Perbandingan Kinerja Algoritma KNN-DT-RF-SVM untuk Deteksi Dini Risiko Kematian Ibu
DOI:
https://doi.org/10.25047/j-remi.v6i2.5658Kata Kunci:
Maternal Mortality Rate, K-Nearest Neighbors, Decision Tree, Random Forest, Support Vector Machine, Health Risk PredictionAbstrak
Angka Kematian Ibu (AKI) di Indonesia masih menjadi permasalahan kesehatan yang signifikan, dengan data menunjukkan tingkat kematian ibu yang jauh di atas target Sustainable Development Goals (SDGs). Penelitian ini bertujuan untuk mengeksplorasi dan membandingkan kinerja algoritma K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), dan Support Vector Machine (SVM) dalam mendeteksi risiko kematian ibu. Dengan menggunakan dataset medis ibu hamil dari Puskesmas Sumbersari, model dibangun untuk mengklasifikasikan tiga kategori risiko kehamilan: risiko rendah (KRR), risiko tinggi (KRT), dan risiko sangat tinggi (KRST). Evaluasi model dilakukan berdasarkan metrik akurasi, precision, recall, dan F1-score. Hasil menunjukkan bahwa algoritma Random Forest memberikan kinerja terbaik dengan akurasi sebesar 76.7%, diikuti oleh Decision Tree dan SVM dengan akurasi 70%, sedangkan KNN memberikan akurasi terendah sebesar 50%. Tantangan utama yang dihadapi adalah ketidakseimbangan data dalam klasifikasi risiko sangat tinggi. Penelitian ini menyarankan penggunaan metode balancing data seperti SMOTE dan penambahan data untuk meningkatkan performa model. Temuan ini dapat digunakan untuk puskesmas dalam memberikan dasar untuk implementasi sistem deteksi dini berbasis machine learning guna mengurangi angka kematian ibu.
Referensi
[1] J. P. Souza et al., “A global analysis of the determinants of maternal health and transitions in maternal mortality,” Lancet Glob. Heal., vol. 12, no. 2, pp. e306–e316, Feb. 2024, doi: 10.1016/S2214-109X(23)00468-0.
[2] M. Syairaji, D. S. Nurdiati, B. S. Wiratama, Z. D. Prüst, K. W. M. Bloemenkamp, and K. J. C. Verschueren, “Trends and causes of maternal mortality in Indonesia: a systematic review,” BMC Pregnancy Childbirth, vol. 24, no. 1, pp. 1–14, Jul. 2024, doi: 10.1186/s12884-024-06687-6.
[3] M. N. Islam, S. N. Mustafina, T. Mahmud, and N. I. Khan, “Machine learning to predict pregnancy outcomes: a systematic review, synthesizing framework and future research agenda,” BMC Pregnancy Childbirth, vol. 22, no. 1, pp. 1–19, Apr. 2022, doi: 10.1186/s12884-022-04594-2.
[4] E. da Silva Rocha, F. L. de Morais Melo, M. E. F. de Mello, B. Figueiroa, V. Sampaio, and P. T. Endo, “On usage of artificial intelligence for predicting mortality during and post-pregnancy: a systematic review of literature,” BMC Med. Inform. Decis. Mak., vol. 22, no. 1, pp. 1–17, Dec. 2022, doi: 10.1186/s12911-022-02082-3.
[5] X. Zhang and H. Yang, “Improving Maternal Mortality Prediction through Machine Learning Algorithms,” J. Med. Syst., vol. 45, no. 2, pp. 65–72, 2021.
[6] S. Suparji, H. S. W. Nugroho, S. Sunarto, and A. S. Prayogi, “The high maternal mortality rate in Indonesia is a challenge that must be addressed immediately,” PAMJ - One Heal., vol. 14, pp. 1–6, 2024, doi: 10.11604/pamj-oh.2024.14.13.44464.
[7] M. H. Sylvain, E. C. Nyabyenda, M. Uwase, I. Komezusenge, F. Ndikumana, and I. Ngaruye, “Prediction of adverse pregnancy outcomes using machine learning techniques: evidence from analysis of electronic medical records data in Rwanda,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, pp. 1–13, Feb. 2025, doi: 10.1186/s12911-025-02921-z.
[8] E. N. Ekwonwune, C. I. Ubochi, and A. E. Duroha, “Data Mining as a Technique for Healthcare Approach,” Int. J. Commun. Netw. Syst. Sci., vol. 15, no. 09, pp. 149–165, 2022, doi: 10.4236/ijcns.2022.159011.
[9] N. Jothi, N. A. Rashid, and W. Husain, “Data Mining in Healthcare – A Review,” Procedia Comput. Sci., vol. 72, pp. 306–313, 2015, doi: 10.1016/j.procs.2015.12.145.
[10] H. S. Khamis, K. W. Cheruiyot, and S. Kimani, “Application of k- Nearest Neighbour Classification in Medical Data Mining,” Int. J. Inf. Commun. Technol. Res., vol. 4, no. 4, pp. 121–128, 2014.
[11] K. E. Setiawan, A. Kurniawan, and S. Y. Prasetyo, “Comparative analysis of machine learning decision tree-based models for predicting maternal health risks,” Procedia Comput. Sci., vol. 245, pp. 57–64, 2024, doi: 10.1016/j.procs.2024.10.229.
[12] A. Raza, H. U. R. Siddiqui, K. Munir, M. Almutairi, F. Rustam, and I. Ashraf, “Ensemble learning-based feature engineering to analyze maternal health during pregnancy and health risk prediction,” PLoS One, vol. 17, no. 11, pp. 1–29, Nov. 2022, doi: 10.1371/journal.pone.0276525.
[13] M. A. Rahman, R. M. Noor, S. Mallik, N. K. Santa, S. Deb, and A. Pathak, “Classification Of Health Risk Levels For Pregnant Women Using Support Vector Machine (SVM) Algorithm,” J. Comput. Eng., vol. 26, no. 3, pp. 7–17, 2024, doi: 10.9790/0661-2603010717.
[14] S. Uddin, I. Haque, H. Lu, M. A. Moni, and E. Gide, “Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction,” Sci. Rep., vol. 12, no. 1, pp. 1–11, Apr. 2022, doi: 10.1038/s41598-022-10358-x.
[15] T. M. Bosschieter et al., “Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomes,” J. Healthc. Informatics Res., pp. 1–25, Oct. 2023, doi: 10.1007/s41666-023-00151-4.
[16] M. M. Mijwil and R. A. Abttan, “Utilizing the Genetic Algorithm to Pruning the C4.5 Decision Tree Algorithm,” Asian J. Appl. Sci., vol. 9, no. 1, pp. 45–52, Feb. 2021, doi: 10.24203/ajas.v9i1.6503.
[17] D. Mennickent et al., “Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications,” Front. Endocrinol. (Lausanne)., vol. 14, pp. 1–22, May 2023, doi: 10.3389/fendo.2023.1130139.
[18] J. Liao et al., “Artificial intelligence assists precision medicine in cancer treatment,” Front. Oncol., vol. 12, pp. 1–16, Jan. 2023, doi: 10.3389/fonc.2022.998222.
[19] S. Yan, J. Li, and W. Wu, “Artificial intelligence in breast cancer: application and future perspectives,” J. Cancer Res. Clin. Oncol., vol. 149, no. 17, pp. 16179–16190, Nov. 2023, doi: 10.1007/s00432-023-05337-2.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Angga Rahagiyanto, Bakhtiyar Hadi Prakoso, Muhammad Yunus, Veronika Vestine, Gandu Eko Juliato Suyoso, Atma Deharja
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
