基于机器学习算法的急诊患者压伤风险预测模型：前瞻性队列研究

IF 1.8 4区医学 Q2 NURSING

International Emergency Nursing Pub Date : 2024-03-02 DOI:10.1016/j.ienj.2024.101419

Li Wei , Honglei Lv , Chenqi Yue , Ying Yao , Ning Gao , Qianwen Chai , Minghui Lu

{"title":"基于机器学习算法的急诊患者压伤风险预测模型：前瞻性队列研究","authors":"Li Wei , Honglei Lv , Chenqi Yue , Ying Yao , Ning Gao , Qianwen Chai , Minghui Lu","doi":"10.1016/j.ienj.2024.101419","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><p>To construct pressure injury risk prediction models for emergency patients based on different machine learning algorithms, to optimize the best model, and to provide a suitable assessment tool for preventing the occurrence of pressure injuries in emergency patients.</p></div><div><h3>Methods</h3><p>A convenience sampling was used to select 312 patients admitted to the emergency department of a tertiary care hospital in Tianjin, China, from May 2022 to March 2023, and the patients were divided into a modeling group (n = 218) and a validation group (n = 94) in a 7:3 ratio. Based on the results of one-factor logistic regression analysis in the modeling group, three machine learning models, namely, logistic regression, decision tree, and neural network, were used to establish a prediction model for pressure injury in emergency patients and compare their prediction effects. The optimal model was selected for external validation of the model.</p></div><div><h3>Results</h3><p>The incidence of pressure injuries in emergency patients was 8.97 %, 64.52 % of pressure injuries occurred in the sacrococcygeal region, and 64.52 % were staged as stage 1. Serum albumin level, incontinence, perception, and mobility were independent risk factors for pressure injuries in emergency patients (P < 0.05), and the area under the ROC curve of the three models was 0.944–0.959, sensitivity was 91.8–95.5 %, specificity was 72.2–90.9 %, and the Yoden index was 0.677–0.802; the decision tree was the best model that The area under the ROC curve for the validation group was 0.866 (95 % CI: 0.688–1.000), with a sensitivity of 89.8 %, a specificity of 83.3 %, and a Yoden index of 0.731.</p></div><div><h3>Conclusions</h3><p>The decision tree model has the best predictive efficacy and is suitable for individualized risk prediction of pressure injuries in emergency medicine specialties, which provides a reference for the prevention and early intervention of pressure injuries in emergency patients.</p></div>","PeriodicalId":48914,"journal":{"name":"International Emergency Nursing","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A machine learning algorithm-based predictive model for pressure injury risk in emergency patients: A prospective cohort study\",\"authors\":\"Li Wei , Honglei Lv , Chenqi Yue , Ying Yao , Ning Gao , Qianwen Chai , Minghui Lu\",\"doi\":\"10.1016/j.ienj.2024.101419\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Objectives</h3><p>To construct pressure injury risk prediction models for emergency patients based on different machine learning algorithms, to optimize the best model, and to provide a suitable assessment tool for preventing the occurrence of pressure injuries in emergency patients.</p></div><div><h3>Methods</h3><p>A convenience sampling was used to select 312 patients admitted to the emergency department of a tertiary care hospital in Tianjin, China, from May 2022 to March 2023, and the patients were divided into a modeling group (n = 218) and a validation group (n = 94) in a 7:3 ratio. Based on the results of one-factor logistic regression analysis in the modeling group, three machine learning models, namely, logistic regression, decision tree, and neural network, were used to establish a prediction model for pressure injury in emergency patients and compare their prediction effects. The optimal model was selected for external validation of the model.</p></div><div><h3>Results</h3><p>The incidence of pressure injuries in emergency patients was 8.97 %, 64.52 % of pressure injuries occurred in the sacrococcygeal region, and 64.52 % were staged as stage 1. Serum albumin level, incontinence, perception, and mobility were independent risk factors for pressure injuries in emergency patients (P < 0.05), and the area under the ROC curve of the three models was 0.944–0.959, sensitivity was 91.8–95.5 %, specificity was 72.2–90.9 %, and the Yoden index was 0.677–0.802; the decision tree was the best model that The area under the ROC curve for the validation group was 0.866 (95 % CI: 0.688–1.000), with a sensitivity of 89.8 %, a specificity of 83.3 %, and a Yoden index of 0.731.</p></div><div><h3>Conclusions</h3><p>The decision tree model has the best predictive efficacy and is suitable for individualized risk prediction of pressure injuries in emergency medicine specialties, which provides a reference for the prevention and early intervention of pressure injuries in emergency patients.</p></div>\",\"PeriodicalId\":48914,\"journal\":{\"name\":\"International Emergency Nursing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-03-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Emergency Nursing\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1755599X24000144\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"NURSING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Emergency Nursing","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1755599X24000144","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NURSING","Score":null,"Total":0}

引用次数: 0

摘要

方法采用便利抽样法选取2022年5月至2023年3月期间天津市某三级甲等医院急诊科收治的312例患者，按7:3的比例分为建模组（n=218）和验证组（n=94）。根据建模组的单因素逻辑回归分析结果，采用逻辑回归、决策树和神经网络三种机器学习模型建立急诊患者压力性损伤预测模型，并比较其预测效果。结果急诊患者压伤发生率为 8.97%，64.52%的压伤发生在骶尾部，64.52%的压伤分期为 1 期。血清白蛋白水平、大小便失禁、知觉和活动能力是急诊患者压力损伤的独立危险因素（P < 0.05），三种模型的 ROC 曲线下面积为 0.944-0.959，灵敏度为 91.8-95.5%，特异性为 72.2-90.9%，Yoden 指数为 0.677-0.802；决策树是最佳模型，验证组的 ROC 曲线下面积为 0.866（95 % CI：0.688-1.000），灵敏度为 89.8 %，特异度为 83.3 %，Yoden 指数为 0.731.结论决策树模型预测疗效最佳，适用于急诊医学专业压力性损伤的个体化风险预测，为急诊患者压力性损伤的预防和早期干预提供参考。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A machine learning algorithm-based predictive model for pressure injury risk in emergency patients: A prospective cohort study

Objectives

To construct pressure injury risk prediction models for emergency patients based on different machine learning algorithms, to optimize the best model, and to provide a suitable assessment tool for preventing the occurrence of pressure injuries in emergency patients.

Methods

A convenience sampling was used to select 312 patients admitted to the emergency department of a tertiary care hospital in Tianjin, China, from May 2022 to March 2023, and the patients were divided into a modeling group (n = 218) and a validation group (n = 94) in a 7:3 ratio. Based on the results of one-factor logistic regression analysis in the modeling group, three machine learning models, namely, logistic regression, decision tree, and neural network, were used to establish a prediction model for pressure injury in emergency patients and compare their prediction effects. The optimal model was selected for external validation of the model.

Results

The incidence of pressure injuries in emergency patients was 8.97 %, 64.52 % of pressure injuries occurred in the sacrococcygeal region, and 64.52 % were staged as stage 1. Serum albumin level, incontinence, perception, and mobility were independent risk factors for pressure injuries in emergency patients (P < 0.05), and the area under the ROC curve of the three models was 0.944–0.959, sensitivity was 91.8–95.5 %, specificity was 72.2–90.9 %, and the Yoden index was 0.677–0.802; the decision tree was the best model that The area under the ROC curve for the validation group was 0.866 (95 % CI: 0.688–1.000), with a sensitivity of 89.8 %, a specificity of 83.3 %, and a Yoden index of 0.731.

Conclusions

The decision tree model has the best predictive efficacy and is suitable for individualized risk prediction of pressure injuries in emergency medicine specialties, which provides a reference for the prevention and early intervention of pressure injuries in emergency patients.

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

International Emergency Nursing NURSING-

CiteScore

3.20

自引率

11.10%

发文量

期刊介绍： International Emergency Nursing is a peer-reviewed journal devoted to nurses and other professionals involved in emergency care. It aims to promote excellence through dissemination of high quality research findings, specialist knowledge and discussion of professional issues that reflect the diversity of this field. With an international readership and authorship, it provides a platform for practitioners worldwide to communicate and enhance the evidence-base of emergency care. The journal publishes a broad range of papers, from personal reflection to primary research findings, created by first-time through to reputable authors from a number of disciplines. It brings together research from practice, education, theory, and operational management, relevant to all levels of staff working in emergency care settings worldwide.