利用行動裝置掌握個人健康狀況之研究

THE STUDY ON PERSONAL HEALTH STATUS USING MOBILE DEVICES

蔡明志(Ming-Jyh Tsai) ； 莊以敏(Yi-min Chuang)

《Journal of Data Analysis》 14卷5期 (2019/10) Pp. 39-71

https://doi.org/10.6338/JDA.201910_14(5).0003

摘要

本研究目的欲利用個人的生理參數、運動參與、睡眠品質等，去探討影響個人健康狀況的關係，並且根據所偵測的數據去預測個人健康狀況的準確率。本研究也以欲有效管理自己健康的人群為主，使用的方法將使用機器學習中：羅吉斯迴歸、支援向量機等分類演算法，找出偵測資料與預測資料的連帶關係，進而做健康狀況預測的準確率。其中一項影響值—血壓，就與心臟病、中風、腎臟病、眼疾等疾病之重大危險因子有極大的相關性。依據國民健康署研究顯示，18歲以上的民眾，罹患高血壓症的盛行率為24.1%，其中18－39歲罹患高血壓的盛行率為4.7%。而研究結果也發現，個人有品質好的睡眠、規律的運動習慣，會直接地對個人生理參數產生不同且較佳的結果，對個人的健康狀況是可以直接做有效改善的影響。

關鍵字

健康狀況 ； 偵測 ； 穿戴式裝置 ； 物聯網

並列摘要

The purpose of this study is to use personal physiological parameters, exercise participation, sleep quality, etc. to explore the relationship that affects an individual's health status, and to predict the accuracy of an individual's health based on the detected data. This study is also based on people who want to effectively manage their own health. Some machine learning algorithms are used, such as Logistic Regression and Support Vector Machine to find out the relationship between detection data and prediction data, and then optimize the accuracy of health predictions. One of the influential values, blood pressure, is highly correlated with major risk factors for diseases such as heart disease, stroke, kidney disease, and eye diseases. According to the National Health Service research, the prevalence of hypertension in people over 18 years old is 24.1%, and the prevalence of hypertension in 18-39 years old is 4.7%. The research results also found that individuals with good quality sleep and regular exercise habits will directly produce different and better results for individual physiological parameters, and can effectively improve the individual's health status.

並列關鍵字

Health status ； detection ； wearable devices ； internet of things

參考文獻

P. Chowdhary, S. Lee, J. Timm, H. Ludwig and S. Knoop. (2016). Coordinating Analytics Methods for Mobile Healthcare Applications. 2016 IEEE/ACM International Workshop on Software Engineering in Healthcare Systems (SEHS), Austin, TX, pp. 58-61.doi: 10.1109/SEHS.2016.019

Gami D. J. (2015). IoT: The Age of Machine, International Journal of Engineering Research and General Science Volume 3, Issue 6, November-December, pp.493-495.

Bravata, D. M., Smith-Spangler, C., Sundaram, V.,Gienger, A. L., Lin, N., Lewis, R., & Sirard, J. R. (2007). Using pedometers to increase physical activity and improve health: A systematic review.JAMA: The Journal of the American Medical Association, 美國醫學協會雜誌 , 298(19), 2007, pp.2296, Retrieved from jamanetwork.com/article.aspx?articleid=209526

Ceesay, S. M., & Prentice, A. M., & Day, K. C., & Murgatroyd, P. R., & Goldberg, K., & Scott, W. (1989). The use of heart rate monitoring in the estimation of energy expenditure: a validation study using indirect whole-body calorimetry. British Journal of Nutrition, 61, pp.175-186.

Darrell F., & Murat T., & John T., & Fuad S., & Christiane C. (2017). Mobile Healthcare Delivery: A Dynamic Environment Where Healthcare, Mobile Technology, Engineering, and Individual Lifestyles Converge.