Deteksi Dini Diabetes menggunakan Machine Learning dengan Metode PCA dan XGBoost
DOI:
https://doi.org/10.26418/jp.v11i1.87780Keywords:
PCA, XGBoost, Deteksi Dini Diabetes, Machine LearningAbstract
Diabetes melitus merupakan masalah kesehatan global yang terus meningkat, dengan dampak signifikan terhadap kualitas hidup individu dan ekonomi masyarakat. Deteksi dini diabetes memainkan peran penting dalam mencegah komplikasi serius, tetapi metode konvensional sering kali terbatas oleh waktu, biaya, dan akurasi. Penelitian ini mengusulkan kombinasi Principal Component Analysis (PCA) dan algoritma XGBoost untuk meningkatkan akurasi dan efisiensi deteksi dini diabetes. PCA digunakan untuk mereduksi dimensi data, sementara XGBoost diterapkan sebagai algoritma klasifikasi. Dataset Pima Indians Diabetes Database digunakan sebagai objek penelitian, dengan tahapan meliputi preprocessing data, penerapan PCA, dan pelatihan model menggunakan XGBoost. Evaluasi model dilakukan menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa kombinasi PCA dan XGBoost meningkatkan performa model dibandingkan dengan XGBoost tanpa PCA, dengan peningkatan akurasi hingga 5.4% dan F1-score sebesar 6.45%. Namun, terdapat tantangan berupa sedikit penurunan recall, yang memerlukan optimasi lebih lanjut. Penelitian ini menunjukkan potensi besar teknologi machine learning dalam mendukung deteksi dini diabetes secara lebih cepat, akurat, dan efisien, serta membuka peluang implementasi di sistem kesehatan berbasis data.References
Hussain, A. (2023). Raising awareness and improving diabetes care to reduce the impact of complications. Diabetes Research and Clinical Practice, 205, 110968. https://doi.org/10.1016/j.diabres.2023.110968
Wahidin, M., Achadi, A., Besral, B., Kosen, S., Nadjib, M., Nurwahyuni, A., Ronoatmodjo, S., Rahajeng, E., Pane, M., & Kusuma, D. (2024). Projection of diabetes morbidity and mortality till 2045 in Indonesia based on risk factors and NCD prevention and control programs. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-54563-2
Ramasubramanian, S., C.N, S., Athreya, A. J., Devarajan, A., Shankar, A. U., & Kumar P, R. (2024). Data dimensionality reduction using principal component analysis: A case study. 2024 1st International Conference on Communications and Computer Science (InCCCS), 1–6. http://dx.doi.org/10.1109/incccs60947.2024.10593421
Wardhani, K. D. K., & Novayani, W. (2024). Principal Component Analysis for Prediabetes Prediction using Extreme Gradient Boosting (XGBoost). Scientific Journal of Informatics, 11(3), 863–872. https://doi.org/10.15294/sji.v11i3.13416
Uddin, Md. A., Islam, Md. M., Talukder, Md. A., Hossain, Md. A. A., Akhter, A., Aryal, S., & Muntaha, M. (2023). Machine learning based diabetes detection model for false negative reduction. Biomedical Materials & Devices, 2(1), 427–443. https://doi.org/10.1007/s44174-023-00104-w
Shaik, F., Yelchuri, R., Gudur, N. A., & Dash, J. K. (2024). ML applications in healthcare. How Machine Learning Is Innovating Today’s World, 201–220. https://doi.org/10.1002/9781394214167.ch14
Aigerim, Ismukhamedova., Indira, Uvaliyeva., Zhenisgul, Rakhmetullina. (2024). 1. Experimental study of a medical data analysis model based on comparative performance of classification algorithms. Indonesian Journal of Electrical Engineering and Computer Science, doi: 10.11591/ijeecs.v36.i1.pp672-684
Md., Alamin, Talukder., Md., Manowarul, Islam., Md., Ashraf, Uddin., Mohsin, Kazi., Majdi, Khalid., Arnisha, Akhter., Mohammad, Ali, Moni. (2024). 3. Towards Reliable Diabetes Prediction: Innovations in Data Engineering and Machine Learning Applications. Cold Spring Harbor Laboratory, doi: 10.1101/2024.07.14.603436
Dr. K. Kasturi. (2024). Comparison of machine learning models for diabetes prediction. International Journal of Advanced Research in Science, Communication and Technology, 531–536. https://doi.org/10.48175/ijarsct-19072
Li, M., Li, L., Cao, W., & Yin, X. (2023). Research on data dimensionality reduction visualization method based on principal component analysis. Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 22. http://dx.doi.org/10.1117/12.3004267
Acito, F. (2023). Dimensionality reduction. In Predictive Analytics with KNIME (pp. 85–103). Springer Nature Switzerland. http://dx.doi.org/10.1007/978-3-031-45630-5_5
Santos, V. de S. (2024). Comparison and selection of machine learning algorithms for diabetes prediction: An exploratory quantitative study based on medical data analysis. In Multidisciplinary Perspectives: Integrating Knowledge. Seven Editora. http://dx.doi.org/10.56238/sevened2024.007-053
Uyen Le, M. N., Zhou, J., Cuong Le, D. P., & Wang, D. (2024). Ensemble of xgboost classifiers based on LDA dimensionality reduction for predicting breast cancer. Universal Journal of Public Health, 12(3), 434–440. https://doi.org/10.13189/ujph.2024.120302
Garg, K., Gill, K. S., Malhotra, S., Devliyal, S., & Sunil, G. (2024). Implementing the XGBOOST classifier for bankruptcy detection and smote analysis for balancing its data. 2024 2nd International Conference on Computer, Communication and Control (IC4), 1–5. http://dx.doi.org/10.1109/ic457434.2024.10486274
Ramdani, F., & Furqon, M. T. (2022). The simplicity of XGBoost algorithm versus the complexity of Random Forest, Support Vector Machine, and Neural Networks algorithms in urban forest classification. F1000Research, 11, 1069. https://doi.org/10.12688/f1000research.124604.1
Merdin Shamal Salih. (2024). Diabetic Prediction based on Machine Learning Using PIMA Indian Dataset. Communications on Applied Nonlinear Analysis, 31(5s), 138–156. https://doi.org/10.52783/cana.v31.1008
