Ningshan Li1, Hui Huang2, Lv Linsheng3, Hui Lu4,5,6, Xun Liu7,8. 1. SJTU-Yale Joint Center for Biostatistics and Data Science, Department of Bioinformatics and Biostatistics, School of Life Science and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China. 2. Cardiovascular Department, The Eighth Affiliated Hospital, Sun Yat-Sen University, Shenzhen, China. 3. Operation Room, The Third Affiliated Hospital of Sun Yat-Sen University, Guangdong, China. 4. SJTU-Yale Joint Center for Biostatistics and Data Science, Department of Bioinformatics and Biostatistics, School of Life Science and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China. huilu@sjtu.edu.cn. 5. MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China. huilu@sjtu.edu.cn. 6. Shanghai Engineering Research Center for Big Data in Pediatric Precision Medicine, Shanghai, China. huilu@sjtu.edu.cn. 7. Clinical Data Center of the Third Affiliated Hospital of Sun Yat-Sen University, Guangdong, China. naturestyle@163.com. 8. Division of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510630, Guangdong, China. naturestyle@163.com.
Abstract
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.
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.
Authors: Lesley A Inker; Christopher H Schmid; Hocine Tighiouart; John H Eckfeldt; Harold I Feldman; Tom Greene; John W Kusek; Jane Manzi; Frederick Van Lente; Yaping Lucy Zhang; Josef Coresh; Andrew S Levey Journal: N Engl J Med Date: 2012-07-05 Impact factor: 91.245