{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:55:18Z","timestamp":1776056118779,"version":"3.50.1"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background and aim<\/jats:title>\n                    <jats:p>Idiopathic nephrotic syndrome (INS) is a glomerular disorder characterized by proteinuria, hypoalbuminemia, and edema, and relapse remains a major clinical challenge. Early prediction of relapse risk may facilitate individualized treatment and follow-up. This study aimed to develop and compare the performance of logistic regression, random forest, and deep learning models for predicting relapse in adult patients with INS using baseline clinical and laboratory data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a retrospective cohort study of 562 adult patients with idiopathic nephrotic syndrome treated between January 2022 and January 2024. The primary outcome was the first relapse within 12 months after baseline assessment. Baseline demographic characteristics, clinical history, laboratory parameters, and treatment-related variables were collected. The dataset was randomly divided into training (70%), validation (15%), and test (15%) sets. Missing data were imputed, continuous variables were standardized as appropriate, and SMOTE was applied to the training set only to address class imbalance. Three predictive models were developed: logistic regression, random forest, and a deep learning-based neural network. Model performance was evaluated using AUC, accuracy, sensitivity, specificity, and F1-score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the three models, the deep learning model showed the best predictive performance, with AUCs of 0.908, 0.900, and 0.883 in the training, validation, and test sets, respectively. The logistic regression model showed intermediate performance, whereas random forest showed the lowest discriminatory ability. The most influential predictors of relapse included steroid resistance, nephrotic-range proteinuria at baseline, prior relapse history\/frequency, elevated ESR, and immunosuppressant use.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Deep learning demonstrated better predictive performance than logistic regression and random forest for predicting 12-month relapse in adult patients with idiopathic nephrotic syndrome. These findings suggest that machine learning-based models, particularly deep learning, may serve as useful tools for relapse risk stratification. External validation in larger independent cohorts is needed before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1687315","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:36:02Z","timestamp":1776054962000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and evaluation of machine learning models for predicting relapse in idiopathic nephrotic syndrome"],"prefix":"10.3389","volume":"17","author":[{"given":"Mingrui","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Kidney Disease, General Hospital of Central Theater Command","place":["Wuhan, Hubei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Kidney Disease, General Hospital of Central Theater Command","place":["Wuhan, Hubei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Kidney Disease, General Hospital of Central Theater Command","place":["Wuhan, Hubei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Kidney Disease, General Hospital of Central Theater Command","place":["Wuhan, Hubei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.2215\/cjn.07180622","article-title":"The immune system and idiopathic nephrotic syndrome","volume":"17","author":"Campbell","year":"2022","journal-title":"Clin J Am Soc Nephrol: CJASN"},{"key":"B2","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/s0140-6736(18)30536-1","article-title":"Idiopathic nephrotic syndrome in children","volume":"392","author":"Noone","year":"2018","journal-title":"Lancet (London England)"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1055\/a-1334-2135","article-title":"Nephrotic syndrome: current understanding and future therapies","volume":"147","author":"Diefenhardt","year":"2022","journal-title":"Deutsche Medizinische Wochenschrift (1946)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.kint.2023.04.032","article-title":"Intussusception as a complication of idiopathic nephrotic syndrome","volume":"104","author":"Dreant","year":"2023","journal-title":"Kidney Int"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2024.1379924","article-title":"A novel flow cytometry panel to identify prognostic markers for steroid-sensitive forms of idiopathic nephrotic syndrome in childhood","volume":"15","author":"Riganati","year":"2024","journal-title":"Front Immunol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cca.2012.05.006","article-title":"Elevated serum \u03b22-GPI-Lp(a) complexes levels in children with nephrotic syndrome","volume":"413","author":"Zhang","year":"2012","journal-title":"Clinica Chimica Acta; Int J Clin Chem"},{"key":"B7","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","year":"2024","journal-title":"Crit Care (London England)"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104151","article-title":"Machine learning model for predicting malaria using clinical information","volume":"129","author":"Lee","year":"2021","journal-title":"Comput Biol Med"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1093\/oncolo\/oyae341","article-title":"Machine learning models for predicting postoperative peritoneal metastasis after hepatocellular carcinoma rupture: a multicenter cohort study in China","volume":"30","author":"Xia","year":"2025","journal-title":"Oncologist"},{"key":"B10","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1186\/s12874-023-01965-x","article-title":"Use and misuse of random forest variable importance metrics in medicine: demonstrations through incident stroke prediction","volume":"23","author":"Wallace","year":"2023","journal-title":"BMC Med Res Methodol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.2174\/1573396318666220314142713","article-title":"Idiopathic nephrotic syndrome in pediatrics: an up-to-date","volume":"18","author":"da Silva Filha","year":"2022","journal-title":"Curr Pediatr Rev"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1080\/20469047.2017.1374003","article-title":"Nephrotic syndrome in infants and children: pathophysiology and management","volume":"37","author":"Downie","year":"2017","journal-title":"Paediatrics Int Child Health"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/s00467-017-3793-2","article-title":"Deriving and understanding the risk of post-transplant recurrence of nephrotic syndrome in the light of current molecular and genetic advances","volume":"33","author":"Bierzynska","year":"2018","journal-title":"Pediatr Nephrol (Berlin Germany)"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fped.2019.00404","article-title":"The search for biomarkers to aid in diagnosis, differentiation, and prognosis of childhood idiopathic nephrotic syndrome","volume":"7","author":"Stone","year":"2019","journal-title":"Front Pediatr"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.2196\/47645","article-title":"Pitfalls in developing machine learning models for predicting cardiovascular diseases: challenge and solutions","volume":"26","author":"Cai","year":"2024","journal-title":"J Med Internet Res"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bios.2024.116523","article-title":"Diagnosis and classification of kidney transplant rejection using machine learning-assisted surface-enhanced Raman spectroscopy using a single drop of serum","volume":"261","author":"Lee","year":"2024","journal-title":"Biosens Bioelectron"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1038\/s41581-020-0321-6","article-title":"Digital pathology and computational image analysis in nephropathology","volume":"16","author":"Barisoni","year":"2020","journal-title":"Nat Rev Nephrol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2022.708610","article-title":"Machine learning-based prediction method for tremors induced by tacrolimus in the treatment of nephrotic syndrome","volume":"13","author":"Shao","year":"2022","journal-title":"Front Pharmacol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/s2352-4642(18)30283-9","article-title":"Management of steroid-resistant nephrotic syndrome in children and adolescents","volume":"2","author":"Tullus","year":"2018","journal-title":"Lancet Child Adolesc Health"},{"key":"B20","doi-asserted-by":"publisher","first-page":"89","DOI":"10.17305\/bjbms.2014.2270","article-title":"Retrospective mutational analysis of NPHS1, NPHS2, WT1 and LAMB2 in children with steroid-resistant focal segmental glomerulosclerosis - a single-centre experience","volume":"14","author":"Bi\u0144czak-Kuleta","year":"2014","journal-title":"Bosnian J Basic Med Sci"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s00467-019-04225-7","article-title":"Treatment of nephrotic syndrome: going beyond immunosuppressive therapy","volume":"35","author":"Zhao","year":"2020","journal-title":"Pediatr Nephrol (Berlin Germany)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1186\/1751-0473-3-17","article-title":"Purposeful selection of variables in logistic regression","volume":"3","author":"Bursac","year":"2008","journal-title":"Source Code Biol Med"},{"key":"B23","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1097\/ta.0000000000004584","article-title":"An introduction to clinical prediction models using logistic regression in acute care surgery research: methodologic considerations and common pitfalls","volume":"98","author":"Garwe","year":"2025","journal-title":"J Trauma Acute Care Surg"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"van der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"111","DOI":"10.21037\/atm.2016.02.15","article-title":"Model building strategy for logistic regression: purposeful selection","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann Trans Med"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1687315\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:36:05Z","timestamp":1776054965000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1687315\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":25,"alternative-id":["10.3389\/fendo.2026.1687315"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1687315","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]},"article-number":"1687315"}}