Advanced Clustering of Blood Test Parameters for the Development of a Health Analytics System: A Case Study in Sam Khok District, Pathum Thani
Health Risk Analytics System using K-means and K-Prototypes Clustering Based on Physical Factors and Laboratory Parameters: A Case Study in Sam Khok District, Pathum Thani Province
Keywords:
Keywords: Advanced clustering, Blood test results, Community health analysis, Sam Khok District.Abstract
Abstract
This study aimed to develop a health analysis system focusing on the population of Sam Khok District, Pathum Thani Province, a semi-rural area with prevalent health problems such as anemia, diabetes, and hypertension. A total of 105 participants, consisting of working-age adults and older adults, were included. The study applied advanced clustering techniques using demographic data (e.g., body mass index and blood pressure) and laboratory results from hematology and clinical chemistry tests. The K-means and K-Prototypes clustering algorithms were employed to classify individuals according to their health risks and specific characteristics. The results revealed three major health clusters: (1) a group characterized by anemia and hyperlipidemia, (2) an overweight and high blood glucose and hyperlipidemia group, and (3) Healthy. Each cluster showed significant differences in clinical parameters and health behaviors (p < 0.05). These findings highlight the potential of advanced data clustering based on laboratory parameters as a proactive tool for community health surveillance and for developing targeted health education programs within local populations.
Keywords: Advanced clustering, Blood test results, Community health analysis, Sam Khok District.
References
เอกสารอ้างอิง
Hassan M. Cluster analysis – Types, methods and examples [Internet]. 2024 [cited 2025 Jul 23]. Available from: https://researchmethod.net/cluster-analysis/
Huang Z. Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Min Knowl Discov. 1998;2(3):283–304.
Yang L, Zhou Q, Wang C, et al. Classification of health needs: A cluster analysis of older adults in urban areas. BMC Geriatr. 2023; 23:638. https://doi.org/10.1186/s12877-023-04226-7
Bing Y, Yuan L, Liu J, Wang Z, Chen L, Sun J, Liu L. Cluster analysis for the overall health status of elderly, multimorbid patients with diabetes. Front Public Health. 2023;11:1031457. https://doi.org/10.3389/fpubh.2023.1031457
Cojic M, Klisic A, Sahmanovic A, Petrovic N, Kocic G. Cluster analysis of patient characteristics, treatment modalities, renal impairments, and inflammatory markers in diabetes mellitus. Sci Rep. 2024;14:5994. https://doi.org/10.1038/s41598-024-56451-1
Han J, Kamber M, Pei J. Data mining: Concepts and techniques. 3rd ed. Boston: Elsevier; 2012.
Mohamad I, Usman D. Standardization and its effects on K-means clustering algorithm. Res J Appl Sci Eng Technol. 2013;6:3299–3303. https://doi.org/10.19026/rjaset.6.3638
Aditya. K-Prototypes clustering with numerical example [Internet]. CODING INFINITE; 2022 [cited 2025 Jul 23]. Available from: https://codinginfinite.com/k-prototypes-clustering-with-numerical-example/
Dalmaijer ES, Nord CL, Astle DE. Statistical power for cluster analysis. BMC Bioinformatics. 2022;23:205. https://doi.org/10.1186/s12859-022-04675-1
MathWorks. What is clustering? Clustering and its applications explained [Internet]. 2025 [cited 2025 Jul 23]. Available from: https://www.mathworks.com/discovery/clustering.html
ถิรจิต บุญแสน. ดัชนีมวลกาย สำคัญอย่างไร [อินเทอร์เน็ต]. กรุงเทพฯ: คณะแพทยศาสตร์ศิริราชพยาบาล ม.มหิดล; 2562 [สืบค้น 23 ก.ค. 2568]. เข้าถึงได้จาก: https://www.si.mahidol.ac.th/th/healthdetail.asp?aid=1361
สมาคมความดันโลหิตสูงแห่งประเทศไทย. โรคความดันโลหิตสูง [อินเทอร์เน็ต]. 2568 [สืบค้น 23 ก.ค. 2568]. เข้าถึงได้จาก: https://www.thaihypertension.org/hypertensiondetail.php?n_id=338
ลลิตา นรเศรษฐ์ธาดา. การแปลผลความสมบูรณ์ของเม็ดเลือดด้วยตนเอง [อินเทอร์เน็ต]. สมาคมโลหิตวิทยาแห่งประเทศไทย; 2568 [สืบค้น 23 ก.ค. 2568]. เข้าถึงได้จาก: https://www.tsh.or.th/Knowledge/Details/34
Wikipedia contributors. Reference ranges for blood tests [Internet]. Wikipedia; 2023 [cited 2025 Jul 23]. Available from: https://en.wikipedia.org/wiki/Reference_ranges_for_blood_tests
Oh JH, Ahn KM, Chung SJ, Shim JS, Park HW. Usefulness of routine blood test-driven clusters for predicting acute exacerbation in patients with asthma. Respir Med. 2020;170:106042. https://doi.org/10.1016/j.rmed.2020.106042
The jamovi project. jamovi (Version 2.3) [Computer software]. 2022 [cited 2025 Jul 23]. Available from: https://www.jamovi.org
Jamovi Stat.Open.Now. Jamovi Desktop [Internet]. 2025 [cited 2025 Jul 23]. Available from: https://www.jamovi.org/
GitHub, Inc. hyunsooseol/snowCluster [Computer software]. 2025 [cited 2025 Jul 23]. Available from: https://github.com/hyunsooseol/snowCluster
Kassambara A, Mundt F. factoextra: Extract and Visualize the Results of Multivariate Data [R package]. 2020 [cited 2025 Jul 23]. Available from: https://CRAN.R-project.org/package=factoextra
