School of Health and Life Sciences, Glasgow Caledonian University, Cowcaddens Rd, Glasgow, G4 0BA, UK.
Environmental Health Department, Health Polytechnic, Ministry of Health, Yogyakarta, Indonesia.
Curr Hypertens Rep. 2023 Nov;25(11):377-383. doi: 10.1007/s11906-023-01261-5. Epub 2023 Aug 29.
This retrospective study investigated factors that influence the occurrence of decreased systolic and diastolic blood pressure including sociodemographic and economic factors, hypertension duration, cigarette consumption, alcohol consumption, duration of smoking, type of cigarettes, exercise, salt consumption, sleeping pills consumption, insomnia, and diabetes. These factors were applied to predict the reality of systolic and diastolic decrease using the machine learning algorithm Naïve Bayes, artificial neural network, logistic regression, and decision tree.
The increase in blood pressure, both systolic and diastolic, is very harmful to the health because uncontrolled high systolic and diastolic blood pressure can cause various diseases such as congestive heart failure, kidney failure, and cardiovascular disease. There have been many studies examining the factors that influence the occurrence of hypertension, but few studies have used machine learning to predict hypertension. The machine learning models performed well and can be used for predicting whether a person with hypertension with certain characteristics will experience a decrease in their systolic or diastolic blood pressure after treatment with antihypertensive drugs.
本回顾性研究调查了影响收缩压和舒张压下降的因素，包括社会人口经济学因素、高血压持续时间、吸烟、饮酒、吸烟持续时间、香烟类型、运动、盐摄入量、安眠药使用、失眠和糖尿病。这些因素被应用于使用机器学习算法朴素贝叶斯、人工神经网络、逻辑回归和决策树来预测收缩压和舒张压下降的实际情况。
血压升高，无论是收缩压还是舒张压，都对健康非常有害，因为不受控制的高收缩压和舒张压会导致充血性心力衰竭、肾衰竭和心血管疾病等各种疾病。已经有很多研究检查了影响高血压发生的因素，但很少有研究使用机器学习来预测高血压。机器学习模型表现良好，可用于预测具有某些特征的高血压患者在使用抗高血压药物治疗后收缩压或舒张压是否会下降。
