Modelling of Hypertension Risk Factors Using Logistic Regression to Prevent Hypertension in Indonesia

Putri Andriani, Nur Chamidah

Research output: Contribution to journalConference articlepeer-review

5 Citations (Scopus)


Hypertension called as the silent killer, is the number one non-infectious disease that causes death in the world every year. There are 185,857 cases recorded in 2018 in Indonesia. In this study, we model the hypertension risk by considering age, heart rate, hypertension history of family, eating salty foods, and smoking or exposure to cigarette smoke as the influence factors of hypertension risk. A cross-sectional survey was conducted in August 2018 at the Haji Hospital of Surabaya. Logistic regression is used to analyse the influence of various risk factors on hypertension and non-hypertension. In addition, we compare between logit and gompit link functions in logistic regression to build the modelling of hypertension risk factors based on the accuracy of the classification model. By using logit and gompit link functions, we obtain percentage of the classification accuracy are 85.2 % and 81.5 %, respectively. It means that the logit link function is better than the gompit link function for modelling hypertension risk factors. For these link functions, the significant factors that influence hypertension are age and heart rate.

Original languageEnglish
Article number012027
JournalJournal of Physics: Conference Series
Issue number1
Publication statusPublished - 9 Sept 2019
Event2nd International Conference on Mathematics: Education, Theory, and Application, ICMETA 2018 - Sukoharjo, Indonesia
Duration: 30 Oct 201831 Oct 2018


  • hypertension
  • logistic regression
  • logit and gompit link functions
  • risk factors


Dive into the research topics of 'Modelling of Hypertension Risk Factors Using Logistic Regression to Prevent Hypertension in Indonesia'. Together they form a unique fingerprint.

Cite this