机器学习利用患者特征和导管技术特征预测与外周置入中心导管相关的深静脉血栓。

IF 1.7 4区 医学 Q2 NURSING
Clinical Nursing Research Pub Date : 2024-07-01 Epub Date: 2024-07-30 DOI:10.1177/10547738241260947
Yuan Sheng, Wei Gao
{"title":"机器学习利用患者特征和导管技术特征预测与外周置入中心导管相关的深静脉血栓。","authors":"Yuan Sheng, Wei Gao","doi":"10.1177/10547738241260947","DOIUrl":null,"url":null,"abstract":"<p><p>This study aims to use patient feature and catheterization technology feature variables to train the corresponding machine learning (ML) models to predict peripherally inserted central catheters-deep vein thrombosis (PICCs-DVT) and analyze the importance of the two types of features to PICCs-DVT from the aspect of \"input-output\" correlation. To comprehensively and systematically summarize the variables used to describe patient features and catheterization technical features, this study combined 18 literature involving the two types of features in predicting PICCs-DVT. A total of 21 variables used to describe the two types of features were summarized, and feature values were extracted from the data of 1,065 PICCs patients from January 1, 2021 to August 31, 2022, to construct a data sample set. Then, 70% of the sample set is used for model training and hyperparameter optimization, and 30% of the sample set is used for PICCs-DVT prediction and feature importance analysis of three common ML classification models (i.e. support vector classifier [SVC], random forest [RF], and artificial neural network [ANN]). In terms of prediction performance, this study selected four metrics to evaluate the prediction performance of the model: precision (<i>P</i>), recall (<i>R</i>), accuracy (<i>ACC</i>), and area under the curve (<i>AUC</i>). In terms of feature importance analysis, this study chooses a single feature analysis method based on the \"input-output\" sensitivity principle-Permutation Importance. For the mean model performance, the three ML models on the test set are <i>P</i> = 0.92, <i>R</i> = 0.95, <i>ACC</i> = 0.88, and <i>AUC</i> = 0.81. Specifically, the RF model is <i>P</i> = 0.95, <i>R</i> = 0.96, <i>ACC</i> = 0.92, <i>AUC</i> = 0.86; the ANN model is <i>P</i> = 0.92, <i>R</i> = 0.95, <i>ACC</i> = 0.88, <i>AUC</i> = 0.81; the SVC model is <i>P</i> = 0.88, <i>R</i> = 0.94, <i>ACC</i> = 0.85, <i>AUC</i> = 0.77. For feature importance analysis, Catheter-to-vein rate (RF: 91.55%, ANN: 82.25%, SVC: 87.71%), Zubrod-ECOG-WHO score (RF: 66.35%, ANN: 82.25%, SVC: 44.35%), and insertion attempt (RF: 44.35%, ANN: 37.65%, SVC: 65.80%) all occupy the top three in the ML models prediction task of PICCs-DVT, showing relatively consistent ranking results. The ML models show good performance in predicting PICCs-DVT and reveal a relatively consistent ranking of feature importance from the data. The important features revealed might help clinical medical staff to better understand and analyze the formation mechanism of PICCs-DVT from a data-driven perspective.</p>","PeriodicalId":50677,"journal":{"name":"Clinical Nursing Research","volume":" ","pages":"460-469"},"PeriodicalIF":1.7000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine Learning Predicts Peripherally Inserted Central Catheters-Related Deep Vein Thrombosis Using Patient Features and Catheterization Technology Features.\",\"authors\":\"Yuan Sheng, Wei Gao\",\"doi\":\"10.1177/10547738241260947\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>This study aims to use patient feature and catheterization technology feature variables to train the corresponding machine learning (ML) models to predict peripherally inserted central catheters-deep vein thrombosis (PICCs-DVT) and analyze the importance of the two types of features to PICCs-DVT from the aspect of \\\"input-output\\\" correlation. To comprehensively and systematically summarize the variables used to describe patient features and catheterization technical features, this study combined 18 literature involving the two types of features in predicting PICCs-DVT. A total of 21 variables used to describe the two types of features were summarized, and feature values were extracted from the data of 1,065 PICCs patients from January 1, 2021 to August 31, 2022, to construct a data sample set. Then, 70% of the sample set is used for model training and hyperparameter optimization, and 30% of the sample set is used for PICCs-DVT prediction and feature importance analysis of three common ML classification models (i.e. support vector classifier [SVC], random forest [RF], and artificial neural network [ANN]). In terms of prediction performance, this study selected four metrics to evaluate the prediction performance of the model: precision (<i>P</i>), recall (<i>R</i>), accuracy (<i>ACC</i>), and area under the curve (<i>AUC</i>). In terms of feature importance analysis, this study chooses a single feature analysis method based on the \\\"input-output\\\" sensitivity principle-Permutation Importance. For the mean model performance, the three ML models on the test set are <i>P</i> = 0.92, <i>R</i> = 0.95, <i>ACC</i> = 0.88, and <i>AUC</i> = 0.81. Specifically, the RF model is <i>P</i> = 0.95, <i>R</i> = 0.96, <i>ACC</i> = 0.92, <i>AUC</i> = 0.86; the ANN model is <i>P</i> = 0.92, <i>R</i> = 0.95, <i>ACC</i> = 0.88, <i>AUC</i> = 0.81; the SVC model is <i>P</i> = 0.88, <i>R</i> = 0.94, <i>ACC</i> = 0.85, <i>AUC</i> = 0.77. For feature importance analysis, Catheter-to-vein rate (RF: 91.55%, ANN: 82.25%, SVC: 87.71%), Zubrod-ECOG-WHO score (RF: 66.35%, ANN: 82.25%, SVC: 44.35%), and insertion attempt (RF: 44.35%, ANN: 37.65%, SVC: 65.80%) all occupy the top three in the ML models prediction task of PICCs-DVT, showing relatively consistent ranking results. The ML models show good performance in predicting PICCs-DVT and reveal a relatively consistent ranking of feature importance from the data. The important features revealed might help clinical medical staff to better understand and analyze the formation mechanism of PICCs-DVT from a data-driven perspective.</p>\",\"PeriodicalId\":50677,\"journal\":{\"name\":\"Clinical Nursing Research\",\"volume\":\" \",\"pages\":\"460-469\"},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical Nursing Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1177/10547738241260947\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/7/30 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"NURSING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Nursing Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/10547738241260947","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/30 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"NURSING","Score":null,"Total":0}
引用次数: 0

摘要

本研究旨在利用患者特征和导管技术特征变量来训练相应的机器学习(ML)模型,以预测外周置入中心导管-深静脉血栓形成(PICCs-DVT),并从 "输入-输出 "相关性方面分析这两类特征对 PICCs-DVT 的重要性。为了全面系统地总结用于描述患者特征和导管技术特征的变量,本研究合并了涉及这两类特征预测 PICCs-DVT 的 18 篇文献。共总结了 21 个用于描述这两类特征的变量,并从 2021 年 1 月 1 日至 2022 年 8 月 31 日的 1,065 例 PICC 患者数据中提取特征值,构建数据样本集。然后,70%的样本集用于模型训练和超参数优化,30%的样本集用于PICCs-DVT预测和三种常见ML分类模型(即支持向量分类器[SVC]、随机森林[RF]和人工神经网络[ANN])的特征重要性分析。在预测性能方面,本研究选择了四个指标来评估模型的预测性能:精确度(P)、召回率(R)、准确度(ACC)和曲线下面积(AUC)。在特征重要性分析方面,本研究选择了一种基于 "输入-输出 "灵敏度原理的单一特征分析方法--推移重要性(Permutation Importance)。就平均模型性能而言,测试集上的三个 ML 模型分别为 P = 0.92、R = 0.95、ACC = 0.88 和 AUC = 0.81。具体来说,RF 模型的 P = 0.95,R = 0.96,ACC = 0.92,AUC = 0.86;ANN 模型的 P = 0.92,R = 0.95,ACC = 0.88,AUC = 0.81;SVC 模型的 P = 0.88,R = 0.94,ACC = 0.85,AUC = 0.77。在特征重要性分析中,导管对静脉率(RF:91.55%,ANN:82.25%,SVC:87.71%)、Zubrod-ECOG-WHO 评分(RF:66.35%,ANN:82.25%,SVC:44.35%)和插入尝试(RF:44.35%,ANN:37.65%,SVC:65.80%)在 PICCs-DVT 的 ML 模型预测任务中均占据前三名,显示出相对一致的排名结果。ML 模型在预测 PICCs-DVT 方面表现出色,并从数据中显示出相对一致的特征重要性排序。所揭示的重要特征可能有助于临床医务人员从数据驱动的角度更好地理解和分析 PICCs-DVT 的形成机制。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Machine Learning Predicts Peripherally Inserted Central Catheters-Related Deep Vein Thrombosis Using Patient Features and Catheterization Technology Features.

This study aims to use patient feature and catheterization technology feature variables to train the corresponding machine learning (ML) models to predict peripherally inserted central catheters-deep vein thrombosis (PICCs-DVT) and analyze the importance of the two types of features to PICCs-DVT from the aspect of "input-output" correlation. To comprehensively and systematically summarize the variables used to describe patient features and catheterization technical features, this study combined 18 literature involving the two types of features in predicting PICCs-DVT. A total of 21 variables used to describe the two types of features were summarized, and feature values were extracted from the data of 1,065 PICCs patients from January 1, 2021 to August 31, 2022, to construct a data sample set. Then, 70% of the sample set is used for model training and hyperparameter optimization, and 30% of the sample set is used for PICCs-DVT prediction and feature importance analysis of three common ML classification models (i.e. support vector classifier [SVC], random forest [RF], and artificial neural network [ANN]). In terms of prediction performance, this study selected four metrics to evaluate the prediction performance of the model: precision (P), recall (R), accuracy (ACC), and area under the curve (AUC). In terms of feature importance analysis, this study chooses a single feature analysis method based on the "input-output" sensitivity principle-Permutation Importance. For the mean model performance, the three ML models on the test set are P = 0.92, R = 0.95, ACC = 0.88, and AUC = 0.81. Specifically, the RF model is P = 0.95, R = 0.96, ACC = 0.92, AUC = 0.86; the ANN model is P = 0.92, R = 0.95, ACC = 0.88, AUC = 0.81; the SVC model is P = 0.88, R = 0.94, ACC = 0.85, AUC = 0.77. For feature importance analysis, Catheter-to-vein rate (RF: 91.55%, ANN: 82.25%, SVC: 87.71%), Zubrod-ECOG-WHO score (RF: 66.35%, ANN: 82.25%, SVC: 44.35%), and insertion attempt (RF: 44.35%, ANN: 37.65%, SVC: 65.80%) all occupy the top three in the ML models prediction task of PICCs-DVT, showing relatively consistent ranking results. The ML models show good performance in predicting PICCs-DVT and reveal a relatively consistent ranking of feature importance from the data. The important features revealed might help clinical medical staff to better understand and analyze the formation mechanism of PICCs-DVT from a data-driven perspective.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
3.40
自引率
5.90%
发文量
107
审稿时长
>12 weeks
期刊介绍: Clinical Nursing Research (CNR) is a peer-reviewed quarterly journal that addresses issues of clinical research that are meaningful to practicing nurses, providing an international forum to encourage discussion among clinical practitioners, enhance clinical practice by pinpointing potential clinical applications of the latest scholarly research, and disseminate research findings of particular interest to practicing nurses. This journal is a member of the Committee on Publication Ethics (COPE).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信