Improving precision of glomerular filtration rate estimating model by ensemble learning
Abstract Background Accurate assessment of kidney function is clinically important, but estimates of glomerular filtration rate (GFR) by regression are imprecise. Methods We hypothesized that ensemble learning could improve precision. A total of 1419 participants were enrolled, with 1002 in the deve...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2017-11-01
|
| Series: | Journal of Translational Medicine |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12967-017-1337-y |
| _version_ | 1811279290453458944 |
|---|---|
| author | Xun Liu Ningshan Li Linsheng Lv Yongmei Fu Cailian Cheng Caixia Wang Yuqiu Ye Shaomin Li Tanqi Lou |
| author_facet | Xun Liu Ningshan Li Linsheng Lv Yongmei Fu Cailian Cheng Caixia Wang Yuqiu Ye Shaomin Li Tanqi Lou |
| author_sort | Xun Liu |
| collection | DOAJ |
| description | Abstract Background Accurate assessment of kidney function is clinically important, but estimates of glomerular filtration rate (GFR) by regression are imprecise. Methods We hypothesized that ensemble learning could improve precision. A total of 1419 participants were enrolled, with 1002 in the development dataset and 417 in the external validation dataset. GFR was independently estimated from age, sex and serum creatinine using an artificial neural network (ANN), support vector machine (SVM), regression, and ensemble learning. GFR was measured by 99mTc-DTPA renal dynamic imaging calibrated with dual plasma sample 99mTc-DTPA GFR. Results Mean measured GFRs were 70.0 ml/min/1.73 m2 in the developmental and 53.4 ml/min/1.73 m2 in the external validation cohorts. In the external validation cohort, precision was better in the ensemble model of the ANN, SVM and regression equation (IQR = 13.5 ml/min/1.73 m2) than in the new regression model (IQR = 14.0 ml/min/1.73 m2, P < 0.001). The precision of ensemble learning was the best of the three models, but the models had similar bias and accuracy. The median difference ranged from 2.3 to 3.7 ml/min/1.73 m2, 30% accuracy ranged from 73.1 to 76.0%, and P was > 0.05 for all comparisons of the new regression equation and the other new models. Conclusions An ensemble learning model including three variables, the average ANN, SVM, and regression equation values, was more precise than the new regression model. A more complex ensemble learning strategy may further improve GFR estimates. |
| first_indexed | 2024-04-13T00:52:00Z |
| format | Article |
| id | doaj.art-5034996b696e4946af959ecc8c729f8f |
| institution | Directory Open Access Journal |
| issn | 1479-5876 |
| language | English |
| last_indexed | 2024-04-13T00:52:00Z |
| publishDate | 2017-11-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Translational Medicine |
| spelling | doaj.art-5034996b696e4946af959ecc8c729f8f2022-12-22T03:09:51ZengBMCJournal of Translational Medicine1479-58762017-11-011511510.1186/s12967-017-1337-yImproving precision of glomerular filtration rate estimating model by ensemble learningXun Liu0Ningshan Li1Linsheng Lv2Yongmei Fu3Cailian Cheng4Caixia Wang5Yuqiu Ye6Shaomin Li7Tanqi Lou8Division of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-sen UniversitySJTU-YALE Joint Center for Biostatistics, Shanghai JiaoTong UniversityOperating Room, The Third Affiliated Hospital of Sun Yat-sen UniversityEmergency Department, The Third Affiliated Hospital of Sun Yat-sen UniversityDivision of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-sen UniversityDivision of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-sen UniversityDivision of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-sen UniversityDivision of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-sen UniversityDivision of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-sen UniversityAbstract Background Accurate assessment of kidney function is clinically important, but estimates of glomerular filtration rate (GFR) by regression are imprecise. Methods We hypothesized that ensemble learning could improve precision. A total of 1419 participants were enrolled, with 1002 in the development dataset and 417 in the external validation dataset. GFR was independently estimated from age, sex and serum creatinine using an artificial neural network (ANN), support vector machine (SVM), regression, and ensemble learning. GFR was measured by 99mTc-DTPA renal dynamic imaging calibrated with dual plasma sample 99mTc-DTPA GFR. Results Mean measured GFRs were 70.0 ml/min/1.73 m2 in the developmental and 53.4 ml/min/1.73 m2 in the external validation cohorts. In the external validation cohort, precision was better in the ensemble model of the ANN, SVM and regression equation (IQR = 13.5 ml/min/1.73 m2) than in the new regression model (IQR = 14.0 ml/min/1.73 m2, P < 0.001). The precision of ensemble learning was the best of the three models, but the models had similar bias and accuracy. The median difference ranged from 2.3 to 3.7 ml/min/1.73 m2, 30% accuracy ranged from 73.1 to 76.0%, and P was > 0.05 for all comparisons of the new regression equation and the other new models. Conclusions An ensemble learning model including three variables, the average ANN, SVM, and regression equation values, was more precise than the new regression model. A more complex ensemble learning strategy may further improve GFR estimates.http://link.springer.com/article/10.1186/s12967-017-1337-yChronic kidney diseaseGlomerular filtration rateEnsemble learningPredictionPrecision |
| spellingShingle | Xun Liu Ningshan Li Linsheng Lv Yongmei Fu Cailian Cheng Caixia Wang Yuqiu Ye Shaomin Li Tanqi Lou Improving precision of glomerular filtration rate estimating model by ensemble learning Journal of Translational Medicine Chronic kidney disease Glomerular filtration rate Ensemble learning Prediction Precision |
| title | Improving precision of glomerular filtration rate estimating model by ensemble learning |
| title_full | Improving precision of glomerular filtration rate estimating model by ensemble learning |
| title_fullStr | Improving precision of glomerular filtration rate estimating model by ensemble learning |
| title_full_unstemmed | Improving precision of glomerular filtration rate estimating model by ensemble learning |
| title_short | Improving precision of glomerular filtration rate estimating model by ensemble learning |
| title_sort | improving precision of glomerular filtration rate estimating model by ensemble learning |
| topic | Chronic kidney disease Glomerular filtration rate Ensemble learning Prediction Precision |
| url | http://link.springer.com/article/10.1186/s12967-017-1337-y |
| work_keys_str_mv | AT xunliu improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT ningshanli improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT linshenglv improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT yongmeifu improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT cailiancheng improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT caixiawang improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT yuqiuye improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT shaominli improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning AT tanqilou improvingprecisionofglomerularfiltrationrateestimatingmodelbyensemblelearning |