Machine learning model to estimate probability of remission in patients with idiopathic membranous nephropathy

列线图 医学 接收机工作特性 肾脏疾病 膜性肾病 内科学 蛋白尿 肾
作者
Lijin Duo,Lei Chen,Yongdi Zuo,Jiulin Guo,Manrong He,Hongsen Zhao,Yingxi Kang,Wanxin Tang
出处
期刊:International Immunopharmacology [Elsevier BV]
卷期号:125: 111126-111126 被引量:5
标识
DOI:10.1016/j.intimp.2023.111126
摘要

Idiopathic membranous nephropathy (IMN) is a type of nephrotic syndrome and the leading cause of chronic kidney disease. As far as we know, no predictive model for assessing the prognosis of IMN is currently available. This study aims to establish a nomogram to predict remission probability in patients with IMN and assists clinicians to make treatment decisions.A total of 266 patients with histopathology-proven IMN were included in this study. Least absolute shrinkage and selection operator regression was utilized to identify the most important variables. Subsequently, multivariate Cox regression analysis was conducted to construct a nomogram, and bootstrap resampling was employed for internal validation. Receiver operating characteristic and calibration curves and decision curve analysis (DCA) were utilized to assess the performance and clinical utility of the developed model.A prognostic nomogram was established, which incorporated creatinine, glomerular_basement_membrane_thickening, gender, IgG_deposition, low-density lipoprotein cholesterol, and fibrinogen. The areas under the curves of the 3-, 12-, 24-month were 0.751, 0.725, and 0.830 in the training set, and 0.729, 0.730, and 0.948 in the validation set respectively. These results and calibration curves demonstrated the good discrimination and calibration of the nomogram in the training and validation sets. Additionally, DCA indicated that the nomogram was useful for remission prediction in clinical settings.The nomogram was useful for clinicians to evaluate the prognosis of patients with IMN in early stage.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
sherry完成签到,获得积分10
刚刚
jr发布了新的文献求助10
刚刚
星辰大海的应助被小一一采纳,获得10
1秒前
1秒前
桐桐的应助被小懿采纳,获得10
1秒前
shdbdbjxj完成签到,获得积分10
2秒前
Crazy_Runner发布了新的文献求助10
2秒前
3秒前
3秒前
害羞含卉完成签到,获得积分10
3秒前
3秒前
4秒前
SUNLE发布了新的文献求助10
4秒前
666完成签到 ,获得积分10
5秒前
在水一方的应助被优雅的白山采纳,获得10
5秒前
5秒前
6秒前
shawnchen发布了新的文献求助10
6秒前
7秒前
zcadqe234完成签到,获得积分10
7秒前
什么呀完成签到,获得积分10
7秒前
科研通AI6.2的应助被jr采纳,获得10
7秒前
乐乐的应助被嘻嘻哈哈采纳,获得10
7秒前
天天快乐的应助被大力的雪珊采纳,获得30
7秒前
7秒前
Miya完成签到 ,获得积分10
8秒前
Neve发布了新的文献求助30
8秒前
8秒前
万致辰完成签到,获得积分10
8秒前
咩了个咩发布了新的文献求助10
8秒前
半夏发布了新的文献求助10
8秒前
东方教主发布了新的文献求助10
8秒前
张天虹完成签到,获得积分10
9秒前
热心市民范女士完成签到,获得积分10
9秒前
9秒前
9秒前
9秒前
9秒前
PP发布了新的文献求助100
10秒前
10秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8161403
求助须知:如何正确求助?哪些是违规求助? 9556121
关于积分的说明 21732327
捐赠科研通 7751529
什么是DOI,文献DOI怎么找? 3427556
关于科研通互助平台的介绍 2552588
邀请新用户注册赠送积分活动 2471994