Prediction of the sarcopenia in peritoneal dialysis using simple clinical information: A machine learning-based model.

IF 1.4 4区医学 Q3 UROLOGY & NEPHROLOGY

Seminars in Dialysis Pub Date : 2023-09-01 Epub Date: 2023-03-08 DOI:10.1111/sdi.13131

Jiaying Wu, Shuangxiang Lin, Jichao Guan, Xiujuan Wu, Miaojia Ding, Shuijuan Shen

{"title":"Prediction of the sarcopenia in peritoneal dialysis using simple clinical information: A machine learning-based model.","authors":"Jiaying Wu, Shuangxiang Lin, Jichao Guan, Xiujuan Wu, Miaojia Ding, Shuijuan Shen","doi":"10.1111/sdi.13131","DOIUrl":null,"url":null,"abstract":"Introduction: Sarcopenia is associated with significant cardiovascular risk, and death in patients undergoing peritoneal dialysis (PD). Three tools are used for diagnosing sarcopenia. The evaluation of muscle mass requires dual energy X-ray absorptiometry (DXA) or computed tomography (CT), which is labor-intensive and relatively expensive. This study aimed to use simple clinical information to develop a machine learning (ML)-based prediction model of PD sarcopenia.Methods: According to the newly revised Asian Working Group for Sarcopenia (AWGS2019), patients were subjected to complete sarcopenia screening, including appendicular skeletal muscle mass, grip strength, and five-time chair stand time test. Simple clinical information such as general information, dialysis-related indices, irisin and other laboratory indices, and bioelectrical impedance analysis (BIA) data were collected. All data were randomly split into training (70%) and testing (30%) sets. Difference, correlation, univariate, and multivariate analyses were used to identify core features significantly associated with PD sarcopenia.Result: 12 core features (C), namely, grip strength, body mass index (BMI), total body water value, irisin, extracellular water/total body water, fat-free mass index, phase angle, albumin/globulin, blood phosphorus, total cholesterol, triglyceride, and prealbumin were excavated for model construction. Two ML models, the neural network (NN), and support vector machine (SVM) were selected with tenfold cross-validation to determine the optimal parameter. The C-SVM model showed a higher area under the curve (AUC) of 0.82 (95% confidence interval [CI]: 0.67-1.00), with a highest specificity of 0.96, sensitivity of 0.91, positive predictive value (PPV) of 0.96, and negative predictive value (NPV) of 0.91.Conclusion: The ML model effectively predicted PD sarcopenia and has clinical potential to be used as a convenient sarcopenia screening tool.","PeriodicalId":21675,"journal":{"name":"Seminars in Dialysis","volume":"36 5","pages":"390-398"},"PeriodicalIF":1.4000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Seminars in Dialysis","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/sdi.13131","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/3/8 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: Sarcopenia is associated with significant cardiovascular risk, and death in patients undergoing peritoneal dialysis (PD). Three tools are used for diagnosing sarcopenia. The evaluation of muscle mass requires dual energy X-ray absorptiometry (DXA) or computed tomography (CT), which is labor-intensive and relatively expensive. This study aimed to use simple clinical information to develop a machine learning (ML)-based prediction model of PD sarcopenia.

Methods: According to the newly revised Asian Working Group for Sarcopenia (AWGS2019), patients were subjected to complete sarcopenia screening, including appendicular skeletal muscle mass, grip strength, and five-time chair stand time test. Simple clinical information such as general information, dialysis-related indices, irisin and other laboratory indices, and bioelectrical impedance analysis (BIA) data were collected. All data were randomly split into training (70%) and testing (30%) sets. Difference, correlation, univariate, and multivariate analyses were used to identify core features significantly associated with PD sarcopenia.

Result: 12 core features (C), namely, grip strength, body mass index (BMI), total body water value, irisin, extracellular water/total body water, fat-free mass index, phase angle, albumin/globulin, blood phosphorus, total cholesterol, triglyceride, and prealbumin were excavated for model construction. Two ML models, the neural network (NN), and support vector machine (SVM) were selected with tenfold cross-validation to determine the optimal parameter. The C-SVM model showed a higher area under the curve (AUC) of 0.82 (95% confidence interval [CI]: 0.67-1.00), with a highest specificity of 0.96, sensitivity of 0.91, positive predictive value (PPV) of 0.96, and negative predictive value (NPV) of 0.91.

Conclusion: The ML model effectively predicted PD sarcopenia and has clinical potential to be used as a convenient sarcopenia screening tool.

查看原文本刊更多论文

使用简单的临床信息预测腹膜透析中少肌症：一个基于机器学习的模型。

引言：在接受腹膜透析（PD）的患者中，Sarcopenia与显著的心血管风险和死亡有关。有三种工具可用于诊断少肌症。肌肉质量的评估需要双能X射线吸收仪（DXA）或计算机断层扫描（CT），这是劳动密集型的，并且相对昂贵。本研究旨在利用简单的临床信息开发一个基于机器学习（ML）的PD少肌症预测模型。方法：根据新修订的亚洲肌肉减少症工作组（AWGS2019），对患者进行完整的肌肉减少症筛查，包括阑尾骨骼肌质量、握力和五次椅子站立时间测试。收集简单的临床信息，如一般信息、透析相关指标、虹膜素和其他实验室指标以及生物电阻抗分析（BIA）数据。所有数据被随机分为训练集（70%）和测试集（30%）。差异、相关性、单变量和多变量分析用于确定与PD少肌症显著相关的核心特征。结果：挖掘出12个核心特征（C），即握力、体重指数（BMI）、全身水分值、鸢尾素、细胞外水/全身水、无脂肪质量指数、相位角、白蛋白/球蛋白、血磷、总胆固醇、甘油三酯和前白蛋白，用于模型构建。通过十倍交叉验证选择了两个ML模型，即神经网络（NN）和支持向量机（SVM）来确定最佳参数。C-SVM模型的曲线下面积（AUC）较高，为0.82（95%置信区间[CI]:0.67-1.00），特异性最高，为0.96，灵敏度为0.91，阳性预测值（PPV）为0.96。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Seminars in Dialysis 医学-泌尿学与肾脏学

CiteScore

3.00

自引率

6.20%

发文量

审稿时长

4-8 weeks

期刊介绍： Seminars in Dialysis is a bimonthly publication focusing exclusively on cutting-edge clinical aspects of dialysis therapy. Besides publishing papers by the most respected names in the field of dialysis, the Journal has unique useful features, all designed to keep you current: -Fellows Forum -Dialysis rounds -Editorials -Opinions -Briefly noted -Summary and Comment -Guest Edited Issues -Special Articles Virtually everything you read in Seminars in Dialysis is written or solicited by the editors after choosing the most effective of nine different editorial styles and formats. They know that facts, speculations, ''how-to-do-it'' information, opinions, and news reports all play important roles in your education and the patient care you provide. Alternate issues of the journal are guest edited and focus on a single clinical topic in dialysis.