nach oben

International Urology and Nephrology

Erschienen in:

12.03.2021 | Nephrology - Original Paper

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

verfasst von: Ningshan Li, Hui Huang, Lv Linsheng, Hui Lu, Xun Liu

Erschienen in: International Urology and Nephrology | Ausgabe 8/2021

Einloggen, um Zugang zu erhalten

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.

Nur mit Berechtigung zugänglich

Webster AC, Nagler EV, Morton RL, Masson P (2017) Chronic Kidney Disease. Lancet 389(10075):1238–1252. https://doi.org/10.1016/S0140-6736(16)32064-5CrossRefPubMed

Glassock RJ, Warnock DG, Delanaye P (2016) The global burden of chronic kidney disease: estimates, variability and pitfalls. Nat Rev Nephrol 13:104. https://doi.org/10.1038/nrneph.2016.163CrossRefPubMed

Zhang L, Wang F, Wang L, Wang W, Liu B, Liu J, Chen M, He Q, Liao Y, Yu X, Chen N, Zhang J-e, Hu Z, Liu F, Hong D, Ma L, Liu H, Zhou X, Chen J, Pan L, Chen W, Wang W, Li X, Wang H (2012) Prevalence of chronic kidney disease in China: a cross-sectional survey. Lancet 379(9818):815–822. https://doi.org/10.1016/S0140-6736(12)60033-6CrossRefPubMed

Zhang L, Long J, Jiang W, Shi Y, He X, Zhou Z, Li Y, Yeung RO, Wang J, Matsushita K, Coresh J, Zhao M-H, Wang H (2016) Trends in Chronic Kidney Disease in China. N Engl J Med 375(9):905–906. https://doi.org/10.1056/NEJMc1602469CrossRefPubMed

Levey AS, Inker LA (2016) GFR as the “Gold Standard”: Estimated, Measured, and True. Am J Kidney Dis 67(1):9–12. https://doi.org/10.1053/j.ajkd.2015.09.014CrossRefPubMed

Levey AS, Inker LA, Coresh J (2014) GFR Estimation: From Physiology to Public Health. Am J Kidney Dis 63(5):820–834. https://doi.org/10.1053/j.ajkd.2013.12.006CrossRefPubMedPubMedCentral

Inker LA, Schmid CH, Tighiouart H, Eckfeldt JH, Feldman HI, Greene T, Kusek JW, Manzi J, Van Lente F, Zhang YL, Coresh J, Levey AS (2012) Estimating glomerular filtration rate from serum creatinine and Cystatin C. N Engl J Med 367(1):20–29. https://doi.org/10.1056/NEJMoa1114248CrossRefPubMedPubMedCentral

Miller G (2013) Practices and Recommendations for Reporting Estimated Glomerular Filtration Rate (eGFR). http://webapps.cap.org/apps/docs/committees/chemistry/current_status_reporting_egfr2013.pdf. Accessed 25 Dec2018

Van Biesen W, Nagler EV (2016) A Swiss army knife for estimating kidney function: why new equations will not solve the real problem. Nephrol Dial Transplant 31(5):685–687. https://doi.org/10.1093/ndt/gfw010CrossRefPubMed

10.

Liu X, Li N-S, Lv L-S, Huang J-H, Tang H, Chen J-X, Ma H-J, Wu X-M, Lou T-Q (2013) A comparison of the performances of an artificial neural network and a regression model for GFR Estimation. Am J Kidney Dis 62(6):1109–1115. https://doi.org/10.1053/j.ajkd.2013.07.010CrossRefPubMed

11.

Liu X, Pei X, Li N, Zhang Y, Zhang X, Chen J, Lv L, Ma H, Wu X, Zhao W, Lou T (2013) Improved glomerular filtration rate estimation by an artificial neural network. PLoS ONE 8(3):e58242. https://doi.org/10.1371/journal.pone.0058242CrossRefPubMedPubMedCentral

12.

Liu X, Li N, Lv L, Fu Y, Cheng C, Wang C, Ye Y, Li S, Lou T (2017) Improving precision of glomerular filtration rate estimating model by ensemble learning. J Transl Med 15(1):231. https://doi.org/10.1186/s12967-017-1337-yCrossRefPubMedPubMedCentral

13.

Liu X, Chen Y-R, Li N-S, Wang C, Lv L-S, Li M, Wu X-M, Lou T-Q (2013) Estimation of glomerular filtration rate by a radial basis function neural network in patients with type-2 diabetes mellitus. BMC Nephrol 14(1):181. https://doi.org/10.1186/1471-2369-14-181CrossRefPubMedPubMedCentral

14.

Libbrecht MW, Noble WS (2015) Machine learning applications in genetics and genomics. Nat Rev Genet 16:321. https://doi.org/10.1038/nrg3920CrossRefPubMedPubMedCentral

15.

Käll L, Canterbury JD, Weston J, Noble WS, MacCoss MJ (2007) Semi-supervised learning for peptide identification from shotgun proteomics datasets. Nat Methods 4:923. https://doi.org/10.1038/nmeth1113CrossRefPubMed

16.

Hafez D, Karabacak A, Krueger S, Hwang Y-C, Wang L-S, Zinzen RP, Ohler U (2017) McEnhancer: predicting gene expression via semi-supervised assignment of enhancers to target genes. Genome Biol 18(1):199. https://doi.org/10.1186/s13059-017-1316-xCrossRefPubMedPubMedCentral

17.

He Z, Liu L, Wang K, Ionita-Laza I (2018) A semi-supervised approach for predicting cell-type specific functional consequences of non-coding variation using MPRAs. Nat Commun 9(1):5199. https://doi.org/10.1038/s41467-018-07349-wCrossRefPubMedPubMedCentral

18.

Nguyen P, Braun R (2017) Semi-supervised network inference using simulated gene expression dynamics. Bioinformatics 34(7):1148–1156. https://doi.org/10.1093/bioinformatics/btx748CrossRefPubMedCentral

19.

Yang F, Shen H-B, Zhang Y, Xu Y-Y (2014) Bioimaging-based detection of mislocalized proteins in human cancers by semi-supervised learning. Bioinformatics 31(7):1111–1119. https://doi.org/10.1093/bioinformatics/btu772CrossRefPubMedPubMedCentral

20.

Gassman JJ, Greene T, Wright JT, Agodoa L, Bakris G, Beck GJ, Douglas J, Jamerson K, Lewis J, Kutner M, Randall OS, Wang S-R (2003) Design and statistical aspects of the african american study of kidney disease and hypertension (AASK). J Am Soc Nephrol 14(suppl 2):S154–S165. https://doi.org/10.1097/01.Asn.0000070080.21680.CbCrossRefPubMed

21.

Feldman HI, Appel LJ, Chertow GM, Cifelli D, Cizman B, Daugirdas J, Fink JC, Franklin-Becker ED, Go AS, Hamm LL, He J, Hostetter T, Hsu C-y, Jamerson K, Joffe M, Kusek JW, Landis JR, Lash JP, Miller ER, Mohler ER, Muntner P, Ojo AO, Rahman M, Townsend RR, Wright JT (2003) The Chronic Renal Insufficiency Cohort (CRIC) Study: Design and Methods. J Am Soc Nephrol 14(suppl 2):S148–S153. https://doi.org/10.1097/01.Asn.0000070149.78399.CeCrossRefPubMed

22.

Group TDR (1986) The Diabetes Control and Complications Trial (DCCT): Design and Methodologic Considerations for the Feasibility Phase. Diabetes 35(5):530–545. https://doi.org/10.2337/diab.35.5.530CrossRef

23.

Greene T, Bourgoignie JJ, Habwe V, Kusek JW, Snetselaar LG, Soucie JM, Yamamoto ME (1993) Baseline characteristics in the Modification of Diet in Renal Disease Study. J Am Soc Nephrol 4(5):1221–1236CrossRefPubMed

24.

Chapman AB, Guay-Woodford LM, Grantham JJ, Torres VE, Bae KT, Baumgarten DA, Kenney PJ, King BF, Glockner JF, Wetzel LH, Brummer ME, Charles O’Neill W, Robbin ML, Bennett WM, Klahr S, Hirschman GH, Kimmel PL, Thompson PA, Philip Miller J (2003) Renal structure in early autosomal-dominant polycystic kidney disease (ADPKD): The Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) cohort1. Kidney Int 64(3):1035–1045. https://doi.org/10.1046/j.1523-1755.2003.00185.xCrossRefPubMed

25.

Levey AS, Stevens LA, Schmid CH et al (2009) A new equation to estimate glomerular filtration rate. Ann Intern Med 150(9):604–612. https://doi.org/10.7326/0003-4819-150-9-200905050-00006CrossRefPubMedPubMedCentral

26.

Valpola H (2015) From neural PCA to deep unsupervised learning. In: Advances in Independent Component Analysis and Learning Machines. Elsevier, pp 143–171

27.

Rasmus A, Berglund M, Honkala M, Valpola H, Raiko T Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems, 2015. pp 3546–3554

28.

Pezeshki M, Fan L, Brakel P, Courville A, Bengio Y Deconstructing the ladder network architecture. In: International Conference on Machine Learning, 2016. pp 2368–2376

29.

Efron B, Tibshirani RJ (1994) An introduction to the bootstrap. CRC Press, New YorkCrossRef

30.

Davison AC, Hinkley DV (1997) Bootstrap methods and their application, vol 1. Cambridge University Press, New YorkCrossRef

31.

Carpenter J, Bithell J (2000) Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians. Stat Med 19(9):1141–1164. https://doi.org/10.1002/(SICI)1097-0258(20000515)19:9%3c1141::AID-SIM479%3e3.0.CO;2-FCrossRefPubMed

32.

Cockcroft DW, Gault MH (1976) Prediction of creatinine clearance from serum creatinine. Nephron 16(1):31–41. https://doi.org/10.1159/000180580CrossRefPubMed

33.

Levey AS, Bosch JP, Lewis J et al (1999) A more accurate method to estimate glomerular filtration rate from serum creatinine: a new prediction equation. Ann Intern Med 130(6):461–470. https://doi.org/10.7326/0003-4819-130-6-199903160-00002CrossRefPubMed

34.

Levey AS, Greene T, Kusek JW, Beck GJ (2000) A simplified equation to predict glomerular filtration rate from serum creatinine. J Am Soc Nephrol 11:155A

35.

Levey AS, Coresh J, Greene T et al (2006) Using standardized serum creatinine values in the modification of diet in renal disease study equation for estimating glomerular filtration rate. Ann Intern Med 145(4):247–254. https://doi.org/10.7326/0003-4819-145-4-200608150-00004CrossRefPubMed

36.

Stevens LA, Coresh J, Greene T, Levey AS (2006) Assessing kidney function—measured and estimated glomerular filtration rate. N Engl J Med 354(23):2473–2483. https://doi.org/10.1056/NEJMra054415CrossRefPubMed

37.

Björk J, Grubb A, Larsson A, Hansson L-O, Flodin M, Sterner G, Lindström V, Nyman U (2015) Accuracy of GFR estimating equations combining standardized cystatin C and creatinine assays: a cross-sectional study in Sweden. Clin Chem Lab Med (CCLM) 53(3):403–414. https://doi.org/10.1515/cclm-2014-0578CrossRef

38.

Inker LA, Tighiouart H, Coresh J, Foster MC, Anderson AH, Beck GJ, Contreras G, Greene T, Karger AB, Kusek JW, Lash J, Lewis J, Schelling JR, Navaneethan SD, Sondheimer J, Shafi T, Levey AS (2016) GFR Estimation Using β-Trace Protein and β2-Microglobulin in CKD. Am J Kidney Dis 67(1):40–48. https://doi.org/10.1053/j.ajkd.2015.07.025CrossRefPubMed

39.

Filler G, Huang S-HS, Lindsay RM (2016) The Search for More Reliable Estimated GFR Biomarkers. Am J Kidney Dis 67(1):5–8. https://doi.org/10.1053/j.ajkd.2015.10.004CrossRefPubMed

40.

Karger AB, Inker LA, Coresh J, Levey AS, Eckfeldt JH (2017) Novel Filtration Markers for GFR Estimation. EJIFCC 28(4):277–288PubMedPubMedCentral

41.

Inker LA, Eckfeldt J, Levey AS, Leiendecker-Foster C, Rynders G, Manzi J, Waheed S, Coresh J (2011) Expressing the CKD-EPI (Chronic Kidney Disease Epidemiology Collaboration) cystatin C equations for estimating GFR with standardized serum cystatin C values. Am J Kidney Dis 58(4):682–684CrossRefPubMedPubMedCentral

42.

Janowitz T, Williams EH, Marshall A, Ainsworth N, Thomas PB, Sammut SJ, Shepherd S, White J, Mark PB, Lynch AG (2017) New model for estimating glomerular filtration rate in patients with cancer. J Clin Oncol 35(24):2798CrossRefPubMedPubMedCentral

43.

Pottel H, Hoste L, Dubourg L, Ebert N, Schaeffner E, Eriksen BO, Melsom T, Lamb EJ, Rule AD, Turner ST (2016) An estimated glomerular filtration rate equation for the full age spectrum. Nephrol Dial Transplant 31(5):798–806CrossRefPubMedPubMedCentral

44.

Pottel H, Delanaye P, Schaeffner E, Dubourg L, Eriksen BO, Melsom T, Lamb EJ, Rule AD, Turner ST, Glassock RJ (2017) Estimating glomerular filtration rate for the full age spectrum from serum creatinine and cystatin C. Nephrol Dial Transplant 32(3):497–507PubMedPubMedCentral

45.

Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2(4):303–314. https://doi.org/10.1007/bf02551274CrossRef

46.

Myers GL, Miller WG, Coresh J, Fleming J, Greenberg N, Greene T, Hostetter T, Levey AS, Panteghini M, Welch M, Eckfeldt JH (2006) Recommendations for Improving Serum Creatinine Measurement: A Report from the Laboratory Working Group of the National Kidney Disease Education Program. Clin Chem 52(1):5–18. https://doi.org/10.1373/clinchem.2005.0525144CrossRefPubMed

Titel: Improving glomerular filtration rate estimation by semi-supervised learning: a development and external validation study
verfasst von: Ningshan Li
Hui Huang
Lv Linsheng
Hui Lu
Xun Liu
Publikationsdatum: 12.03.2021
Verlag: Springer Netherlands
Erschienen in: International Urology and Nephrology / Ausgabe 8/2021
Print ISSN: 0301-1623
Elektronische ISSN: 1573-2584
DOI: https://doi.org/10.1007/s11255-020-02771-w

Leitlinien kompakt für die Innere Medizin

Mit medbee Pocketcards sicher entscheiden.

^{Seit 2022 gehört die medbee GmbH zum Springer Medizin Verlag}

Kostenlos registrieren

Neu im Fachgebiet Innere Medizin

„Überwältigende“ Evidenz für Tripeltherapie beim metastasierten Prostata-Ca.

22.05.2024 Prostatakarzinom Nachrichten

Patienten mit metastasiertem hormonsensitivem Prostatakarzinom sollten nicht mehr mit einer alleinigen Androgendeprivationstherapie (ADT) behandelt werden, mahnt ein US-Team nach Sichtung der aktuellen Datenlage. Mit einer Tripeltherapie haben die Betroffenen offenbar die besten Überlebenschancen.

So sicher sind Tattoos: Neue Daten zur Risikobewertung

22.05.2024 Melanom Nachrichten

Das größte medizinische Problem bei Tattoos bleiben allergische Reaktionen. Melanome werden dadurch offensichtlich nicht gefördert, die Farbpigmente könnten aber andere Tumoren begünstigen.

CAR-M-Zellen: Warten auf das große Fressen

22.05.2024 Onkologische Immuntherapie Nachrichten

Auch myeloide Immunzellen lassen sich mit chimären Antigenrezeptoren gegen Tumoren ausstatten. Solche CAR-Fresszell-Therapien werden jetzt für solide Tumoren entwickelt. Künftig soll dieser Prozess nicht mehr ex vivo, sondern per mRNA im Körper der Betroffenen erfolgen.

Frühzeitige HbA1c-Kontrolle macht sich lebenslang bemerkbar

22.05.2024 Typ-2-Diabetes Nachrichten

Menschen mit Typ-2-Diabetes von Anfang an intensiv BZ-senkend zu behandeln, wirkt sich positiv auf Komplikationen und Mortalität aus – und das offenbar lebenslang, wie eine weitere Nachfolgeuntersuchung der UKPD-Studie nahelegt.

Update Innere Medizin

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Die Highlights vom Kongress des American College of Cardiology 2024

Springer Medizin

Abstract

Background

Methods

Results

Conclusions

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 8/2021

Entacapone scavenges peroxynitrite and protects against kidney and liver injuries induced by renal ischemia/reperfusion in rats

Effectiveness of renal-specific oral nutritional supplements compared with diet counseling in malnourished hemodialysis patients

Differentiation and proliferation of spermatogonial stem cells using a three-dimensional decellularized testicular scaffold: a new method to study the testicular microenvironment in vitro

Herbal nutraceutical treatment of chronic prostatitis–chronic pelvic pain syndrome: a literature review

Systemic inflammation response index predicts all-cause mortality in patients with antineutrophil cytoplasmic antibody-associated vasculitis

The prevalence and associated factors of nonadherence to antihypertensive medication in secondary healthcare