Volume 5, Issue 2 (8-2022)                   Iran J Health Insur 2022, 5(2): 108-117 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Salari M, Sabbaghian Tousi S, Rastaghi S, Golpour P, Vejdani M, Sadati S M et al . Comparison of PAM and CLARA Clustering Algorithms for Assessing the Causes of Mortality in the Population Covered by Mashhad University of Medical Sciences, Iran. Iran J Health Insur 2022; 5 (2) :108-117
URL: http://journal.ihio.gov.ir/article-1-233-en.html
1- Department of Epidemiology and Biostatistics, School of Health, Mashhad University of Medical Sciences, Mashhad, Iran , salarimr@mums.ac.ir
2- Department of Epidemiology and Biostatistics, School of Health, Mashhad University of Medical Sciences, Mashhad, Iran
3- Student Research Committee, Mashhad University of Medical Sciences, Mashhad, Iran
4- Department of General Surgery, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
Abstract:   (217 Views)
Introduction: Analysing data related to morality is one of the important tools in health policy for any country. The present study was conducted in order to cluster people who died in 2017 in the area covered by Mashhad University of Medical Sciences.
Methods: An analytical and cross-sectional study was conducted on the number of 21,838 deaths reported in 2017 in the population covered by Mashhad University of Medical Sciences, which were extracted from the death registration system of this university. After cleaning the data and fixing the existing defects, people were clustered with PAM and CLARA algorithms based on 4 variables: age, gender, cause of death and region of residence. The optimal number of clusters and the evaluation of the clustering performance were obtained using the average silhouette criterion.
Results: According to the silhouette criterion, the biggest difference between the clusters was observed with the number of five clusters. In all clusters (except the third cluster), which included people over 65 years old (64.5%), circulatory diseases (43%), neoplasms (17%), diseases of the respiratory system (10%) and Endocrine, nutritional and metabolic diseases (6%) were the most common cause of death. In the third cluster, the most important causes of death were congenital malformations, deformation (44%) and diseases of prenatal origin (19%) for children under 1 year of age (74%).
Conclusion: Age distribution of the causes of death is one of the most important cases. The existence of congenital malformations, deformation, and diseases of prenatal origin for children under 1 year of age, as well as the cause of death due to the presence of cancer at the age of less than 14 years, according to the upcoming policies regarding the youth of the population, should be considered by health care providers. The high percentage of death due to neurological diseases is one of the cases that can be studied carefully to plan a health road map.
Full-Text [PDF 717 kb]   (44 Downloads)    
Type of Study: Research | Subject: Special
Received: 2022/04/5 | Revised: 2022/10/19 | Accepted: 2022/07/26 | ePublished: 2022/10/8

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2022 CC BY-NC 4.0 | Iranian Journal of Health Insurance

Designed & Developed by : Yektaweb