Cluster modelling of longitudinal disease data: asthma and potential clinical phenotypes. (4th March 2022)

• Record Type: Journal Article
• Authors: Wesonga, Ronald; Bakheit, Charles; Ababneh, Faisal
• Is Part Of: International journal of modelling & simulation. Volume 42:Number 2(2022)
• Page Start: 227
• Page End: 239
• Publication Date: 2022-03-04
• Subjects: Asthma -- clinical phenotypes -- k-means -- hierarchical agglomerative clustering -- statistics; Mathematical models -- Periodicals; Simulation methods -- Periodicals; Mathematical models; Simulation methods; Periodicals; 003.3
• DOI: 10.1080/02286203.2021.1873221
• Languages: English
• ISSNs: 0228-6203

Abstract

ABSTRACT: Asthma and chronic obstructive pulmonary diseases are assiduous inflammatory diseases with substantial effects on health and well-being of individuals, and are known to pose great financial implications. This study aimed to explore a possibility of potential clusters of these diseases based on the reported incidences by the Ministry of Health, Sultanate of Oman. Maternal asthma has been found to be a major risk factor for asthma in infants. However, the clustering of asthma morbidity has not been explained fully. In our study, we developed five potential clusters and mapped them onto asthma clinical phenotypes using the complete linkage hierarchical agglomerative cluster models. Accordingly, the majority (92%) who had relatively easy to control symptoms of asthma were the younger male, while the much older female patients experienced difficult to control asthma symptoms. Asthma disease clustering facilitates targeted efforts to prioritize medical response, control and management of the disease. Further research is sought to develop cost of illness optimization models for healthcare resource allocation so as to combat the scourge.