使用机器学习方法预测与未控制高血压相关的因素:伊朗西部的一项横断面研究。

IF 1.9 4区 医学 Q3 PERIPHERAL VASCULAR DISEASE
International Journal of Hypertension Pub Date : 2025-02-18 eCollection Date: 2025-01-01 DOI:10.1155/ijhy/4011397
Zahra Cheraghi, Mahboobeh Doosti-Irani, Masoumeh Sohrabi, Amin Doosti-Irani
{"title":"使用机器学习方法预测与未控制高血压相关的因素:伊朗西部的一项横断面研究。","authors":"Zahra Cheraghi, Mahboobeh Doosti-Irani, Masoumeh Sohrabi, Amin Doosti-Irani","doi":"10.1155/ijhy/4011397","DOIUrl":null,"url":null,"abstract":"<p><p>Uncontrolled hypertension is a major public health issue globally. This study aimed to uncover the factors contributing to uncontrolled hypertension using machine learning techniques. In this study, 303 adults with hypertension were included in this cross-sectional study. Data were collected using the Standard Health Literacy Questionnaire. Uncontrolled hypertension was defined as systolic blood pressure (BP) ≥ 140 mmHg and/or diastolic BP ≥ 90 mmHg on both days. Data were analyzed using percentages and chi-square tests. Four machine learning algorithms were employed in this study. The efficacy of these algorithms was assessed using several performance metrics, including accuracy, positive predictive value, sensitivity, <i>F</i>_Score, and the area under the receiver operating characteristic (ROC) curve (AUC). The analyses were performed utilizing Python version 3.8. Of the four models evaluated, logistic regression exhibited the highest accuracy at 75.4% and the greatest AUC at 0.87. According to the logistic regression algorithm, individuals who did not adhere to their treatment had a significantly lower likelihood of having uncontrolled hypertension (OR = 0.17, <i>p</i> value < 0.001). Number of children (OR = 0.44, <i>p</i> < 0.001), physical activity (OR = 0.94, <i>p</i> < 0.001), and health literacy (OR = 0.29, <i>p</i> = 0.10) were all associated directly, and salt intake (OR = 9.60, <i>p</i> < 0.001) was associated inversely with the odds of having uncontrolled hypertension. Based on variable importance analysis, low physical activity was identified as the most important variable, followed by weak health literacy and nonadherence to drug treatment. Factors such as age, duration of hypertension, chronic disease, and salt consumption were also significant. Adherence to treatment, physical activity, health literacy, and salt intake play crucial roles in uncontrolled hypertension. Interventions targeting these factors could help in managing and preventing uncontrolled hypertension.</p>","PeriodicalId":14132,"journal":{"name":"International Journal of Hypertension","volume":"2025 ","pages":"4011397"},"PeriodicalIF":1.9000,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11858708/pdf/","citationCount":"0","resultStr":"{\"title\":\"Predicting Factors Associated With Uncontrolled Hypertension Using Machine Learning Methods: A Cross-Sectional Study in Western Iran.\",\"authors\":\"Zahra Cheraghi, Mahboobeh Doosti-Irani, Masoumeh Sohrabi, Amin Doosti-Irani\",\"doi\":\"10.1155/ijhy/4011397\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Uncontrolled hypertension is a major public health issue globally. This study aimed to uncover the factors contributing to uncontrolled hypertension using machine learning techniques. In this study, 303 adults with hypertension were included in this cross-sectional study. Data were collected using the Standard Health Literacy Questionnaire. Uncontrolled hypertension was defined as systolic blood pressure (BP) ≥ 140 mmHg and/or diastolic BP ≥ 90 mmHg on both days. Data were analyzed using percentages and chi-square tests. Four machine learning algorithms were employed in this study. The efficacy of these algorithms was assessed using several performance metrics, including accuracy, positive predictive value, sensitivity, <i>F</i>_Score, and the area under the receiver operating characteristic (ROC) curve (AUC). The analyses were performed utilizing Python version 3.8. Of the four models evaluated, logistic regression exhibited the highest accuracy at 75.4% and the greatest AUC at 0.87. According to the logistic regression algorithm, individuals who did not adhere to their treatment had a significantly lower likelihood of having uncontrolled hypertension (OR = 0.17, <i>p</i> value < 0.001). Number of children (OR = 0.44, <i>p</i> < 0.001), physical activity (OR = 0.94, <i>p</i> < 0.001), and health literacy (OR = 0.29, <i>p</i> = 0.10) were all associated directly, and salt intake (OR = 9.60, <i>p</i> < 0.001) was associated inversely with the odds of having uncontrolled hypertension. Based on variable importance analysis, low physical activity was identified as the most important variable, followed by weak health literacy and nonadherence to drug treatment. Factors such as age, duration of hypertension, chronic disease, and salt consumption were also significant. Adherence to treatment, physical activity, health literacy, and salt intake play crucial roles in uncontrolled hypertension. Interventions targeting these factors could help in managing and preventing uncontrolled hypertension.</p>\",\"PeriodicalId\":14132,\"journal\":{\"name\":\"International Journal of Hypertension\",\"volume\":\"2025 \",\"pages\":\"4011397\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-02-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11858708/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Hypertension\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1155/ijhy/4011397\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q3\",\"JCRName\":\"PERIPHERAL VASCULAR DISEASE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Hypertension","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1155/ijhy/4011397","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"PERIPHERAL VASCULAR DISEASE","Score":null,"Total":0}
引用次数: 0

摘要

不受控制的高血压是一个全球性的重大公共卫生问题。本研究旨在利用机器学习技术揭示导致高血压失控的因素。在这项横断面研究中,303名成人高血压患者被纳入研究。使用标准健康素养问卷收集数据。未控制的高血压定义为两天收缩压(BP)≥140 mmHg和/或舒张压≥90 mmHg。数据分析采用百分比和卡方检验。本研究采用了四种机器学习算法。使用几个性能指标评估这些算法的有效性,包括准确性、阳性预测值、灵敏度、F_Score和受试者工作特征(ROC)曲线下面积(AUC)。使用Python 3.8版本执行分析。在评估的四种模型中,逻辑回归的准确率最高,为75.4%,AUC最高,为0.87。根据logistic回归算法,未坚持治疗的个体高血压不受控制的可能性显著降低(OR = 0.17, p值< 0.001)。儿童数量(OR = 0.44, p < 0.001)、体力活动(OR = 0.94, p < 0.001)和健康素养(OR = 0.29, p = 0.10)均与高血压不受控制的几率直接相关,盐摄入量(OR = 9.60, p < 0.001)与高血压不受控制的几率呈负相关。根据变量重要性分析,低体力活动被确定为最重要的变量,其次是卫生知识薄弱和不坚持药物治疗。年龄、高血压病程、慢性疾病和盐摄入量等因素也很重要。坚持治疗、身体活动、健康知识和盐摄入在高血压不受控制中起着至关重要的作用。针对这些因素的干预可能有助于控制和预防不受控制的高血压。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Predicting Factors Associated With Uncontrolled Hypertension Using Machine Learning Methods: A Cross-Sectional Study in Western Iran.

Uncontrolled hypertension is a major public health issue globally. This study aimed to uncover the factors contributing to uncontrolled hypertension using machine learning techniques. In this study, 303 adults with hypertension were included in this cross-sectional study. Data were collected using the Standard Health Literacy Questionnaire. Uncontrolled hypertension was defined as systolic blood pressure (BP) ≥ 140 mmHg and/or diastolic BP ≥ 90 mmHg on both days. Data were analyzed using percentages and chi-square tests. Four machine learning algorithms were employed in this study. The efficacy of these algorithms was assessed using several performance metrics, including accuracy, positive predictive value, sensitivity, F_Score, and the area under the receiver operating characteristic (ROC) curve (AUC). The analyses were performed utilizing Python version 3.8. Of the four models evaluated, logistic regression exhibited the highest accuracy at 75.4% and the greatest AUC at 0.87. According to the logistic regression algorithm, individuals who did not adhere to their treatment had a significantly lower likelihood of having uncontrolled hypertension (OR = 0.17, p value < 0.001). Number of children (OR = 0.44, p < 0.001), physical activity (OR = 0.94, p < 0.001), and health literacy (OR = 0.29, p = 0.10) were all associated directly, and salt intake (OR = 9.60, p < 0.001) was associated inversely with the odds of having uncontrolled hypertension. Based on variable importance analysis, low physical activity was identified as the most important variable, followed by weak health literacy and nonadherence to drug treatment. Factors such as age, duration of hypertension, chronic disease, and salt consumption were also significant. Adherence to treatment, physical activity, health literacy, and salt intake play crucial roles in uncontrolled hypertension. Interventions targeting these factors could help in managing and preventing uncontrolled hypertension.

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 Journal of Hypertension
International Journal of Hypertension Medicine-Internal Medicine
CiteScore
4.00
自引率
5.30%
发文量
45
期刊介绍: International Journal of Hypertension is a peer-reviewed, Open Access journal that provides a forum for clinicians and basic scientists interested in blood pressure regulation and pathophysiology, as well as treatment and prevention of hypertension. The journal publishes original research articles, review articles, and clinical studies on the etiology and risk factors of hypertension, with a special focus on vascular biology, epidemiology, pediatric hypertension, and hypertensive nephropathy.
×
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