The Definition of Insulin Resistance Using HOMA-IR for Americans of Mexican Descent Using Machine Learning

Abstract

ObjectiveThe lack of standardized reference range for the homeostasis model assessment-estimated insulin resistance (HOMA-IR) index has limited its clinical application. This study defines the reference range of HOMA-IR index in an adult Hispanic population based with machine learning methods.MethodsThis study investigated a Hispanic population of 1854 adults, randomly selected on the basis of 2000 Census tract data in the city of Brownsville, Cameron County. Machine learning methods, support vector machine (SVM) and Bayesian Logistic Regression (BLR), were used to automatically identify measureable variables using standardized values that correlate with HOMA-IR; K-means clustering was then used to classify the individuals by insulin resistance.ResultsOur study showed that the best cutoff of HOMA-IR for identifying those with insulin resistance is 3.80. There are 39.1% individuals in this Hispanic population with HOMA-IR>3.80.ConclusionsOur results are dramatically different using the popular clinical cutoff of 2.60. The high sensitivity and specificity of HOMA-IR>3.80 for insulin resistance provide a critical fundamental for our further efforts to improve the public health of this Hispanic population.

Homeostasis Model Assessment of Insulin Resistance (HOMA-IR) in the Diagnosis of Insulin Resistance and Prediabetes

“…The cutoff value is different for different population like one large study study comprising of Hispanic population of 1854 adults concluded that cutoff value of HOMA-IR was 3.80. This value was far greater than popular clinical cutoff value of 2.6 (19) . If various limitations of HOMA-IR values and factors affecting its cut-off values in different population is kept in mind then it's one of the most reliable, less invasive, inexpensive, and less labor-intensive method to measure insulin resistance (20) .…”

Insulin and HOMA-IR in Healthy Young Mexicans: A Cut-off Points Proposal

“…The higher value reported for HOMA-IR (2.5), compared with those found in this study means that lower ROC curves (1.87 women, 1.55 men) could be explained by two facts: first, the detection of MetS in different ages (children or young), and second, in our study the young with one or two metabolic alterations were included in the 'Non-Healthy' group. In other study [14], using a machine learning algorithm involving several parameters related to MetS, including among them the serum aminotransferases, proposed a HOMA-IR cut-off point of 2.6 (and hence with 83% sensitivity, 54% specificity) for Americans of Mexican ascent. Furthermore, in one study [15] based on a sample population of 22 Japanese of 22-24 years old, set an upper threshold of 2.5 for HOMA-IR.…”

Beta Cell Dysfunction, Insulin Resistance and Impaired Insulin Sensitivity in Obese Adolescents

“…MK Garg et al (46) also concluded that waist hip ratio was negatively associated with insulin sensitivity and positively associated with insulin resistance which were statistically significant. Hui-Qi Qu et al (52) also concluded that insulin resistance was positively correlated with waist hip ratio. Waist hip ratio contributes an additional independent effect, which emphasizes the important role of central fat distribution in the risk of insulin resistance (52) .…”

“…Hui-Qi Qu et al (52) also concluded that insulin resistance was positively correlated with waist hip ratio. Waist hip ratio contributes an additional independent effect, which emphasizes the important role of central fat distribution in the risk of insulin resistance (52) . Otto Tschritter, MD et al (53) concluded that waist hip ratio was more in…”