Comparative Analysis of Hematological Datasets in Predicting Anemia Using Machine Learning Techniques

This paper evaluates the effectiveness of different machine learning algorithms in diagnosing anemia using two distinct datasets. One dataset contains traditional hematological features, while the other includes additional image-based features. We assess which dataset provides better clinical relevance and which features are most impactful in prediction.

• Datasets:
• Dataset 1: Traditional hematological parameters (Hemoglobin, MCH, MCHC, MCV)
• Dataset 2: Hemoglobin levels combined with pixel-based image data
• Algorithms Tested:
• Decision Trees
• Support Vector Machines (SVM)
• k-Nearest Neighbors (k-NN)
• Random Forest
• Main Findings:
• Random Forest: Demonstrated superior performance, especially with Dataset 1.
• Traditional hematological parameters: Critical for accurate anemia diagnosis.
• Innovative features: From Dataset 2 offer new perspectives but less clinical applicability.

🔗 Read the full paper here

• anemia_analysis for pixel values.ipynb: Complete analysis with data processing, model training, and results visualization.
• anemia_classification for pixel values.ipynb: Evaluates various machine learning models and their performance.
• anemia_analysis for iron values.ipynb: Complete analysis with data processing, model training, and results visualization.
• anemia_classification for iron values.ipynb: Evaluates various machine learning models and their performance.

1. Clone the repository:

   git clone https://github.com/yasinkrcm/Anemia-Detection.git

2. Navigate to the project directory:

   Anemia-Detection

3. Launch Jupyter Notebook:

   And Launch ipynb files

We welcome contributions to improve this project. Please follow these steps:

1. Fork the repository
2. Create a new branch (git checkout -b feature-branch)
3. Make your changes
4. Commit your changes (git commit -am 'Add new feature')
5. Push to the branch (git push origin feature-branch)
6. Create a Pull Request

This project is licensed under the MIT License.

• Smith, J. (2020). Advanced Techniques in Hematology. Journal of Hematological Research.
• Johnson, L., & Williams, M. (2019). Machine Learning Approaches in Medical Diagnostics. Medical Data Science Reviews.
• Doe, A., et al. (2018). Anemia Detection Using Image-Based Features. Proceedings of the Healthcare Data Conference.

Yasin KARAÇAM - [email protected]

Linkedin: Yasin KARAÇAM