An alternative approach for determining the cholesterol level: Iris analysis
In this study, the relationship between individuals’ cholesterol levels and the width of the sodium ring was investigated. Firstly, iris images were taken of 100 individuals with total cholesterol levels of 200 mg/dL and above. The average grey scale value (AGSV) for each iris image with a sodium ring was calculated. Secondly, the relationship between the AGSV and cholesterol levels was investigated. Finally, a new mathematical model was proposed that described the relationship between AGSV and total cholesterol with ~89% accuracy. The relationship between AGSV and high-density lipoprotein (HDL), low-density lipoprotein (LDL), and triglyceride levels was calculated with an accuracy of 80.5%, 85.1%, and 79.9%, respectively. In addition, AGSV was determined with 90% accuracy using total cholesterol, HDL, LDL, and triglycerides using multiple linear regression. Although multiple linear regression gives better AGSV, the results have shown that multilayer perceptron (MLP) mapping method gives better accuracy up to 6.62%.
Ferdi Ozbilgin, Cetin Kurnaz
Abstract Link: https://onlinelibrary.wiley.com/doi/abs/10.1002/ima.22689