Related Experiment Video
Updated: Aug 24, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Harnessing machine learning models for non-invasive pre-diabetes screening in children and adolescents
Savitesh Kushwaha1, Rachana Srivastava1, Rachita Jain1
1Department of Community Medicine and School of Public Health, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India.
Insights
A new machine learning model accurately predicts pre-diabetes in children and adolescents using non-invasive methods. This tool enables early detection, allowing at-risk individuals to take steps to prevent diabetes progression.
Area of Science:
- Pediatric Endocrinology
- Machine Learning in Healthcare
- Preventive Medicine
Background:
- Pre-diabetes is a critical precursor to type 2 diabetes, particularly concerning in pediatric populations.
- Early identification of pre-diabetes in children and adolescents is vital for intervention and disease prevention.
Purpose of the Study:
- To develop and implement a cross-validated machine learning model for non-invasive pre-diabetes screening in young individuals.
- To create an automated tool for real-time pre-diabetes prediction.
Main Methods:
- Analysis of a national representative dataset (n=26,567) of children and adolescents (5-19 years) using HbA1c levels.
- Development and evaluation of six hyper-tuned machine learning models, considering eight features.
- Selection of the best model based on area under the receiver operator curve (AUC), Cohen's kappa, and cross-validation scores.
Main Results:
- The XGBoost classifier demonstrated the highest 10-fold cross-validation score (90.13%).
- Random Forest achieved the highest AUC (0.970), with XGBoost also showing strong performance (0.959).
- The selected XGBoost model was integrated into a screening tool for automated prediction.
Conclusions:
- A machine learning model for automated, real-time pre-diabetes screening has been successfully developed and deployed.
- The screening tool, usable on computers and adaptable to software, aids in early detection of pediatric pre-diabetes.
- Machine learning effectively identifies key features for pre-diabetes prediction, supporting preventive strategies.
Background And Objectives:
Pre-diabetes has been identified as an intermediate diagnosis and a sign of a relatively high chance of developing diabetes in the future. Diabetes has become one of the most frequent chronic disorders in children and adolescents around the world; therefore, predicting the onset of pre-diabetes allows a person at risk to make efforts to avoid or restrict disease progression. This research aims to create and implement a cross-validated machine learning model that can predict pre-diabetes using non-invasive methods.
Methods:
We have analysed the national representative dataset of children and adolescents (5-19 years) to develop a machine learning model for non-invasive pre-diabetes screening. Based on HbA1c levels the data (n = 26,567) was segregated into normal (n = 23,777) and pre-diabetes (n = 2790). We have considered eight features, six hyper-tuned machine learning models and different metrics for model evaluation. The final model was selected based on the area under the receiver operator curve (AUC), Cohen's kappa and cross-validation score. The selected model was integrated into the screening tool for automated pre-diabetes prediction.
Results:
The XG boost classifier was the best model, including all eight features. The 10-fold cross-validation score was highest for the XG boost model (90.13%) and least for the support vector machine (61.17%). The AUC was highest for RF (0.970), followed by GB (0.968), XGB (0.959), ETC (0.918), DT (0.908), and SVM (0.574) models. The XGB model was used to develop the screening tool.
Conclusion:
We have developed and deployed a machine learning model for automated real-time pre-diabetes screening. The screening tool can be used over computers and can be transformed into software for easy usage. The detection of pre-diabetes in the pediatric age may help avoid its enhancement. Machine learning can also show great competence in determining important features in pre-diabetes.
