The CMLA score: A novel tool for early prediction of renal replacement therapy in patients with cardiogenic shock

IF 3 3区医学 Q2 CARDIAC & CARDIOVASCULAR SYSTEMS

Current Problems in Cardiology Pub Date : 2024-09-27 DOI:10.1016/j.cpcardiol.2024.102870

Shuo Pang, Shen Wang, Chu Fan, Fadong Li, Wenxin Zhao, Boqun Shi, Yue Wang, Xiaofan Wu

{"title":"The CMLA score: A novel tool for early prediction of renal replacement therapy in patients with cardiogenic shock","authors":"Shuo Pang, Shen Wang, Chu Fan, Fadong Li, Wenxin Zhao, Boqun Shi, Yue Wang, Xiaofan Wu","doi":"10.1016/j.cpcardiol.2024.102870","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Early identification of cardiogenic shock (CS) patients at risk for renal replacement therapy (RRT) is crucial for improving clinical outcomes. This study aimed to develop and validate a prediction model using readily available clinical variables.</div></div><div><h3>Methods</h3><div>A retrospective cohort study was conducted using data from 4,133 CS patients from the MIMIC and eICU-CRD databases. Patients from MIMIC databases were randomly divided into 80 % training and 20 % validation cohorts, while those from eICU-CRD constituted the test cohort. Feature selection involved univariate logistic regression (LR), LASSO, and Boruta methods. Prediction models for RRT were developed using stepwise selection by LR and five machine learning (ML) algorithms (naive bayes, support vector machines, k-nearest neighbors, random forest, extreme gradient boosting) in the training cohort. Model performance was evaluated in both validation and test cohorts. A nomogram was constructed based on LR model. Kaplan-Meier survival analysis assessed 28-day mortality.</div></div><div><h3>Results</h3><div>The incidence of RRT was approximately 13 % across all cohorts. Ten variables were selected: age, anion gap, chloride, bun, creatinine, potassium, ast, lactate, estimated glomerular filtration rate (eGFR), and mechanical ventilation. Compared with ML models, the LR model showed superior predictive performance with an AUC of 0.731 in the validation cohort and 0.714 in the test cohort. Four variables that best predicted the need for RRT (age, lactate, mechanical ventilation, and creatinine) were used to generate the CMLA nomogram risk score. The CMLA model showed better predictive accuracy for RRT in the test cohort compared to the previous CALL-K model (AUC: 0.731 vs. 0.699, DeLong test P < 0.05). Calibration curves and decision curve analysis (DCA) indicated that the CMLA model also had good calibration (Hosmer–Lemeshow P=0.323) and clinical utility in the test cohort. Kaplan-Meier analysis indicated significantly higher 28-day mortality in the high-risk CMLA group.</div></div><div><h3>Conclusions</h3><div>A clinically applicable nomogram with four key variables was developed to predict RRT risk in CS patients. It demonstrated good performance, promising enhanced clinical decision-making.</div></div>","PeriodicalId":51006,"journal":{"name":"Current Problems in Cardiology","volume":"49 12","pages":"Article 102870"},"PeriodicalIF":3.0000,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current Problems in Cardiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S014628062400505X","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Early identification of cardiogenic shock (CS) patients at risk for renal replacement therapy (RRT) is crucial for improving clinical outcomes. This study aimed to develop and validate a prediction model using readily available clinical variables.

Methods

A retrospective cohort study was conducted using data from 4,133 CS patients from the MIMIC and eICU-CRD databases. Patients from MIMIC databases were randomly divided into 80 % training and 20 % validation cohorts, while those from eICU-CRD constituted the test cohort. Feature selection involved univariate logistic regression (LR), LASSO, and Boruta methods. Prediction models for RRT were developed using stepwise selection by LR and five machine learning (ML) algorithms (naive bayes, support vector machines, k-nearest neighbors, random forest, extreme gradient boosting) in the training cohort. Model performance was evaluated in both validation and test cohorts. A nomogram was constructed based on LR model. Kaplan-Meier survival analysis assessed 28-day mortality.

Results

The incidence of RRT was approximately 13 % across all cohorts. Ten variables were selected: age, anion gap, chloride, bun, creatinine, potassium, ast, lactate, estimated glomerular filtration rate (eGFR), and mechanical ventilation. Compared with ML models, the LR model showed superior predictive performance with an AUC of 0.731 in the validation cohort and 0.714 in the test cohort. Four variables that best predicted the need for RRT (age, lactate, mechanical ventilation, and creatinine) were used to generate the CMLA nomogram risk score. The CMLA model showed better predictive accuracy for RRT in the test cohort compared to the previous CALL-K model (AUC: 0.731 vs. 0.699, DeLong test P < 0.05). Calibration curves and decision curve analysis (DCA) indicated that the CMLA model also had good calibration (Hosmer–Lemeshow P=0.323) and clinical utility in the test cohort. Kaplan-Meier analysis indicated significantly higher 28-day mortality in the high-risk CMLA group.

Conclusions

A clinically applicable nomogram with four key variables was developed to predict RRT risk in CS patients. It demonstrated good performance, promising enhanced clinical decision-making.

查看原文本刊更多论文

CMLA 评分：用于早期预测心源性休克患者肾脏替代疗法的新工具。

背景：早期识别有接受肾脏替代治疗（RRT）风险的心源性休克（CS）患者对改善临床预后至关重要。本研究旨在利用现成的临床变量开发并验证一个预测模型：利用 MIMIC 和 eICU-CRD 数据库中 4,133 名 CS 患者的数据进行了一项回顾性队列研究。来自 MIMIC 数据库的患者被随机分为 80% 的训练队列和 20% 的验证队列，而来自 eICU-CRD 数据库的患者则构成测试队列。特征选择包括单变量逻辑回归（LR）、LASSO 和 Boruta 方法。在训练队列中使用 LR 逐步选择法和五种机器学习（ML）算法（奈夫贝叶斯、支持向量机、k-近邻、随机森林、极端梯度提升）建立了 RRT 预测模型，并在验证队列和测试队列中评估了模型的性能。根据 LR 模型构建了提名图。Kaplan-Meier生存分析评估了28天死亡率：所有队列的 RRT 发生率约为 13%。选择了十个变量：年龄、阴离子间隙、氯化物、馒头、肌酐、钾、哮喘、乳酸、估计肾小球滤过率（eGFR）和机械通气。与 ML 模型相比，LR 模型显示出更优越的预测性能，在验证队列中的 AUC 为 0.731，在测试队列中为 0.714。预测 RRT 需求的四个最佳变量（年龄、乳酸、机械通气和肌酐）被用于生成 CMLA 提名图风险评分。与之前的 CALL-K 模型相比，CMLA 模型对测试队列中 RRT 的预测准确性更高（AUC：0.731 对 0.699，DeLong 检验 P <0.05）。校准曲线和决策曲线分析（DCA）表明，CMLA 模型在测试队列中也具有良好的校准性（Hosmer-Lemeshow P=0.323）和临床实用性。Kaplan-Meier分析表明，高风险CMLA组的28天死亡率明显更高：结论：通过四个关键变量建立了一个适用于临床的提名图，用于预测 CS 患者的 RRT 风险。结论：利用四个关键变量开发出了一种适用于临床的预测 CS 患者 RRT 风险的提名图，该提名图表现良好，有望改善临床决策。

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

Current Problems in Cardiology 医学-心血管系统

CiteScore

4.80

自引率

2.40%

发文量

392

审稿时长

6 days

期刊介绍： Under the editorial leadership of noted cardiologist Dr. Hector O. Ventura, Current Problems in Cardiology provides focused, comprehensive coverage of important clinical topics in cardiology. Each monthly issues, addresses a selected clinical problem or condition, including pathophysiology, invasive and noninvasive diagnosis, drug therapy, surgical management, and rehabilitation; or explores the clinical applications of a diagnostic modality or a particular category of drugs. Critical commentary from the distinguished editorial board accompanies each monograph, providing readers with additional insights. An extensive bibliography in each issue saves hours of library research.