Related Experiment Video
Updated: Jan 15, 2026
An In Ovo Model for Testing Insulin-mimetic Compounds
Published on: April 23, 2018
Machine learning predictive model to identify metabolic status in Mexican children, using homeostasis model
Karen E Villagrana-Bañuelos1, Carlos E Galván-Tejada1, Antonio García-Domínguez1
1Unidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Zacatecas, Zacatecas, Mexico, Instituto Mexicano del Seguro Social, México.
Insights
Total amylase activity shows potential in predicting metabolic syndrome and diabetes risk. This machine learning model aids in early identification of patients in the prepathogenic period.
Area of Science:
- Biochemistry
- Medical Diagnostics
- Machine Learning
Background:
- Childhood obesity is a significant global health concern, increasing the risk of metabolic syndrome and diabetes.
- Early disease detection is crucial, shifting healthcare focus towards pre-disease stages.
- Current diagnostic methods for established diseases rely on laboratory studies.
Purpose of the Study:
- To evaluate the utility of total amylase activity in predicting metabolic syndrome and diabetes.
- To develop a predictive model for identifying at-risk individuals before disease onset.
Main Methods:
- Utilized a database of 101 Mexican patients.
- Employed the homeostasis model assessment for insulin resistance (HOMA-IR) to categorize patients into normal, metabolic risk, and diabetes groups.
- Applied Random Forest (RF) machine learning for predictive analysis using amylase activity and HOMA-IR.
Main Results:
- The RF model achieved an area under the curve (AUC) of 0.7075.
- Achieved a specificity of 0.7619, sensitivity of 0.7142, and overall accuracy of 0.7500.
- Demonstrated the predictive capability of amylase activity and HOMA-IR.
Conclusions:
- A feasible prediction model can be developed using total amylase activity and RF.
- This model can assist in identifying individuals at risk for metabolic syndrome and diabetes during the prepathogenic phase.
- Highlights the potential of biochemical markers for early disease prediction.
Background:
Childhood obesity is a global health problem, as it is a risk factor for developing diseases such as metabolic syndrome and diabetes. At present, identifying these already established diseases is relatively easy for health professionals with the support of laboratory studies. The global trend in health involves acting before the disease is established.
Objectives:
The objective of this study is to identify whether total amylase activity is useful to predict which patients will develop metabolic syndrome or diabetes.
Material And Methods:
Using a database with 101 Mexican patients, considering the value of the homeostasis model assessment insulin resistance as a diagnostic variable in three groups < 2 normal, between 2 and 5 with metabolic risk and > 5 as diabetes, as well as the value of the amylase enzymatic activity. Random forest (RF) was used as a machine learning method.
Results:
The RF model obtained the following results: area under the curve 0.7075, specificity 0.7619, sensitivity 0.7142, and accuracy 0.7500.
Conclusions:
It is concluded that with these variables and RF, it is feasible to have a prediction model that contributes to identifying this type of patients in the prepathogenic period.
More Related Videos
06:04Author Spotlight: Assessing the Cardiovascular Profile of Patients with Metabolic Syndrome
Published on: September 27, 2024
08:13Study of In Vivo Glucose Metabolism in High-fat Diet-fed Mice Using Oral Glucose Tolerance Test OGTT and Insulin Tolerance Test ITT
Published on: January 7, 2018
