sole solution. Addressing the disproportionate burden of kidney failure on Black individuals in the US requires an enduring, multifaceted approach that should include improving diagnostics, tackling social determinants of health, confronting systemic racism, and using effective disease prevention and management strategies.

Dataset Information

Improving accuracy of estimating glomerular filtration rate using artificial neural network: model development and validation.

Background

Methods

Results

Conclusions

Publications

Improving accuracy of estimating glomerular filtration rate using artificial neural network: model development and validation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets