Klasifikasi Kelahiran Normal dan Kelahiran Tidak Normal menggunakan Algoritma Gradient Boosted Decision Trees di Kawasan Pegunungan: Studi Kasus Pasien di Kawasan Gunung Dempo

Angga Putrawansyah PB; M Izman Herdianyah

doi:10.55681/armada.v4i10.4301

Authors

Angga Putrawansyah PB Program Studi Teknik Informatika, Program Pascasarjana, Universitas Bina Darma, Indonesia
M Izman Herdianyah Program Studi Teknik Informatika, Program Pascasarjana, Universitas Bina Darma, Indonesia

DOI:

https://doi.org/10.55681/armada.v4i10.4301

Keywords:

Gradient Boosted Decision Trees (GBDT), Klasifikasi Persalinan, Kawasan Pegunungan, Rekam Medis Elektronik, Sistem Pendukung Keputusan

Abstract

Angka Kematian Ibu (AKI) di Indonesia, terutama pada wilayah terpencil dan pegunungan, masih menjadi permasalahan dalam pelayanan kesehatan maternal akibat keterbatasan akses geografis dan fasilitas kesehatan. Penelitian ini bertujuan mengimplementasikan dan mengevaluasi algoritma Gradient Boosted Decision Trees (GBDT) untuk mengklasifikasikan jenis persalinan normal dan tidak normal berdasarkan faktor klinis maternal serta geografis pasien ibu hamil di kawasan Gunung Dempo. Data penelitian menggunakan 350 rekam medis elektronik pasien UPTD RSD Besemah Kota Pagar Alam dengan atribut usia ibu, hipertensi, kadar glukosa, riwayat partus, kondisi janin, panggul sempit, ketuban pecah dini, kunjungan ANC, jarak, dan waktu tempuh menuju rumah sakit. Model dikembangkan melalui tahapan preprocessing dan Stratified Train-Test Split dengan 280 data latih dan 70 data uji. Hasil evaluasi menunjukkan akurasi 81,43%, presisi 84,9%, recall 90,0%, dan F1-Score 87,37%. Nilai recall yang tinggi menunjukkan kemampuan model dalam mendeteksi risiko persalinan secara dini. Penelitian ini berkontribusi dalam pengembangan sistem pendukung keputusan medis untuk membantu optimalisasi rujukan persalinan di daerah terpencil.

Downloads

Download data is not yet available.

References

Atmaja, D. M. U., Hakim, A. R., Basri, A., & Ariyanto, A. (2023). Klasifikasi Metode Persalinan pada Ibu Hamil Menggunakan Algoritma Random Forest Berbasis Mobile. JRST (Jurnal Riset Sains Dan Teknologi), 7(2), 161. https://doi.org/10.30595/jrst.v7i2.16705

Gondwe, T., Betha, K., Kusneniwar, G. N., Bunker, C. H., Tang, G., Simhan, H., Reddy, P. S., & Haggerty, C. L. (2019). Maternal factors associated with mode of delivery in a population with a high cesarean section rate. Journal of Epidemiology and Global Health, 9(4), 252–258. https://doi.org/10.2991/jegh.k.191017.001

Hamzah, H. A., Aadhanti, P. M., Raka, K., Romadhan, M. D., Deanasa, R. S., Farhan, M., & Chang, P. (2023). The Impact of Health Insurance on Maternal Health Care in Indonesia: A Systematic Review. Research Square, 1–10.

Kusumah, N., Idris, H., & Sitorus, R. J. (2022). Fakror-Faktor yang Mempengaruhi Pemilihan Persalinan Sectio. Jurnal Kesehatan, 13, 97–102.

Ningsih, M. P. S. D., & Noranita, B. (2018). Status Proses Persalinan Menggunakan Algoritma C4.5. Jurnal Masyarakat Informatika, 9(1), 1–13. https://doi.org/10.14710/jmasif.9.1.31478

Schapire, R. E. (2003). The Boosting Approach to Machine Learning: An Overview BT - Nonlinear Estimation and Classification. Nonlinear Estimation and Classification, 171(Chapter 9), 149–171.

Zhang, Z., Zhao, Y., Canes, A., Steinberg, D., & Lyashevska, O. (2019). Predictive analytics with gradient boosting in clinical medicine. 7(7). https://doi.org/10.21037/atm.2019.03.29

Abbas, A., Zha, M., Shah, S. A., & Khan, M. A. (2023). Machine learning-based prediction of pregnancy complications using maternal health data: A systematic review. Artificial Intelligence in Medicine, 139, 102524. https://doi.org/10.1016/j.artmed.2023.102524

Al-Mashrafi, S. M., Al-Balushi, S., Al-Mahrouqi, A., Al-Rashdi, I., & Al-Hinai, S. (2024). Machine learning approaches for predicting maternal health risks using clinical characteristics: A comparative study of ensemble models. BMC Pregnancy and Childbirth, 24, 245. https://doi.org/10.1186/s12884-024-07030-9

Aziz, H., Ahmed, F., & Khan, M. S. (2022). Predictive modelling of pregnancy outcomes using machine learning techniques: A review. Journal of Biomedical Informatics, 130, 104078. https://doi.org/10.1016/j.jbi.2022.104078

Barda, N., Riesel, D., Akriv, A., Levy, J., Finkel, U., & Netzer, D. (2021). Developing a machine learning model for predicting adverse pregnancy outcomes using electronic health records. NPJ Digital Medicine, 4, 123. https://doi.org/10.1038/s41746-021-00493-0

Bertsimas, D., Pawlowski, C., & Zhuo, Y. D. (2020). From predictive models to clinical decision support systems: Machine learning applications in healthcare. Operations Research, 68(6), 1583–1601. https://doi.org/10.1287/opre.2020.1997

Chen, T., & Guestrin, C. (2020). XGBoost: A scalable tree boosting system for machine learning applications. ACM Computing Surveys, 53(1), 1–36. https://doi.org/10.1145/3369784

Choudhury, A., & Islam, M. M. (2023). Explainable machine learning for healthcare prediction: Applications and challenges. Computers in Biology and Medicine, 153, 106540. https://doi.org/10.1016/j.compbiomed.2022.106540

Cui, S., Wang, D., Wang, Y., Yu, X., & Li, Y. (2023). Machine learning approaches for clinical risk prediction: A comparative analysis of gradient boosting algorithms. IEEE Access, 11, 45678–45689. https://doi.org/10.1109/ACCESS.2023.3278456

Dinh, A., Miertschin, S., Young, A., & Mohanty, S. D. (2021). A data-driven approach to predicting maternal health outcomes using machine learning. Journal of Medical Systems, 45, 112. https://doi.org/10.1007/s10916-021-01775-8

Fergus, P., Selvaraj, J., & Chalmers, C. (2022). Machine learning techniques for healthcare analytics: Predicting clinical outcomes using electronic health records. Future Generation Computer Systems, 128, 347–359. https://doi.org/10.1016/j.future.2021.10.012

Khan, M. A., Kadry, S., Al-Ali, A. K., Damaševičius, R., & Blažauskas, T. (2022). Machine learning and deep learning approaches for healthcare decision support systems. Sensors, 22(7), 2476. https://doi.org/10.3390/s22072476

Kohli, M., Prevedello, L. M., Filice, R. W., & Geis, J. R. (2021). Implementing machine learning in healthcare: Challenges and opportunities. Radiology, 298(2), 270–277. https://doi.org/10.1148/radiol.2020200375

Liu, Y., Chen, P. H. C., Krause, J., & Peng, L. (2021). How to read articles that use machine learning: Users’ guides to the medical literature. JAMA, 326(18), 1806–1816. https://doi.org/10.1001/jama.2021.17137

Mishra, S., Tripathy, H. K., & Mishra, D. (2023). Predictive analytics in maternal healthcare using machine learning algorithms. Healthcare Analytics, 3, 100158. https://doi.org/10.1016/j.health.2023.100158

Rajkomar, A., Dean, J., & Kohane, I. (2020). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347–1358. https://doi.org/10.1056/NEJMra1814259

Sufriyana, H., Husin, M., & Tan, K. (2022). Machine learning models for predicting pregnancy and obstetric outcomes: A systematic review. International Journal of Medical Informatics, 162, 104746. https://doi.org/10.1016/j.ijmedinf.2022.104746

Topol, E. J. (2021). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 27, 44–56. https://doi.org/10.1038/s41591-020-01170-5