Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy
HIV/AIDS remains a significant global health challenge, requiring accurate predictive models for early detection and improved clinical decision-making. However, developing an effective predictive model faces challenges such as data imbalance and the presence of irrelevant features, which can comprom...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Politeknik Negeri Batam
2025-03-01
|
| Series: | Journal of Applied Informatics and Computing |
| Subjects: | |
| Online Access: | https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850172225129283584 |
|---|---|
| author | Abdul Mizwar A Rahim Ahmad Ridwan Bambang Pilu Hartato Firman Asharudin |
| author_facet | Abdul Mizwar A Rahim Ahmad Ridwan Bambang Pilu Hartato Firman Asharudin |
| author_sort | Abdul Mizwar A Rahim |
| collection | DOAJ |
| description | HIV/AIDS remains a significant global health challenge, requiring accurate predictive models for early detection and improved clinical decision-making. However, developing an effective predictive model faces challenges such as data imbalance and the presence of irrelevant features, which can compromise model accuracy. This study aims to enhance the performance of AIDS infection prediction models by integrating feature selection, data balancing, and machine learning classification techniques. Feature selection is conducted using Pearson Correlation, Mutual Information, and Chi-Square tests to retain only the most relevant features. Random Oversampling, SMOTE, and ADASYN are employed to address data imbalance and improve model robustness. Nine machine learning algorithms, including Decision Tree, Random Forest, XGBoost, LightGBM, Gradient Boosting, Support Vector Machine, AdaBoost, and Logistic Regression, are tested for classification. Performance evaluation using confusion matrix, precision, recall, F1-score, and AUC-ROC shows that tree-based models (Random Forest, Extra Trees, and XGBoost) achieve the best results, particularly in handling minority class predictions. The study concludes that combining feature selection, data balancing, and machine learning techniques significantly improves predictive performance, making it a valuable approach for early detection and clinical decision support in HIV/AIDS diagnosis. Future research may explore hyperparameter tuning and real-world clinical data integration to enhance practical applicability. |
| format | Article |
| id | doaj-art-9ffb623ddff74bf09f5bc32b833b93de |
| institution | OA Journals |
| issn | 2548-6861 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Politeknik Negeri Batam |
| record_format | Article |
| series | Journal of Applied Informatics and Computing |
| spelling | doaj-art-9ffb623ddff74bf09f5bc32b833b93de2025-08-20T02:20:08ZengPoliteknik Negeri BatamJournal of Applied Informatics and Computing2548-68612025-03-019233834710.30871/jaic.v9i2.91256675Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing StrategyAbdul Mizwar A RahimAhmad RidwanBambang Pilu HartatoFirman AsharudinHIV/AIDS remains a significant global health challenge, requiring accurate predictive models for early detection and improved clinical decision-making. However, developing an effective predictive model faces challenges such as data imbalance and the presence of irrelevant features, which can compromise model accuracy. This study aims to enhance the performance of AIDS infection prediction models by integrating feature selection, data balancing, and machine learning classification techniques. Feature selection is conducted using Pearson Correlation, Mutual Information, and Chi-Square tests to retain only the most relevant features. Random Oversampling, SMOTE, and ADASYN are employed to address data imbalance and improve model robustness. Nine machine learning algorithms, including Decision Tree, Random Forest, XGBoost, LightGBM, Gradient Boosting, Support Vector Machine, AdaBoost, and Logistic Regression, are tested for classification. Performance evaluation using confusion matrix, precision, recall, F1-score, and AUC-ROC shows that tree-based models (Random Forest, Extra Trees, and XGBoost) achieve the best results, particularly in handling minority class predictions. The study concludes that combining feature selection, data balancing, and machine learning techniques significantly improves predictive performance, making it a valuable approach for early detection and clinical decision support in HIV/AIDS diagnosis. Future research may explore hyperparameter tuning and real-world clinical data integration to enhance practical applicability.https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9125machine learning classificationfeature selectionrandom oversamplinghiv/aids predictionensemble learning. |
| spellingShingle | Abdul Mizwar A Rahim Ahmad Ridwan Bambang Pilu Hartato Firman Asharudin Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy Journal of Applied Informatics and Computing machine learning classification feature selection random oversampling hiv/aids prediction ensemble learning. |
| title | Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy |
| title_full | Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy |
| title_fullStr | Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy |
| title_full_unstemmed | Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy |
| title_short | Machine Learning-Based Approach for HIV/AIDS Prediction: Feature Selection and Data Balancing Strategy |
| title_sort | machine learning based approach for hiv aids prediction feature selection and data balancing strategy |
| topic | machine learning classification feature selection random oversampling hiv/aids prediction ensemble learning. |
| url | https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9125 |
| work_keys_str_mv | AT abdulmizwararahim machinelearningbasedapproachforhivaidspredictionfeatureselectionanddatabalancingstrategy AT ahmadridwan machinelearningbasedapproachforhivaidspredictionfeatureselectionanddatabalancingstrategy AT bambangpiluhartato machinelearningbasedapproachforhivaidspredictionfeatureselectionanddatabalancingstrategy AT firmanasharudin machinelearningbasedapproachforhivaidspredictionfeatureselectionanddatabalancingstrategy |