Modeling of Health Related Quality of Life Using an Integrated Fuzzy Inference System and Linear Regression

• Published in: Procedia computer science Vol. 42; pp. 99 - 105
• Main Author: Abdullah, Lazim
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 2014
• Subjects: chronic kidney diseases; Fuzzy inference system; health status; inference rule; multi-linear regression; health status; chronic kidney diseases; Fuzzy inference system; inference rule; multi-linear regression
• ISSN: 1877-0509; 1877-0509
• DOI: 10.1016/j.procs.2014.11.039

Health Related Quality of Life (HRQL) is one of the increasing subjects used for assessing health condition among patients who suffer from specific diseases or illness. It has been assumed that multiple variables of HRQL would provide the one's overall health conditions. However, devising the extent of contribution of multiple variables towards overall health conditions is not straight forward as the arbitrary nature of HRQL variables. This paper aims to model the relationship between HRQL variables using an integrated model of fuzzy inference system and linear regression. An experiment was conducted to measure the strength of the relationship between variables and health indices among patients with chronic kidney diseases (CKD). To model this relationship, thirty outpatients with CKD were recruited from a government funded hospital in Peninsular Malaysia. Linguistic data were collected via guided interview and fed into the fuzzy inference system to yield HRQL indices. Multi-linear regressions were then undertaken to establish the relationship between variables and HRQL indices. The model shows that the variable of ‘unemployment’ was identified as the highest impact factor for patients with CKD. The employment of the integrated model, fuzzy inference system and multi-linear regressions were successfully identified the strength of the relationship between the multiple variables of HRQL and the health status.