Improved glomerular filtration rate estimation by an artificial neural network

A Deep Learning Approach for the Estimation of Glomerular Filtration Rate

An accurate estimation of glomerular filtration rate (GFR) is clinically crucial for kidney disease diagnosis and predicting the prognosis of chronic kidney disease (CKD). Machine learning methodologies such as deep neural networks provide a potential avenue for increasing accuracy in GFR estimation. We developed a novel deep learning architecture, a deep and shallow neural network, to estimate GFR (dlGFR for short) and examined its comparative performance with estimated GFR from Modification of Diet in Renal Disease (MDRD) and Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equations. The dlGFR model jointly trains a shallow learning model and a deep neural network to enable both linear transformation from input features to a log GFR target, and non-linear feature embedding for stage of kidney function classification. We validate the proposed methods on the data from multiple studies obtained from the NIDDK Central Database Repository. The deep learning model predicted values of GFR within 30% of measured GFR with 88.3% accuracy, compared to the 87.1% and 84.7% of the accuracy achieved by CKD-EPI and MDRD equations (p=0.051 and p<0.001, respectively). Our results suggest that deep learning methods are superior to equations resulting from traditional statistical methods in estimating glomerular filtration rate. Based on these results, an end-to-end predication system has been deployed to facilitate use of the proposed dlGFR algorithm.

Artificial neural network for the prediction model of glomerular filtration rate to estimate the normal or abnormal stages of kidney using gamma camera

OBJECTIVE

Chronic kidney disease (CKD) is evaluated based on glomerular filtration rate (GFR) using a gamma camera in the nuclear medicine center or hospital in a routine procedure, but the gamma camera does not provide the accurate stages of the diseases. Therefore, this research aimed to find out the normal or abnormal stages of CKD based on the value of GFR using an artificial neural network (ANN).

METHODS

Two hundred fifty (Training 188, Testing 62) kidney patients who underwent the ultrasonography test to diagnose the renal test in our nuclear medical centre were scanned using gamma camera. The patients were injected with 99mTc-DTPA before the scanning procedure. After pushing the syringe into the patient's vein, the pre-syringe and post syringe radioactive counts were calculated using the gamma camera. The artificial neural network uses the softmax function with cross-entropy loss to diagnose CKD normal or abnormal labels depending on the value of GFR in the output layer.

RESULTS

The results showed that the accuracy of the proposed ANN model was 99.20% for K-fold cross-validation. The sensitivity and specificity were 99.10% and 99.20%, respectively. The Area under the curve (AUC) was 0.9994.

CONCLUSION

The proposed model using an artificial neural network can classify the normal or abnormal stages of CKD. After implementing the proposed model clinically, it may upgrade the gamma camera to diagnose the normal or abnormal stages of the CKD with an appropriate GFR value.

Improving glomerular filtration rate estimation by semi-supervised learning: a development and external validation study

BACKGROUND

Accurate estimating glomerular filtration rate (GFR) is crucial both in clinical practice and epidemiological survey. We incorporated semi-supervised learning technology to improve GFR estimation performance.

METHODS

AASK [African American Study of Kidney Disease and Hypertension], CRIC [Chronic Renal Insufficiency Cohort] and DCCT [Diabetes Control and Complications Trial] studies were pooled together for model development, whereas MDRD [Modification of Diet in Renal Disease] and CRISP [Consortium for Radiological Imaging Studies of Polycystic Kidney Disease] studies for model external validation. A total of seven variables (Serum creatinine, Age, Sex, Black race, Diabetes status, Hypertension and Body Mass Index) were included as independent variables, while the outcome variable GFR was measured as the urinary clearance of ¹²⁵I-iothalamate. The revised CKD-EPI [Chronic Kidney Disease Epidemiology Collaboration] creatinine equations was selected as benchmark for performance comparisons. Head-to-head performance comparisons from four-variable to seven-variable combination were conducted between revised CKD-EPI equations and semi-supervised models.

RESULTS

In each independent variables combination, the semi-supervised models consistently achieved superior results in all three performance indicators compared with corresponding revised CKD-EPI equations in the external validation data set. Furthermore, compared with revised four-variable CKD-EPI equation, the seven-variable semi-supervised model performed less biased (mean of difference: 0.03 [- 0.28, 0.34] vs 1.53 [1.28, 1.85], P < 0.001), more precise (interquartile range of difference: 7.94 [7.37, 8.50] vs 8.28 [7.76, 8.83], P = 0.1) and accurate (P30: 88.9% [87.4%, 90.2%] vs 86.0% [84.4%, 87.4%], P < 0.001.

CONCLUSIONS

The superior performance of the semi-supervised models during head-to-head comparisons supported the hypothesis that semi-supervised learning technology could improve GFR estimation performance.

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

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.

Glomerular Filtration Rate Estimation by a Novel Numerical Binning-Less Isotonic Statistical Bivariate Numerical Modeling Method

Statistical bivariate numerical modeling is a method to infer an empirical relationship between unpaired sets of data based on statistical distributions matching. In the present paper, a novel efficient numerical algorithm is proposed to perform bivariate numerical modeling. The algorithm is then applied to correlate glomerular filtration rate to serum creatinine concentration. Glomerular filtration rate is adopted in clinical nephrology as an indicator of kidney function and is relevant for assessing progression of renal disease. As direct measurement of glomerular filtration rate is highly impractical, there is considerable interest in developing numerical algorithms to estimate glomerular filtration rate from parameters which are easier to obtain, such as demographic and `bedside’ assays data.

A new modified CKD-EPI equation for Chinese patients with type 2 diabetes

Objective

To improve the performance of glomerular filtration rate (GFR) estimating equation in Chinese type 2 diabetic patients by modification of the CKD-EPI equation.

Design and patients

A total of 1196 subjects were enrolled. Measured GFR was calibrated to the dual plasma sample ^99mTc-DTPA-GFR. GFRs estimated by the re-expressed 4-variable MDRD equation, the CKD-EPI equation and the Asian modified CKD-EPI equation were compared in 351 diabetic/non-diabetic pairs. And a new modified CKD-EPI equation was reconstructed in a total of 589 type 2 diabetic patients.

Results

In terms of both precision and accuracy, GFR estimating equations all achieved better results in the non-diabetic cohort comparing with those in the type 2 diabetic cohort (30% accuracy, P≤0.01 for all comparisons). In the validation data set, the new modified equation showed less bias (median difference, 2.3 ml/min/1.73 m² for the new modified equation vs. ranged from −3.8 to −7.9 ml/min/1.73 m² for the other 3 equations [P<0.001 for all comparisons]), as was precision (IQR of the difference, 24.5 ml/min/1.73 m² vs. ranged from 27.3 to 30.7 ml/min/1.73 m²), leading to a greater accuracy (30% accuracy, 71.4% vs. 55.2% for the re-expressed 4 variable MDRD equation and 61.0% for the Asian modified CKD-EPI equation [P = 0.001 and P = 0.02]).

Conclusion

A new modified CKD-EPI equation for type 2 diabetic patients was developed and validated. The new modified equation improves the performance of GFR estimation.

A new equation to estimate glomerular filtration rate in Chinese elderly population

Background

We sought to develop a new equation to estimate glomerular filtration rate (GFR) in Chinese elderly population.

Methods

A total of 668 Chinese elderly participants, including the development cohort (n = 433), the validation cohort (n = 235) were enrolled. The new equation using the generalized additive model, and age, gender, serum creatinine as predictor variables was developed and the performances was compared with the CKD-EPI equation.

Results

In the validation data set, both bias and precision were improved with the new equation, as compared with the CKD-EPI equation (median difference, −1.5 ml/min/1.73 m² vs. 7.4 ml/min/1.73 m² for the new equation and the CKD-EPI equation, [P<0.001]; interquartile range [IQR] for the difference, 16.2 ml/min/1.73 m² vs. 19.0 ml/min/1.73 m² [P<0.001]), as were accuracies (15% accuracy, 40.4% vs. 30.6% [P = 0.02]; 30% accuracy, 71.1% vs. 47.2%, [P<0.001]; 50% accuracy, 90.2% vs. 75.7%, [P<0.001]), allowing improvement in GFR categorization (GFR category misclassification rate, 37.4% vs. 53.2% [P = <0.001]).

Conclusions

A new equation was developed in Chinese elderly population. In the validation data set, the new equation performed better than the original CKD-EPI equation. The new equation needs further external validations. Calibration of the GFR referent standard to a more accurate one should be an useful way to improve the performance of GFR estimating equations.

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

Background

We 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 methods

Glomerular 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.

Results

Although 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).

Conclusion

Compared 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.

A comparison of the performances of an artificial neural network and a regression model for GFR estimation

BACKGROUND

Accurate estimation of glomerular filtration rate (GFR) is important in clinical practice. Current models derived from regression are limited by the imprecision of GFR estimates. We hypothesized that an artificial neural network (ANN) might improve the precision of GFR estimates.

STUDY DESIGN

A study of diagnostic test accuracy.

SETTING & PARTICIPANTS

1,230 patients with chronic kidney disease were enrolled, including the development cohort (n=581), internal validation cohort (n=278), and external validation cohort (n=371).

INDEX TESTS

Estimated GFR (eGFR) using a new ANN model and a new regression model using age, sex, and standardized serum creatinine level derived in the development and internal validation cohort, and the CKD-EPI (Chronic Kidney Disease Epidemiology Collaboration) 2009 creatinine equation.

REFERENCE TEST

Measured GFR (mGFR).

OTHER MEASUREMENTS

GFR was measured using a diethylenetriaminepentaacetic acid renal dynamic imaging method. Serum creatinine was measured with an enzymatic method traceable to isotope-dilution mass spectrometry.

RESULTS

In the external validation cohort, mean mGFR was 49±27 (SD) mL/min/1.73 m2 and biases (median difference between mGFR and eGFR) for the CKD-EPI, new regression, and new ANN models were 0.4, 1.5, and -0.5 mL/min/1.73 m2, respectively (P<0.001 and P=0.02 compared to CKD-EPI and P<0.001 comparing the new regression and ANN models). Precisions (IQRs for the difference) were 22.6, 14.9, and 15.6 mL/min/1.73 m2, respectively (P<0.001 for both compared to CKD-EPI and P<0.001 comparing the new ANN and new regression models). Accuracies (proportions of eGFRs not deviating >30% from mGFR) were 50.9%, 77.4%, and 78.7%, respectively (P<0.001 for both compared to CKD-EPI and P=0.5 comparing the new ANN and new regression models).

LIMITATIONS

Different methods for measuring GFR were a source of systematic bias in comparisons of new models to CKD-EPI, and both the derivation and validation cohorts consisted of a group of patients who were referred to the same institution.

CONCLUSIONS

An ANN model using 3 variables did not perform better than a new regression model. Whether ANN can improve GFR estimation using more variables requires further investigation.