Harnessing Machine Learning for Diabetes Prediction: Optimizing Classifiers to Tackle Canada's Growing Health Challenge
Diabetes is becoming a leading public health issue affecting millions of people, and hospital costs are continually on the rise. Reactive diagnostic techniques, including simple glucose tests, are mainly used to diagnose diabetes when it has grown worse, which results in the late implementation of m...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IJMADA
2024-09-01
|
| Series: | International Journal of Management and Data Analytics |
| Subjects: | |
| Online Access: | https://ijmada.com/index.php/ijmada/article/view/54 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Diabetes is becoming a leading public health issue affecting millions of people, and hospital costs are continually on the rise. Reactive diagnostic techniques, including simple glucose tests, are mainly used to diagnose diabetes when it has grown worse, which results in the late implementation of measures that can potentially reduce cardiovascular disease and kidney failure. The existing gap is the lack of adequate risk predictors that would enable early detection of the susceptible person before the symptom(s) appear. To overcome this gap, the proposal incorporates machine learning (ML) that involves analyzing a given diabetes dataset and then applying different ML models for Diabetes prediction. Therefore, based on tree-based, function-based techniques, and rule-based models, the study seeks to establish the best and most understandable model for early diabetes prediction. This will help the healthcare providers manage conditions before they worsen while enhancing the quality of life of patients. This study provides evidence to inform practicing clinicians, public health agencies, and policymakers to design and implement more efficient diabetes prevention efforts. |
|---|---|
| ISSN: | 2816-9395 |