Exploring the relationship between hypertension and nutritional ingredients intake with machine learning

• Main Authors: Yu Liu, Shijie Li, Huaiyan Jiang, Junfeng Wang
• Format: Article
• Language: English
• Published: Wiley 2020-05-01
• Series: Healthcare Technology Letters
• Subjects: pattern classification; learning (artificial intelligence); diseases; hypertension; machine learning methods; nutritional ingredient data conversion; xgboost
• Online Access: https://digital-library.theiet.org/content/journals/10.1049/htl.2019.0055

Hypertension is a chronic disease that can harm the health of many people. Though hypertension may be caused by many factors, the diet has been recognised as a factor, which can seriously impact hypertension. In this Letter, the authors explore the relationship between the nutritional ingredients and hypertension with machine learning methods. They design a prediction scheme, which is constructed by nutritional ingredients data conversion, feature selection, classifiers etc. To choose the proper classifier, the performance of several classification algorithms are compared. Based on their experimental results, XGboost is used as the classifier in their scheme as it obtains the highest accuracy (84.9%) and [inline-formula].