Improving Gestational Diabetes Detection in Pregnancy through Machine Learning Models
The three forms of diabetes mellitus—Type 1, Type 2, and Gestational Diabetes Mellitus (GDM)—represent a significant public health issue in the modern era. The worldwide prevalence of GDM, a type of glucose intolerance usually diagnosed between weeks 24 and 28, has increased from 47.6 to 63.5 occur...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sir Syed University of Engineering and Technology, Karachi.
2024-12-01
|
| Series: | Sir Syed University Research Journal of Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sirsyeduniversity.edu.pk/ssurj/rj/index.php/ssurj/article/view/652 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The three forms of diabetes mellitus—Type 1, Type 2, and Gestational Diabetes Mellitus (GDM)—represent a significant public health issue in the modern era. The worldwide prevalence of GDM, a type of glucose intolerance usually diagnosed between weeks 24 and 28, has increased from 47.6 to 63.5 occurrences per 1,000 live births between 2011 and 2019. With increased risks among women who are overweight or obese, its global prevalence will reach 14% by 2022. In addition to raising the risk of developing Type 2 diabetes in the future, problems such as hypertension, preterm delivery, and neonatal hypoglycemia are associated with GDM. This study automates GDM identification using a variety of machine-learning approaches. These techniques include Decision Trees, Random Forest, and XGBoost. With an F1-score of 0.92 and a recall of 0.94, the Random Forest model outperformed the others. To enhance risk categorization and better serve varied groups, it is recommended that these models be further refined.
|
|---|---|
| ISSN: | 1997-0641 2415-2048 |