AbstractMinimal change disease (MCD) is a common cause of nephrotic syndrome. Due to its rapid progression, early detection is essential; however, definitive diagnosis requires invasive kidney biopsy. This study aims to develop non-invasive predictive models for diagnosing MCD by machine learning. We retrospectively collected data on demographic characteristics, blood tests, and urine tests from patients with nephrotic syndrome who underwent kidney biopsy.

摘要微小病变（MCD）是肾病综合征的常见原因。由于其进展迅速，早期发现至关重要；。本研究旨在通过机器学习开发用于诊断MCD的非侵入性预测模型。我们回顾性收集了接受肾脏活检的肾病综合征患者的人口统计学特征，血液检查和尿液检查数据。

We applied four machine learning algorithms—TabPFN, LightGBM, Random Forest, and Artificial Neural Network—and logistic regression. We compared their performance using stratified 5-repeated 5-fold cross-validation for the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).

我们应用了四种机器学习算法TabPFN，LightGBM，随机森林，人工神经网络和逻辑回归。我们使用分层5次重复的5倍交叉验证对受试者工作特征曲线（AUROC）下的面积和精确召回曲线（AUPRC）下的面积进行了比较。

Variable importance was evaluated using the SHapley Additive exPlanations (SHAP) method. A total of 248 patients were included, with 82 cases (33%) were diagnosed with MCD. TabPFN demonstrated the best performance with an AUROC of 0.915 (95% CI 0.896–0.932) and an AUPRC of 0.840 (95% CI 0.807–0.872).

使用SHapley加法解释（SHAP）方法评估变量重要性。共纳入248例患者，其中82例（33%）被诊断为MCD。TabPFN表现出最佳的性能，AUROC为0.915（95%CI为0.896-0.932），AUPRC为0.840（95%CI为0.807-0.872）。

The SHAP methods identified C3, total cholesterol, and urine red blood cells as key predictors for TabPFN, consistent with previous reports. Machine learning models could be valuable non-invasive diagnostic tools for MCD..

SHAP方法确定C3，总胆固醇和尿红细胞是TabPFN的关键预测因子，与以前的报道一致。机器学习模型可能是MCD的有价值的非侵入性诊断工具。。

IntroductionMinimal change disease (MCD) is one of the primary causes of nephrotic syndrome in adults worldwide1. Unlike most other causes of nephrotic syndrome, which progress over weeks to months, MCD is characterized by a rapid onset worsening from a few days to 1–2 weeks. Approximately 25–35% of MCD patients develop acute kidney injury, and in severe cases, urgent hemodialysis may be required2,3.

引言微小病变（MCD）是全球成年人肾病综合征的主要原因之一1。与肾病综合征的大多数其他原因不同，它会持续数周至数月，MCD的特征是从几天到1-2周迅速恶化。大约25-35%的MCD患者发生急性肾损伤，在严重的情况下，可能需要紧急血液透析2,3。

Due to its rapid onset, early diagnosis and timely treatment are crucial for a good prognosis in MCD patients. The diverse causes of nephrotic syndrome in adults make diagnosing MCD through general clinical tests challenging, thus requiring definitive diagnosis via kidney biopsy. However, kidney biopsy has several contraindications and carries risks of severe complications like bleeding, arteriovenous fistulas, and infections4,5.

由于其发病迅速，早期诊断和及时治疗对于MCD患者的良好预后至关重要。成人肾病综合征的多种原因使得通过一般临床试验诊断MCD具有挑战性，因此需要通过肾脏活检进行明确诊断。然而，肾活检有几种禁忌症，并有出血，动静脉瘘和感染等严重并发症的风险4,5。

Furthermore, since it takes time to obtain biopsy results, the condition may rapidly worsen if immediate treatment cannot be administered during this period. Therefore, there is an urgent need to explore non-invasive and practical diagnostic methods for MCD.The potential for diagnosing MCD before or without kidney biopsy through non-invasive diagnostic approaches using blood and urine biomarkers has been discussed.

此外，由于需要时间才能获得活检结果，如果在此期间无法立即进行治疗，病情可能会迅速恶化。因此，迫切需要探索MCD的非侵入性和实用的诊断方法。已经讨论了使用血液和尿液生物标志物通过非侵入性诊断方法在肾活检之前或之后诊断MCD的潜力。

Serum IL-12p40, urinary CD80, urinary fatty acid-binding protein 4, and urinary epidermal growth factor are among the biomarkers expected to distinguish MCD from other diseases6,7,8,9,10. However, these biomarkers cannot yet be measured in general medical facilities without advanced equipment, so their clinical utility remains uncertain.

血清IL-12p40，尿CD80，尿脂肪酸结合蛋白4和尿表皮生长因子是预期将MCD与其他疾病区分开来的生物标志物6,7,8,9,10。然而，如果没有先进的设备，这些生物标志物还不能在一般医疗设施中进行测量，因此它们的临床应用仍然不确定。

Currently, no single parameter measured in clinical settings stands out as a strong disease-specific predictor11,12,13. Therefore, it is crucial to combine various parameters for a comprehensive assessme.

目前，在临床环境中没有一个单一的参数可以作为强有力的疾病特异性预测因子11,12,13。因此，将各种参数结合起来进行综合评估至关重要。

Data availability

数据可用性

The dataset cannot be disclosed as approval has not been received from the Ethics Committee of St. Marianna University Hospital. The code for analysis on the development and evaluation of the models is available at the following GitHub link: https://github.com/Ryunosuke1219/MCD-diagnostic-prediction..

该数据集无法披露，因为尚未获得圣马里亚纳大学医院伦理委员会的批准。有关模型开发和评估的分析代码，请访问以下GitHub链接：https://github.com/Ryunosuke1219/MCD-diagnostic-prediction..

ReferencesCameron, J. S. The nephrotic syndrome and its complications. Am. J. Kidney Dis.10, 157–171 (1987).PubMed

参考文献Cameron，J.S。肾病综合征及其并发症。《美国肾脏杂志》10157-171（1987）。PubMed出版社

Google Scholar

谷歌学者

Smith, J. D. & Hayslett, J. P. Reversible renal failure in the nephrotic syndrome. Am. J. Kidney Dis.19, 201–213 (1992).PubMed

Smith，J.D。＆Hayslett，J.P。肾病综合征的可逆性肾衰竭。《美国肾脏杂志》第19201-213页（1992年）。PubMed出版社

Google Scholar

谷歌学者

Waldman, M. et al. Adult minimal-change disease: clinical characteristics, treatment, and outcomes. Clin. J. Am. Soc. Nephrol.2, 445–453 (2007).PubMed

Waldman，M.等人，《成人微小病变：临床特征、治疗和结果》。临床。J、 《美国社会学杂志》，第2445-453页（2007年）。PubMed出版社

Google Scholar

谷歌学者

Poggio, E. D. et al. Systematic review and meta-analysis of native kidney biopsy complications. Clin. J. Am. Soc. Nephrol.15, 1595 (2020).PubMed

Poggio，E.D.等人。天然肾活检并发症的系统评价和荟萃分析。临床。J、 《美国社会学》Nephrol.151595（2020）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Andrulli, S. et al. The risks associated with percutaneous native kidney biopsies: a prospective study. Nephrol. Dial. Transpl.38, 655–663 (2023).

Andrulli，S.等人。经皮天然肾活检相关风险：一项前瞻性研究。肾。拨号。Transpl.38655-663（2023）。

Google Scholar

谷歌学者

Bai, M. et al. Serum IL-12p40: a novel biomarker for early prediction of minimal change disease relapse following glucocorticoids therapy. Front. Med. 9, (2022).Garin, E. H. et al. Urinary CD80 is elevated in minimal change disease but not in focal segmental glomerulosclerosis. Kidney Int.78, 296–302 (2010).PubMed .

Bai，M。等人。血清IL-12p40：一种用于早期预测糖皮质激素治疗后微小变化疾病复发的新型生物标志物。正面。医学9，（2022）。Garin，E.H。等人。尿CD80在微小病变疾病中升高，但在局灶性节段性肾小球硬化症中不升高。肾脏Int.78296-302（2010）。PubMed。

Google Scholar

谷歌学者

Ling, C. et al. Urinary CD80 levels as a diagnostic biomarker of minimal change disease. Pediatr. Nephrol.30, 309–316 (2015).PubMed

Ling，C。等人。尿CD80水平作为微小变化疾病的诊断生物标志物。儿科。Nephrol.30309-316（2015）。PubMed出版社

Google Scholar

谷歌学者

Tanaka, M. et al. Significance of urinary fatty acid-binding protein 4 level as a possible biomarker for the identification of minimal change disease in patents with nephrotic-range proteinuria. BMC Nephrol.21, 459 (2020).PubMed

Tanaka，M.等人，《尿脂肪酸结合蛋白4水平作为鉴定肾病范围蛋白尿专利中微小变化疾病的可能生物标志物的意义》，BMC Nephrol.21459（2020）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lodeweyckx, N., Wouters, K., Ledeganck, K. J. & Trouet, D. Biopsy or Biomarker? Children With Minimal Change Disease Have a Distinct Profile of Urinary Epidermal Growth Factor. Front. Pediatr. 9, (2021).Segarra-Medrano, A. et al. Biological markers of nephrotic syndrome: A few steps forward in the long way.

Lodeweyckx，N.，Wouters，K.，Ledeganck，K.J。＆Trouet，D。活检或生物标志物？患有微小变化疾病的儿童具有明显的尿表皮生长因子特征。正面。儿科。9，（2021年）。Segarra Medrano，A.等人，《肾病综合征的生物学标志物：在漫长的道路上向前迈进了几步》。

Nefrologia32, 558–572 (2012).PubMed .

肾脏病学32558-572（2012）。PubMed。

Google Scholar

谷歌学者

Cara-Fuentes, G. & Smoyer, W. E. Biomarkers in pediatric glomerulonephritis and nephrotic syndrome. Pediatr. Nephrol. Berl Ger.36, 2659–2673 (2021).

Cara Fuentes，G。＆Smoyer，W.E。小儿肾小球肾炎和肾病综合征的生物标志物。儿科。肾。Berl Ger.362659-2673（2021）。

Google Scholar

谷歌学者

Weening, J. J. Will laboratory markers replace kidney biopsy in patients with nephrotic syndrome? Neth. J. Med.70, 107–108 (2012).ADS

Weening，J.J。实验室标记物会替代肾病综合征患者的肾活检吗？内特。J、 Med.70107-108（2012）。广告

PubMed

PubMed

Google Scholar

谷歌学者

Yan, G. et al. Establishment of a novel nomogram for the clinically diagnostic prediction of minimal change disease, –a common cause of nephrotic syndrome. BMC Nephrol.21, 396 (2020).PubMed

Yan，G.等人。建立一种新的列线图，用于临床诊断预测微小变化疾病，这是肾病综合征的常见原因。BMC Nephrol.21396（2020）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wu, F. et al. Development and validation of a discrimination model between primary PLA2R-negative membranous nephropathy and minimal change disease confirmed by renal biopsy. Sci. Rep.11, 18064 (2021).ADS

Wu，F。等人。原发性PLA2R阴性膜性肾病与肾活检证实的微小变化疾病之间鉴别模型的开发和验证。科学。Rep.1118064（2021）。广告

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zhu, H. et al. A diagnostic model for minimal change disease based on biological parameters. PeerJ. 6, e4237 (2018).PubMed

朱，H。等。基于生物学参数的微小变化疾病诊断模型。PeerJ.6，e4237（2018）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Goldstein, B. A., Navar, A. M. & Carter, R. E. Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. Eur. Heart J.38, 1805–1814 (2017).PubMed

Goldstein，B.A.，Navar，A.M。＆Carter，R.E。超越心血管风险预测中的回归技术：应用机器学习来解决分析挑战。《欧洲心脏杂志》381805-1814（2017）。PubMed出版社

Google Scholar

谷歌学者

Wong, J., Horwitz, M. M., Zhou, L. & Toh, S. Using machine learning to identify health outcomes from electronic health record data. Curr. Epidemiol. Rep.5, 331–342 (2018).PubMed

Wong，J.，Horwitz，M.M.，Zhou，L。＆Toh，S。使用机器学习从电子健康记录数据中识别健康结果。货币。流行病。Rep.5331–342（2018）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Hobensack, M., Song, J., Scharp, D., Bowles, K. H. & Topaz, M. Machine learning applied to electronic health record data in home healthcare: a scoping review. Int. J. Med. Inf.170, 104978 (2023).

Hobensack，M.，Song，J.，Scharp，D.，Bowles，K.H。＆Topaz，M。机器学习应用于家庭医疗保健中的电子健康记录数据：范围界定评论。《国际医学杂志》Inf.170104978（2023）。

Google Scholar

谷歌学者

Tomašev, N. et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 572, 116–119 (2019).ADS

Tomašev，N.等人。一种连续预测未来急性肾损伤的临床适用方法。自然。572116-119（2019）。广告

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kanda, E., Epureanu, B. I., Adachi, T. & Kashihara, N. Machine-learning-based web system for the prediction of chronic kidney disease progression and mortality. PLOS Digit. Health. 2, e0000188 (2023).PubMed

Kanda，E.，Epureanu，B.I.，Adachi，T。＆Kashihara，N。基于机器学习的网络系统，用于预测慢性肾脏疾病的进展和死亡率。PLOS数字。健康。2，e0000188（2023）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Noda, R., Ichikawa, D. & Shibagaki, Y. Machine learning-based diagnostic prediction of IgA nephropathy: Model development and validation study. Sci. Rep.14, 12426 (2024).ADS

Noda，R.，Ichikawa，D。和Shibagaki，Y。基于机器学习的IgA肾病诊断预测：模型开发和验证研究。科学。Rep.141426（2024年）。广告

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lee, H. et al. Deep learning model for real-time prediction of intradialytic hypotension. Clin. J. Am. Soc. Nephrol.16, 396 (2021).PubMed

。临床。J、 《美国社会学杂志》第16396页（2021年）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Collins, G. S. et al. TRIPOD + AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ e078378 (2024).Luo, W. et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: A multidisciplinary view.

Collins，G.S.等人，《TRIPOD+ AI声明：报告使用回归或机器学习方法的临床预测模型的更新指南》。。Luo，W.等人。生物医学研究中开发和报告机器学习预测模型的指南：多学科观点。

J. Med. Internet Res.18, e323 (2016).PubMed .

《医学与互联网研究杂志》第18期，第323页（2016年）。PubMed。

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Matsuo, S. et al. Revised equations for estimated GFR from serum creatinine in Japan. Am. J. Kidney Dis.53, 982–992 (2009).PubMed

Matsuo，S.等人修订了日本血清肌酐估计GFR的方程式。《美国肾脏杂志》53982-992（2009）。PubMed出版社

Google Scholar

谷歌学者

Peduzzi, P., Concato, J., Kemper, E., Holford, T. R. & Feinstein, A. R. A simulation study of the number of events per variable in logistic regression analysis. J. Clin. Epidemiol.49, 1373–1379 (1996).PubMed

Peduzzi，P.，Concato，J.，Kemper，E.，Holford，T.R。＆Feinstein，A.R。逻辑回归分析中每个变量事件数量的模拟研究。J、 临床。Epidemiol.491373-1379（1996）。PubMed出版社

Google Scholar

谷歌学者

Hollmann, N., Müller, S., Eggensperger, K. & Hutter, F. TabPFN: A transformer that solves small tabular classification problems in a second. Preprint at (2023). http://arxiv.org/abs/2207.01848Ke, G. et al. LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems vol.

Hollmann，N.，Müller，S.，Eggensperger，K。＆Hutter，F。TabPFN：一种变压器，可以在一秒钟内解决小的表格分类问题。预印本（2023）。http://arxiv.org/abs/2207.01848Ke，G。等人。LightGBM：一种高效的梯度提升决策树。。

30 (Curran Associates, Inc.; 2017).Breiman, L. Random forests. Mach. Learn.45, 5–32 (2001)..

30（Curran Associates，Inc.；2017）。。马赫。学习.45，5-32（2001）。。

Google Scholar

谷歌学者

Jain, A. K., Mao, J. & Mohiuddin, K. M. Artificial neural networks: A tutorial. Computer29, 31–44 (1996).

Jain，A.K.，Mao，J。和Mohiuddin，K.M。人工神经网络：教程。计算机29，31-44（1996）。

Google Scholar

谷歌学者

Cox, D. R. The regression analysis of binary sequences. J. R Stat. Soc. Ser. B Methodol.20, 215–242 (1958).MathSciNet

Cox，D.R。二元序列的回归分析。J、 R统计Soc序列。B Methodol.20215-242（1958）。数学网

Google Scholar

谷歌学者

Carrington, A. M. et al. Deep ROC analysis and AUC as balanced average accuracy, for improved classifier selection, audit and explanation. IEEE Trans. Pattern Anal. Mach. Intell.45, 329–341 (2023).PubMed

Carrington，A.M.等人。深度ROC分析和AUC作为平衡的平均准确度，用于改进分类器的选择，审核和解释。。模式肛门。马赫。Intell.45329-341（2023）。PubMed出版社

Google Scholar

谷歌学者

Lundberg, S. M. & Lee, S. I. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, 4768–4777, (Curran Associates Inc.; 2017).Hsiao, C. C. et al. (2018) Immunoglobulin E and G levels in predicting minimal change disease before renal biopsy.

Lundberg，S.M。和Lee，S.I。解释模型预测的统一方法。在第31届神经信息处理系统国际会议论文集，4768-4777，（Curran Associates Inc.；2017）。Hsiao，C.C.等人（2018）免疫球蛋白E和G水平在肾活检前预测微小变化疾病。

BioMed. Res. Int.2018, 1–6.Shao, Y. N. et al. Serum immunoglobulin E can predict minimal change disease before renal biopsy. Am. J. Med. Sci.338, 264–267 (2009).PubMed .

生物医学。Res.Int.2018，1-6.Shao，Y.N.等人。血清免疫球蛋白E可以预测肾活检前的微小变化疾病。《美国医学杂志》科学338264-267（2009）。PubMed。

Google Scholar

谷歌学者

Caruana, R. & Niculescu-Mizil, A. An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd International Conference on Machine Learning - ICML ’06 161–168 (ACM Press; 2006).Fernández-Delgado, M., Cernadas, E., Barro, S. & Amorim, D. Do we need hundreds of classifiers to solve real world classification problems?.

。在2006年第23届国际机器学习会议论文集161-168（ACM出版社；2006年）。Fernández-Delgado，M.，Cernadas，E.，Barro，S。＆Amorim，D。我们需要数百个分类器来解决现实世界的分类问题吗？。

J. Mach. Learn. Res.15, 3133–3181 (2014).MathSciNet .

J、 马赫。学习。第153133-3181号决议（2014年）。MathSciNet。

Google Scholar

谷歌学者

Karabacak, M., Jagtiani, P., Carrasquilla, A., Shrivastava, R. K. & Margetis, K. Advancing personalized prognosis in atypical and anaplastic meningiomas through interpretable machine learning models. J. Neurooncol.164, 671–681 (2023).PubMed

Karaback，M.，Jagtiani，P.，Carrasquilla，A.，Shrivastava，R.K。＆Margetis，K。通过可解释的机器学习模型推进非典型和间变性脑膜瘤的个性化预后。J、 Neuroncol.164671-681（2023）。PubMed出版社

Google Scholar

谷歌学者

Karabacak, M. & Margetis, K. Development of personalized machine learning-based prediction models for short-term postoperative outcomes in patients undergoing cervical laminoplasty. Eur. Spine J.32, 3857–3867 (2023).PubMed

Karaback，M。＆Margetis，K。开发基于个性化机器学习的预测模型，用于接受颈椎管成形术的患者的短期术后结果。欧洲脊柱杂志323857-3867（2023）。PubMed出版社

Google Scholar

谷歌学者

Karabacak, M. et al. Development and internal validation of machine learning models for personalized survival predictions in spinal cord glioma patients. Spine J.24, 1065–1076 (2024).PubMed

Karaback，M.等人。用于脊髓胶质瘤患者个性化生存预测的机器学习模型的开发和内部验证。脊柱J.241065-1076（2024）。PubMed出版社

Google Scholar

谷歌学者

Cui, Z. & Gong, G. The effect of machine learning regression algorithms and sample size on individualized behavioral prediction with functional connectivity features. NeuroImage. 178, 622–637 (2018).PubMed

Cui，Z。＆Gong，G。机器学习回归算法和样本量对具有功能连通性特征的个性化行为预测的影响。神经影像。178622-637（2018）。PubMed出版社

Google Scholar

谷歌学者

Raudys, S. J. & Jain, A. K. Small sample size effects in statistical pattern recognition: Recommendations for practitioners. IEEE Trans. Pattern Anal. Mach. Intell.13, 252–264 (1991).

Raudys，S.J.＆Jain，A.K。统计模式识别中的小样本效应：对从业者的建议。。模式肛门。马赫。Intell.13252-264（1991）。

Google Scholar

谷歌学者

Thorsen-Meyer, H. C. et al. Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: A retrospective study of high-frequency data in electronic patient records. Lancet Digit. Health2, e179–e191 (2020).PubMed

。柳叶刀数字。Health2，e179-e191（2020）。PubMed出版社

Google Scholar

谷歌学者

Hebert, L. A., Cosio, F. G. & Neff, J. C. Diagnostic significance of hypocomplementemia. Kidney Int.39, 811–821 (1991).PubMed

Hebert，L.A.，Cosio，F.G。＆Neff，J.C。低补体血症的诊断意义。肾脏Int.39811-821（1991）。PubMed出版社

Google Scholar

谷歌学者

Saeki, T. & Kawano, M. IgG4-related kidney disease. Kidney Int.85, 251–257 (2014).PubMed

Saeki，T。＆Kawano，M。IgG4相关的肾脏疾病。肾脏Int.85251-257（2014）。PubMed出版社

Google Scholar

谷歌学者

Habib, R. Focal glomerular sclerosis. Kidney Int.4, 355–361 (1973).PubMed

Habib，R。局灶性肾小球硬化。肾脏Int.4355-361（1973）。PubMed出版社

Google Scholar

谷歌学者

Korbet, S. Clinical picture and outcome of primary focal segmental glomerulosclerosis. Nephrol. Dial. Transpl.14, 68–73 (1999).

Korbet，S。原发性局灶节段性肾小球硬化的临床表现和结果。肾。拨号。Transpl.14，68-73（1999）。

Google Scholar

谷歌学者

Ozeki, T. et al. Clinical manifestations of focal segmental glomerulosclerosis in Japan from the Japan Renal Biopsy Registry: Age stratification and comparison with minimal change disease. Sci. Rep.11, 2602 (2021).PubMed

Ozeki，T.等人，《日本肾活检登记处日本局灶性节段性肾小球硬化的临床表现：年龄分层和与微小变化疾病的比较》。科学。Rep.112602（2021）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Download referencesAcknowledgementsWe sincerely appreciate Ms. Yoshiko Ono and Ms. Mami Ohori for their invaluable contributions to patient data collection. Their commitment and hard work played a crucial role in the progress of our research.Author informationAuthors and AffiliationsDivision of Nephrology and Hypertension, Department of Internal Medicine, St.

下载参考文献致谢我们衷心感谢Yoshiko Ono女士和Mami Ohori女士对患者数据收集的宝贵贡献。他们的承诺和辛勤工作在我们的研究进展中起着至关重要的作用。作者信息作者和附属机构肾脏病和高血压科，内科，St。

Marianna University School of Medicine, Miyamae-ku, Kawasaki, Kanagawa, 216-8511, JapanRyunosuke Noda, Daisuke Ichikawa & Yugo ShibagakiAuthorsRyunosuke NodaView author publicationsYou can also search for this author in.

。

PubMed Google ScholarDaisuke IchikawaView author publicationsYou can also search for this author in

PubMed谷歌学者Aisuke IchikawaView作者出版物您也可以在

PubMed Google ScholarYugo ShibagakiView author publicationsYou can also search for this author in

PubMed Google ScholarYugo ShibagakiView作者出版物您也可以在

PubMed Google ScholarContributionsR.N. designed the research plan and analyzed the data. R.N., D.I., and Y.S. participated in the writing of the paper. R.N., D.I., and Y.S. participated in approving the final manuscript.Corresponding authorCorrespondence to

PubMed谷歌学术贡献。N、 设计研究计划并分析数据。R、 N.，D.I。和Y.S.参与了论文的撰写。R、 N.，D.I。和Y.S.参与了最终手稿的批准。对应作者对应

Ryunosuke Noda.Ethics declarations

野田龙之介。道德宣言

Competing interests

相互竞争的利益

The authors declare no competing interests.

作者声明没有利益冲突。

Additional informationPublisher’s noteSpringer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Electronic supplementary materialBelow is the link to the electronic supplementary material.Supplementary Material 1Rights and permissions

Additional informationPublisher的noteSpringer Nature在已发布地图和机构隶属关系中的管辖权主张方面保持中立。电子补充材料流是指向电子补充材料的链接。补充材料1权利和许可

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material.

开放获取本文是根据知识共享署名非商业性NoDerivatives 4.0国际许可证授权的，该许可证允许以任何媒介或格式进行任何非商业性使用，共享，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出您是否修改了许可材料。

You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

根据本许可证，您无权共享源自本文或其部分的改编材料。本文中的图像或其他第三方材料包含在文章的知识共享许可证中，除非该材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by-nc-nd/4.0/..

Reprints and permissionsAbout this articleCite this articleNoda, R., Ichikawa, D. & Shibagaki, Y. Machine learning-based diagnostic prediction of minimal change disease: model development study.

转载和许可本文引用本文Noda，R.，Ichikawa，D。＆Shibagaki，Y。基于机器学习的最小变化疾病诊断预测：模型开发研究。

Sci Rep 14, 23460 (2024). https://doi.org/10.1038/s41598-024-73898-4Download citationReceived: 14 June 2024Accepted: 23 September 2024Published: 08 October 2024DOI: https://doi.org/10.1038/s41598-024-73898-4Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

科学报告1423460（2024）。https://doi.org/10.1038/s41598-024-73898-4Download引文接收日期：2024年6月14日接受日期：2024年9月23日发布日期：2024年10月8日OI：https://doi.org/10.1038/s41598-024-73898-4Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供

CommentsBy submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

评论通过提交评论，您同意遵守我们的条款和社区指南。如果您发现有虐待行为或不符合我们的条款或准则，请将其标记为不合适。