Prognostic prediction of idiopathic membranous nephropathy using interpretable machine learning

References

• Gañán IN, Iturrieta-Zuazo I, Rita CG, et al. Revisiting immunological and clinical aspects of membranous nephropathy. Clin Immunol. 2022;237:1. doi: 10.1016/j.clim.2022.108976.
   Web of Science ®Google Scholar
• Xu X, Wang G, Chen N, et al. Long-term exposure to air pollution and increased risk of membranous nephropathy in China. J Am Soc Nephrol. 2016;27(12):3739–11. doi: 10.1681/ASN.2016010093.
   PubMed Web of Science ®Google Scholar
• Keri KC, Blumenthal S, Kulkarni V, et al. Primary membranous nephropathy: comprehensive review and historical perspective. Postgrad Med J. 2019;95(1119):23–31. doi: 10.1136/postgradmedj-2018-135729.
   PubMed Web of Science ®Google Scholar
• Francis JM, Beck LH, Salant DJ. Membranous nephropathy: a journey from bench to bedside. Am J Kidney Dis. 2016;68(1):138–147. doi: 10.1053/j.ajkd.2016.01.030.
   PubMed Web of Science ®Google Scholar
• McGrogan A, Franssen CFM, De Vries CS. The incidence of primary glomerulonephritis worldwide: a systematic review of the literature. Nephrol Dial Transplant. 2011;26(2):414–430. doi: 10.1093/ndt/gfq665.
   PubMed Web of Science ®Google Scholar
• Xiaofan H, Jing X, Chenni G, et al. New risk score for predicting progression of membranous nephropathy. J Transl Med. 2019;17(1):41. doi: 10.1186/s12967-019-1792-8.
   PubMedGoogle Scholar
• Cheng W, Sun L, Dong H, et al. Clinicopathologic characteristic and prognosis in idiopathic membranous nephropathy patients with focal segmental sclerosis lesion: a retrospective observational study. Medicine. 2021;100(3):e23988. doi: 10.1097/MD.0000000000023988.
   PubMed Web of Science ®Google Scholar
• Choi J-Y, Chin HJ, Lee H, et al. Idiopathic membranous nephropathy in older patients: clinical features and outcomes. PLOS One. 2020;15(10):e0240566. doi: 10.1371/journal.pone.0240566.
   PubMed Web of Science ®Google Scholar
• Chan L, Nadkarni GN, Fleming F, et al. Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease. Diabetologia. 2021;64(7):1504–1515. doi: 10.1007/s00125-021-05444-0.
   PubMed Web of Science ®Google Scholar
• Hu C, Tan Q, Zhang Q, et al. Application of interpretable machine learning for early prediction of prognosis in acute kidney injury. Comput Struct Biotechnol J. 2022;20:2861–2870. doi: 10.1016/j.csbj.2022.06.003.
   PubMed Web of Science ®Google Scholar
• Wu X, Sun Y, Xu X, et al. Mortality prediction in severe traumatic brain injury using traditional and machine learning algorithms. J Neurotrauma. 2023;40(13–14):1366–1375. doi: 10.1089/neu.2022.0221.
   PubMed Web of Science ®Google Scholar
• Couser WG. Primary membranous nephropathy. Clin J Am Soc Nephrol. 2017;12(6):983–997. doi: 10.2215/CJN.11761116.
   PubMed Web of Science ®Google Scholar
• Fitzmaurice G, Laird N. Multivariate analysis: discrete variables (logistic regression). IESBS. 2001:10221–10228. doi: 10.1016/b0-08-043076-7/00476-9.
   Google Scholar
• Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273–297. doi: 10.1007/BF00994018.
   Web of Science ®Google Scholar
• Breiman L. Random forests. Mach Learn. 2001;45(1):5–32. doi: 10.1023/A:1010933404324.
   Web of Science ®Google Scholar
• Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016 Aug; New York, NY, USA. doi: 10.1145/2939672.2939785.
   Google Scholar
• Ke G, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
   Google Scholar
• Genuer R, Poggi JM, Tuleau-Malot C. Variable selection using random forests. Pattern Recognit Lett. 2010;31(14):2225–2236. doi: 10.1016/j.patrec.2010.03.014.
   Web of Science ®Google Scholar
• Lundberg S, Erion G, Lee S-I. Consistent individualized feature attribution for tree ensembles. arXiv. 1802.03888; 2018.
   Google Scholar
• Tseng PY, Chen YT, Wang CH, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care. 2020;24(1):478. doi: 10.1186/s13054-020-03179-9.
   PubMed Web of Science ®Google Scholar
• Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:346.
   Google Scholar
• van De Logt AE, Justino J, Vink CH, et al. Anti-PLA2R1 antibodies as prognostic biomarker in membranous nephropathy. Kidney Int Rep. 2021;6(6):1677–1686. doi: 10.1016/j.ekir.2021.04.002.
   PubMed Web of Science ®Google Scholar
• Ghiggeri GM, Seitz-Polski B, Justino J, et al. Multi-autoantibody signature and clinical outcome in membranous nephropathy. Clin J Am Soc Nephrol. 2020;15(12):1762–1776. doi: 10.2215/CJN.02500220.
   PubMed Web of Science ®Google Scholar
• Du Y, Li J, He F, et al. The diagnosis accuracy of PLA2R-AB in the diagnosis of idiopathic membranous nephropathy: a meta-analysis. PLOS One. 2014;9(8):e104936. doi: 10.1371/journal.pone.0104936.
   PubMed Web of Science ®Google Scholar
• Akiyama S, Akiyama M, Imai E, et al. Prevalence of anti-phospholipase A2 receptor antibodies in Japanese patients with membranous nephropathy. Clin Exp Nephrol. 2015;19(4):653–660. doi: 10.1007/s10157-014-1054-2.
   PubMed Web of Science ®Google Scholar
• Li X, Wei D, Zhou Z, et al. Anti-PLA2R antibodies in Chinese patients with membranous nephropathy. Med Sci Monit. 2016;22:1630–1636. doi: 10.12659/MSM.896090.
   PubMed Web of Science ®Google Scholar
• Qin HZ, Zhang MC, Le WB, et al. Combined assessment of phospholipase A2 receptor autoantibodies and glomerular deposits in membranous nephropathy. J Am Soc Nephrol. 2016;27(10):3195–3203. doi: 10.1681/ASN.2015080953.
   PubMed Web of Science ®Google Scholar
• Zhang B, Cheng M, Yang M, et al. Analysis of the prognostic risk factors of idiopathic membranous nephropathy using a new surrogate end-point. Biomed Rep. 2016;4(2):147–152. doi: 10.3892/br.2015.555.
   PubMed Web of Science ®Google Scholar
• Liu B, Zhao L, Yang Q, et al. Hyperuricemia and hypertriglyceridemia indicate tubular atrophy/interstitial fibrosis in patients with IgA nephropathy and membranous nephropathy. Int Urol Nephrol. 2021;53(11):2321–2332. doi: 10.1007/s11255-021-02844-4.
   PubMed Web of Science ®Google Scholar
• Reichert LJ, Koene RA, Wetzels JF. Prognostic factors in idiopathic membranous nephropathy. Am J Kidney Dis. 1998;31(1):1–11. doi: 10.1053/ajkd.1998.v31.pm9428445.
   PubMed Web of Science ®Google Scholar
• Zhu H, Qi J, Schoepf J, et al. Prevalence and associated risk factors of pulmonary embolism in children and young adults with nephrotic syndrome: a Chinese large cohort study. J Thorac Imaging. 2021;36(5):326–332. doi: 10.1097/RTI.0000000000000603.
   PubMed Web of Science ®Google Scholar
• Liu X, Xue J, Guo X, et al. A PLA2R-IgG4 antibody-based predictive model for assessing risk stratification of idiopathic membranous nephropathy. J Healthcare Eng. 2021;2021:1–6. doi: 10.1155/2021/1521013.
   Web of Science ®Google Scholar
• Seitz-Polski B, Payré C, Ambrosetti D, et al. Prediction of membranous nephropathy recurrence after transplantation by monitoring of anti-PLA2R1 (M-type phospholipase A2 receptor) autoantibodies: a case series of 15 patients. Nephrol Dial Transplant. 2014;29(12):2334–2342. doi: 10.1093/ndt/gfu252.
   PubMed Web of Science ®Google Scholar
• Huang CC, Lehman A, Albawardi A, et al. IgG subclass staining in renal biopsies with membranous glomerulonephritis indicates subclass switch during disease progression. Mod Pathol. 2013;26(6):799–805. doi: 10.1038/modpathol.2012.237.
   PubMed Web of Science ®Google Scholar
• Zhang L, Yan X, Fan Q, et al. D‐dimer levels on admission to predict in‐hospital mortality in patients with covid‐19. J Thromb Haemost. 2020;18(6):1324–1329. doi: 10.1111/jth.14859.
   PubMed Web of Science ®Google Scholar
• Nazerian P, Mueller C, Soeiro AM, et al. Diagnostic accuracy of the aortic dissection detection risk score plus D-dimer for acute aortic syndromes: the ADvISED prospective multicenter study. Circulation. 2018;137(3):250–258. doi: 10.1161/CIRCULATIONAHA.117.029457.
   PubMed Web of Science ®Google Scholar
• Kim EY, Song KY. Prognostic value of D-dimer levels in patients with gastric cancer undergoing gastrectomy. Surg Oncol. 2021;37:101570. doi: 10.1016/j.suronc.2021.101570.
   PubMed Web of Science ®Google Scholar
• Fok JS, Kolkhir P, Church MK, et al. Predictors of treatment response in chronic spontaneous urticaria. Allergy. 2021;76(10):2965–2981. doi: 10.1111/all.14757.
   PubMed Web of Science ®Google Scholar
• Pyo JY, Yoo B, Kwon M, et al. D-dimer predicts poor hospitalisation outcomes in patients with antineutrophil cytoplasmic autoantibody-associated vasculitis. Clin Exp Rheumatol. 2021;39(2):94–100. doi: 10.55563/clinexprheumatol/4nlfpe.
   PubMed Web of Science ®Google Scholar
• Johnson ED, Schell JC, Rodgers GM. The D‐dimer assay. Am J Hematol. 2019;94(7):833–839. doi: 10.1002/ajh.25482.
   PubMed Web of Science ®Google Scholar
• RiYang L, HangYing Y, JunYan Q, et al. Association between tongue coating thickness and clinical characteristics among idiopathic membranous nephropathy patients. J Ethnopharmacol. 2015;171:125–130. doi: 10.1016/j.jep.2015.05.008.
   PubMed Web of Science ®Google Scholar
• Kaneshige H, Endoh M, Tomino Y, et al. Abnormal glucose tolerance in patients with chronic glomerulonephritis without renal failure. Diabetes Care. 1983;6(4):381–386. doi: 10.2337/diacare.6.4.381.
   PubMed Web of Science ®Google Scholar
• Liu L, Zuo K, Le W, et al. Non-diabetic urine glucose in idiopathic membranous nephropathy. Ren Fail. 2022;44(1):1105–1112. doi: 10.1080/0886022X.2022.2094806.
   Web of Science ®Google Scholar
• Jin J, Jin B, Huang S, et al. Insulin resistance in children with primary nephrotic syndrome and normal renal function. Pediatr Nephrol. 2012;27(10):1901–1909. doi: 10.1007/s00467-012-2190-0.
   PubMed Web of Science ®Google Scholar