Optimizing Anemia Detection Using Effective Computational Techniques
Worldwide, anemia is the most common blood disease. The World Health Organization (WHO) defines anemia as the lack of red blood cells, which prevents the body from carrying enough oxygen to satisfy its requirements. Anemia is characterized by decreased erythrocyte mass, blood hemoglobin, and hemo...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
INTI International University
2024
|
| Subjects: | |
| Online Access: | http://eprints.intimal.edu.my/2021/1/jods2024_39.pdf http://eprints.intimal.edu.my/2021/2/561 http://eprints.intimal.edu.my/2021/ http://ipublishing.intimal.edu.my/jods.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Worldwide, anemia is the most common blood disease. The World Health Organization (WHO)
defines anemia as the lack of red blood cells, which prevents the body from carrying enough
oxygen to satisfy its requirements. Anemia is characterized by decreased erythrocyte mass, blood
hemoglobin, and hemocrit levels. Early detection and accurate diagnosis are essential for effective
management and therapy. The study's goal is to develop an algorithm for optimizing anemia
detection utilizing an effective computational technique. The study proposed a brand-new
Dynamic Gannet-tuned Light Gradient Boosting Machine (DG-LGBM) model for the detection of
anemia in typical clinical practice settings. In this study, anemia data is collected from a publicly
available dataset from Kaggle. The data was preprocessed using data cleaning and normalization
for the obtained data. The study aims to improve the predicted accuracy and efficiency of anemia
diagnosis by utilizing clinical and biochemical markers. The results demonstrate that, in
comparison to traditional methods, the DG-LGBM model performed better in terms of anemia
detection rates, highlighting the potential of computational tools to completely transform anemia
screening practices. In a comparative analysis, the proposed model is validated using precision
(92%), recall (91.71%) f1-score (93.07%), and accuracy (91.06%) values. In addition to advancing
the area of medical diagnostics, this study highlights the significance of technology in enhancing
healthcare outcomes for impacted communities. |
|---|