PENGEMBANGAN DETEKSI DINI RISIKO KEMATIAN NEONATAL MENGGUNAKAN ARTIFICIAL INTELLIGENCE (AI)  BERBASIS WEB

Farida Umamy; Eldesi Medisa Ilmawati; Wilda Nurfadila Tanjung

doi:10.31004/prepotif.v9i3.49590

Authors

Farida Umamy Sekolah Tinggi Ilmu Kesehatan As Syifa
Eldesi Medisa Ilmawati Sekolah Tinggi Ilmu Kesehatan As Syifa
Wilda Nurfadila Tanjung Sekolah Tinggi Ilmu Kesehatan As Syifa

DOI:

https://doi.org/10.31004/prepotif.v9i3.49590

Keywords:

Kematian Neonatal, Deteksi Dini, Aplikasi Web, Artificial Intelligence, Random Forests

Abstract

Kematian neonatal masih menjadi salah satu penyebab utama tingginya angka kematian bayi di dunia, khususnya di negara berkembang. Deteksi dini terhadap risiko kematian neonatal sangat penting untuk meningkatkan peluang intervensi tepat waktu dan menurunkan angka mortalitas. Penelitian ini bertujuan mengembangkan sistem deteksi dini risiko kematian neonatal berbasis Artificial Intelligence (AI) menggunakan model Random Forests yang diintegrasikan ke dalam aplikasi web. Penelitian menggunakan metode Research and Development (R&D) dengan tahapan analisis kebutuhan, perancangan sistem, implementasi model AI, dan pengujian akurasi. Data diperoleh dari rekam medis pasien neonatal yang mencakup parameter klinis, tanda vital, riwayat persalinan, dan faktor risiko ibu. Model Random Forests dilatih untuk memproses data tersebut dan menghasilkan prediksi probabilitas risiko kematian neonatal, disertai rekomendasi tindakan klinis berbasis pedoman keperawatan. Pengujian dilakukan pada 300 set data pasien dengan hasil tingkat akurasi keseluruhan sebesar 97%, precision 96%, recall 95%, dan F1-score 95,5%. Hasil ini menunjukkan bahwa sistem yang dikembangkan mampu memberikan prediksi yang andal dan rekomendasi intervensi secara cepat. Kesimpulannya, penerapan AI berbasis web dengan model Random Forests efektif digunakan untuk deteksi dini risiko kematian neonatal, sehingga berpotensi menjadi alat bantu pengambilan keputusan klinis di fasilitas kesehatan. Optimalisasi basis pengetahuan dan perluasan data pelatihan diperlukan untuk meningkatkan akurasi pada berbagai kondisi klinis yang lebih kompleks.

References

Andrade-Rivas, F. et al. (2024) ‘Epidemiological insights into neonatal deaths: The role of cooking fuel pollution in Colombia’, International Journal of Hygiene and Environmental Health, 261(July), p. 114429. Available at: https://doi.org/10.1016/j.ijheh.2024.114429.

Dimitrova, Asya et al. (2024) ‘Temperature-related neonatal deaths attributable to climate change in 29 low- and middle-income countries’, Nature Communications, 15(1), pp. 1–11. Available at: https://doi.org/10.1038/s41467-024-49890-x.

Garvey, M. (2024) ‘Neonatal Infectious Disease: A Major Contributor to Infant Mortality Requiring Advances in Point-of-Care Diagnosis’, Antibiotics, 13(9), pp. 1–14. Available at: https://doi.org/10.3390/antibiotics13090877.

Ilham, A. et al. (2025) ‘Fetal Health Risk Classification Using Important Feature Selection and Cart Model on Cardiotocography Data’, Informatica (Slovenia), 49(1), pp. 193–206. Available at: https://doi.org/10.31449/inf.v49i1.5658.

Indonesia, K.K.R. (2024) ‘Fokus Menurunkan Angka Kematian Anak, Menkes Budi Tegaskan Keberlanjutan Program Vaksinasi GAVI di Indonesia’, Sehat Negeriku - Kementerian Kesehatan Republik Indonesia [Preprint]. Available at: https://sehatnegeriku.kemkes.go.id/baca/rilis-media/20241204/0746955/fokus-menurunkan-angka-kematian-anak-menkes-budi-tegaskan-keberlanjutan-program-vaksinasi-gavi-di-indonesia/.

Jayatilake, S.M.D.A.C. and Ganegoda, G.U. (2021) ‘Involvement of Machine Learning Tools in Healthcare Decision Making’, Journal of Healthcare Engineering, 2021. Available at: https://doi.org/10.1155/2021/6679512.

Jieyang, P. et al. (2023) ‘A systematic review of data-driven approaches to fault diagnosis and early warning’, Journal of Intelligent Manufacturing, 34(8), pp. 3277–3304. Available at: https://doi.org/10.1007/s10845-022-02020-0.

Keles, E. and Bagci, U. (2023) ‘The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review’, npj Digital Medicine, 6(1), pp. 13–15. Available at: https://doi.org/10.1038/s41746-023-00941-5.

Khashu, M. and Allegaert, K. (2025) ‘Editorial: What is new on the horizon in neonatology? Recent advances in monitoring, diagnostics, and therapeutics in neonatal care’, Frontiers in Pediatrics, 13(January), pp. 1–4. Available at: https://doi.org/10.3389/fped.2025.1552262.

Kresnawati, W. et al. (2025) ‘Quality improvement on reducing neonatal mortality through intensive Clinical Mentorship Intervention: a case study in Biak Regional Hospital, Papua-Indonesia’, BMJ Open Quality, 14(1), pp. 1–8. Available at: https://doi.org/10.1136/bmjoq-2024-002862.

Lubrano, C. et al. (2022) ‘Perinatal and Neonatal Outcomes in Fetal Growth Restriction and Small for Gestational Age’, Journal of Clinical Medicine, 11(10). Available at: https://doi.org/10.3390/jcm11102729.

Mohamed, H.A. et al. (2022) ‘Neonatal mortality and associated factors among neonates admitted to neonatal intensive care unit at public hospitals of Somali Regional State, Eastern Ethiopia: A multicenter retrospective analysis’, PLoS ONE, 17(5 5), pp. 1–16. Available at: https://doi.org/10.1371/journal.pone.0268648.

Ooi, K.-B. et al. (2025) ‘The Potential of Generative Artificial Intelligence Across Disciplines: Perspectives and Future Directions’, Journal of Computer Information Systems, 65(1), pp. 76–107. Available at: https://doi.org/10.1080/08874417.2023.2261010.

Salam, A. and Abhinesh, N. (2024) ‘Revolutionizing dermatology: The role of Artificial Intelligence in clinical practice’, IP Indian Journal of Clinical and Experimental Dermatology, 10(2), pp. 107–112. Available at: https://doi.org/10.18231/j.ijced.2024.021.

Saifuddin, A. B. (2021). Ilmu Kebidanan. Yayasan Bina Pustaka Sarwono Prawirohardjo.

Shepherd, E. et al. (2024) ‘Neonatal magnesium sulphate for neuroprotection: A systematic review and meta-analysis’, Developmental Medicine and Child Neurology, 66(9), pp. 1157–1172. Available at: https://doi.org/10.1111/dmcn.15899.

Tesfay, N. et al. (2022) ‘Cause and risk factors of early neonatal death in Ethiopia’, PLoS ONE, 17(9 September), pp. 1–22. Available at: https://doi.org/10.1371/journal.pone.0275475.

Umamy, F., Harahap, I.A. and Christiani, M. (2021) ‘Effect of Pineapple Juice on Perineal Wound Healing in Postpartum Mothers at Anugrah Clinic’, Science Midwifery, 10(1), pp. 461–466. Available at: www.midwifery.iocspublisher.org.

Vasconcelos, A. et al. (2024) ‘Factors associated with perinatal and neonatal deaths in Sao Tome & Principe: a prospective cohort study’, Frontiers in Pediatrics, 12(February), pp. 1–14. Available at: https://doi.org/10.3389/fped.2024.1335926.

Wudu, M.A. et al. (2025) ‘Incidence and predictors of mortality among neonates admitted with birth asphyxia to neonatal intensive care units in Ethiopia: a systematic review and meta-analysis’, BMC Pediatrics, 25(1). Available at: https://doi.org/10.1186/s12887-025-05481-3.

Yaqoob, A. et al. (2025) ‘SGA-Driven feature selection and random forest classification for enhanced breast cancer diagnosis : A comparative study’, pp. 1–23.