Investigating Optimal HOMA-IR Cut-off values for detecting Diabetes Mellitus in Omani Population using Machine Learning Methods

Project: Other project

Project Details

Description

Diabetes Mellitus (DM) is one of the most challenging medical problems worldwide as well as in Oman. Insulin resistance (IR) is a key feature for the prognosis of diabetes mellitus type 2 and the homeostasis model assessment of insulin resistance (HOMA-IR) is commonly used for IR detection. This project aims to defining a reference range of HOMA-IR index in adult Omani population by implementing machine learning techniques. Identifying an optimum value of OMA-IR cut-off that indicates insulin resistance is still an active research topic and several research works demonstrated the dependence of the threshold on various parameters such as race, gender and age. To the best of our knowledge, no study has been conducted on Omani population to evaluate the impact of these parameters on the value of the optimal HOMA-IR threshold. Besides, although machine learning techniques have been widely used in analyzing and predicting various diseases and related issues, there is very little research works that addressed this problem using a machine learning perspective. Our aim is therefore to develop a more accurate method based on machine learning technology for identifying individuals suffering from Insulin Resistance so that timely and adequate measures are taken to delay or even prevent the onset of DM in these individuals.

Layman's description

Diabetes Mellitus (DM) is one of the most challenging medical problems worldwide as well as in Oman. Insulin resistance (IR) is a key feature for the prognosis of diabetes mellitus type 2 and the homeostasis model assessment of insulin resistance (HOMA-IR) is commonly used for IR detection. This project aims to defining a reference range of HOMA-IR index in adult Omani population by implementing machine learning techniques. Identifying an optimum value of OMA-IR cut-off that indicates insulin resistance is still an active research topic and several research works demonstrated the dependence of the threshold on various parameters such as race, gender and age. To the best of our knowledge, no study has been conducted on Omani population to evaluate the impact of these parameters on the value of the optimal HOMA-IR threshold. Besides, although machine learning techniques have been widely used in analyzing and predicting various diseases and related issues, there is very little research works that addressed this problem using a machine learning perspective. Our aim is therefore to develop a more accurate method based on machine learning technology for identifying individuals suffering from Insulin Resistance so that timely and adequate measures are taken to delay or even prevent the onset of DM in these individuals.
AcronymTTotP
StatusNot started

Keywords

  • HOMA-IR
  • Diabetes Mellitus
  • Machine Learning Techniques
  • Support Vector Machines
  • Artificial Neural Networks

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.