Improved Glomerular Filtration Rate Estimation by an Artificial Neural Network

Liu, Xun; Pei, Xiaohua; Li, Ningshan; Zhang, Yunong; Zhang, Xiang; Chen, Jinxia; Lv, Linsheng; Ma, Huijuan; Wu, Xiaoming; Zhao, Weihong; Lou, Tanqi

doi:10.1371/journal.pone.0058242

Cited by 13 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GFR was measured by the 99m Tc-DTPA renal dynamic imaging method, 67 as described previously8 According to the method developed by Ma et al,9 we determined the minimum sample size to be 36 (95% confidence interval and 80% power), using Open Epi Version 2 (http://www.openepi.com)10 to compare means (in order to ensure that our measured GFR [mGFR] values were calibrated equally to the dual plasma sample 99m Tc-DTPA-GFR). Calculation was based on the findings in a previous Chinese study11 We randomly selected 36 cases (GFR measured by the DTPA renal dynamic imaging method, range 15.6–106.3 mL/minute/1.73 m 2 ) and performed the dual plasma samples method 99m Tc-DTPA clearance simultaneously with the renal dynamic imaging.…”

Section: Methodsmentioning

confidence: 99%

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine–cystatin C equation useful for glomerular filtration rate estimation in the elderly?

Liu¹,

Ma²,

Huang³

et al. 2013

CIA

Self Cite

View full text Add to dashboard Cite

BackgroundWe aimed to evaluate the performance of the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) creatinine–cystatin C equation in a cohort of elderly Chinese participants.Materials and methodsGlomerular filtration rate (GFR) was measured in 431 elderly Chinese participants by the technetium-99m diethylene-triamine-penta-acetic acid (99mTc-DTPA) renal dynamic imaging method, and was calibrated equally to the dual plasma sample 99mTc-DTPA-GFR. Performance of the CKD-EPI creatinine–cystatin C equation was compared with the Cockcroft–Gault equation, the re-expressed 4-variable Modification of Diet in Renal Disease (MDRD) equation, and the CKD-EPI creatinine equation.ResultsAlthough the bias of the CKD-EPI creatinine–cystatin C equation was greater than with the other equations (median difference, 5.7 mL/minute/1.73 m2 versus a range from 0.4–2.5 mL/minute/1.73 m2; P<0.001 for all), the precision was improved with the CKD-EPI creatinine–cystatin C equation (interquartile range for the difference, 19.5 mL/minute/1.73 m2 versus a range from 23.0–23.6 mL/minute/1.73 m2; P<0.001 for all comparisons), leading to slight improvement in accuracy (median absolute difference, 10.5 mL/minute/1.73 m2 versus 12.2 and 11.4 mL/minute/1.73 m2 for the Cockcroft–Gault equation and the re-expressed 4-variable MDRD equation, P=0.04 for both; 11.6 mL/minute/1.73 m2 for the CKD-EPI creatinine equation, P=0.11), as the optimal scores of performance (6.0 versus a range from 1.0–2.0 for the other equations). Higher GFR category and diabetes were independent factors that negatively correlated with the accuracy of the CKD-EPI creatinine–cystatin C equation (β=−0.184 and −0.113, P<0.001 and P=0.02, respectively).ConclusionCompared with the creatinine-based equations, the CKD-EPI creatinine–cystatin C equation is more suitable for the elderly Chinese population. However, the cost-effectiveness of the CKD-EPI creatinine–cystatin C equation for clinical use should be considered.

show abstract

Section: Methodsmentioning

confidence: 99%

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine–cystatin C equation useful for glomerular filtration rate estimation in the elderly?

Liu¹,

Ma²,

Huang³

et al. 2013

CIA

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some studies reported that ANN and other data mining methods supported medical decisions regarding VUR and some nephrological problems (21)(22)(23)(24)(25)(26)(27).…”

Section: Discussionmentioning

confidence: 99%

The Use of Artificial Neural Networks for Differential Diagnosis between Vesicoureteral Reflux and Urinary Tract Infection in Children

Keskınoğlu¹,

Özgür²

2020

jpr

View full text Add to dashboard Cite

Vesicoureteral reflux (VUR) and urinary tract infection (UTI) are common problems in children. Our goal is to use different models for the clinical decision of differential diagnosis of VUR and UTI in children. Materials and Methods: This was a retrospective cross-sectional study with 611 pediatric patients enrolled. Detailed information for the patients was obtained from hospital records and patient files. Three models including different variables were evaluated via an artificial neural network for the differential diagnosis of VUR and recurrent UTI. Clinical findings were included in Model 1, clinical and laboratory findings were included in Model 2, and clinical, laboratory and detailed urinary ultrasonography (USG) findings were included in Model 3. A cross-validation technique was used to evaluate predictive models by partitioning the original sample into a training set to train the model, and a test set to evaluate it. Results: Of the 611 children, 425 (69.6%) had VUR and 186 (30.4%) had UTI. The sensitivity of Model 1 and Model 2 were 0.682 and 0.856, respectively. Also, Model 3 showed the best performance and highest sensitivity with 0.939 for differential diagnosis. Conclusion: Differential diagnosis between VUR and UTI in children can be predicted by using clinical, laboratory and USG variables via an Artificial Neural Network. Model 3, which included clinical, laboratory and USG variables together, showed the best performance and highest sensitivity.

show abstract

“…A series of machine learning methods contribute to a speci c improvement for eGFR Eq. (13)(14)(15). However, no prediction equation can comprehensively exceed the CKD-EPI equation.…”

Section: Discussionmentioning

confidence: 99%

“…The measurement of standard GFR (sGFR) or measured GFR (mGFR) was radionuclide renal dynamic imaging or 99mTc-DTPA, which was described in detail before (13)(14)(15)22). Serum creatinine (SC) measurement was on Hitachi 7180 auto-analyzer (Hitachi, Tokyo, Japan) using reagents from Roche Diagnostics (Mannheim, Germany).…”

Section: Laboratory Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Applying Random Forest Model Algorithm to GFR estimation

Yang

Chong

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background The utilization of estimating-GFR equations is critical for kidney disease in the clinic. However, the performance of the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equation has not improved substantially in the past eight years. Here we hypothesized that random forest regression(RF) method could go beyond revised linear regression, which is used to build the CKD-EPI equation Methods 1732 participants were enrolled in this study totally (1333 in development data set from Tianhe District and 399 in external data set Luogang District). Recursive feature elimination (RFE) is applied to the development data to select important variables and build random forest models. Then same variables were used to develop the estimated GFR equation with linear regression as a comparison. The performances of these equations are measured by bias, 30% accuracy, precision and root mean square error(RMSE). Results Of all the variables, creatinine, cystatin C, weight, body mass index (BMI), age, uric acid(UA), blood urea nitrogen(BUN), hematocrit(HCT) and apolipoprotein B(APOB) were selected by RFE method. The results revealed that the overall performance of random forest regression models ascended the revised regression models based on the same variables. In the 9-variable model, RF model was better than revised linear regression in term of bias, precision ,30%accuracy and RMSE(0.78 vs 2.98, 16.90 vs 23.62, 0.84 vs 0.80, 16.88 vs 18.70, all P < 0.01 ). In the 4-variable model, random forest regression model showed an improvement in precision and RMSE compared with revised regression model. (20.82 vs 25.25, P < 0.01, 19.08 vs 20.60, P < 0.001). Bias and 30%accurancy were preferable, but the results were not statistically significant (0.34 vs 2.07, P = 0.10, 0.8 vs 0.78, P = 0.19, respectively). Conclusions The performances of random forest regression models are better than revised linear regression models when it comes to GFR estimation.

show abstract

Improved Glomerular Filtration Rate Estimation by an Artificial Neural Network

Cited by 13 publications

References 32 publications

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine–cystatin C equation useful for glomerular filtration rate estimation in the elderly?

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine–cystatin C equation useful for glomerular filtration rate estimation in the elderly?

The Use of Artificial Neural Networks for Differential Diagnosis between Vesicoureteral Reflux and Urinary Tract Infection in Children

Applying Random Forest Model Algorithm to GFR estimation

Contact Info

Product

Resources

About

Improved Glomerular Filtration Rate Estimation by an Artificial Neural Network

Cited by 13 publications

References 32 publications

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine&ndash;cystatin C equation useful for glomerular filtration rate estimation in the elderly?

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine&ndash;cystatin C equation useful for glomerular filtration rate estimation in the elderly?

The Use of Artificial Neural Networks for Differential Diagnosis between Vesicoureteral Reflux and Urinary Tract Infection in Children

Applying Random Forest Model Algorithm to GFR estimation

Contact Info

Product

Resources

About

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine–cystatin C equation useful for glomerular filtration rate estimation in the elderly?

Is the Chronic Kidney Disease Epidemiology Collaboration creatinine–cystatin C equation useful for glomerular filtration rate estimation in the elderly?