Optimasi Keputusan Metode Persalinan dengan Algoritma C4.5
DOI:
https://doi.org/10.25047/j-remi.v6i1.4777Keywords:
C4.5 Algorithm, Data Mining, Classification, ChildbirthAbstract
In 2018, the Indonesian Ministry of Health conducted a survey revealing that the rate of deliveries via Caesarean Section (C-Section) had exceeded the WHO's maximum standard of 17.6%. At Aulia Hospital in Pekanbaru, the prevalence of C-Sections reached 76% per 1000 births, significantly higher than the international benchmark. This study aims to analyze the factors influencing delivery methods using the C4.5 algorithm. The research employs a quantitative analytic approach with Secondary Data Analysis (SDA). A dataset of 500 records with 11 variables was utilized, including maternal age, gestational age, hypertension, hemoglobin, glucose levels, delivery history, fetal position, Cephalopelvic Disproportion (CPD), premature rupture of membranes (PROM), oligohydramnios, and estimated fetal weight (EFW). The C4.5 algorithm demonstrated 92% accuracy in predicting delivery methods, with a precision of 75%, indicating its ability to correctly identify necessary C-Sections. Furthermore, it achieved a recall of 100%, reflecting its effectiveness in identifying all actual C-Section cases. The rule tree analysis highlighted delivery history as the primary determinant in selecting the delivery method. These findings are expected to support medical decision-making processes regarding delivery methods and improve the management of high C-Section rates.
References
[1] A. K. Pratiwi, “Faktor Risiko yang Mempengaruhi Metode Persalinan di Rumah Sakit Ibu dan Anak Sitti Khadijah 1 Makassar,” UMI Med. J., vol. 4, no. 2, pp. 63–69, Dec. 2019, doi: 10.33096/umj.v4i2.71.
[2] H. Rosyati, “Indikasi Janin Terhadap Persalinan Seksio Sesarea di Rumah Sakit Islam Jakarta Cempaka Putih,” J. Kedokt. dan Kesehat., vol. 10, no. 2, pp. 99–104, 2014.
[3] WHO, “Death rates from caesarean section far higher in developing countries, finds major global study,” 2019. https://www.qmul.ac.uk/media/news/2019/smd/death-rates-from-caesarean-section-far-higher-in-developing-countries-finds-major-global-study.html (accessed Mar. 24, 2024).
[4] A. Aprina and A. Puri, “Faktor-faktor yang Berhubungan dengan Persalinan Sectio Caesarea di RSUD dr. H. Abdul Moeloek Provinsi Lampung,” J. Kesehat., vol. 7, no. 1, pp. 90–96, Apr. 2016, doi: 10.26630/jk.v7i1.124.
[5] L. Indawati, D. R. Dewi, A. E. Pramono, and Y. Maryati, Manajemen Informasi Kesehatan V: Sistem Klaim dan Asuransi Pelayanan Kesehatan. Jakarta: Kementerian Kesehatan Republik Indonesia, 2018.
[6] D. Ardiansyah and W. Walim, “Algoritma C4.5 Untuk Klasifikasi Calon Peserta Lomba Cerdas Cermat Siswa Smp Dengan Menggunakan Aplikasi Rapid Miner,” J. Inkofar, vol. 1, no. 2, pp. 5–12, Jan. 2018, doi: 10.46846/jurnalinkofar.v1i2.29.
[7] M. Fatchan, N. Tedi, Alfiyan, Kurniawan, and E. Widodo, “Perbandingan Dalam Memprediksi Penyakit Liver Menggunakan Algoritma Naïve Bayes Dan K-Nearest Neighbor,” J. Pelita Teknol., vol. 16, no. 1, pp. 15–21, 2021.
[8] C. D. Sucipto, Metodologi Penelitian Kesehatan. Yogyakarta: Gosyen Publishing, 2020.
[9] Sugiyono, Metode Penelitian Kuantitatif Kualitatif, dan R&D. Bandung: Alfabeta, 2019.
[10] P. F. Armi and Y. Andriyani, “Klasifikasi Teknik Persalinan Berdasarkan Data Rekam Medis Menggunakan Algoritma Naive Bayes,” Universitas Riau, 2021.
[11] W. Widystuti and B. Darmawan, “Pengaruh Jumlah Data Set terhadap Akurasi Pengenalan dalam Deep Convolutional Network,” in Konferensi Nasional Sistem Informasi 2018, STMIK Atma Luhur Pangkalpinang, 2018, pp. 634–638.
[12] Anita, A. Wicaksono, and T. N. Padilah, “Pengaruh Jumlah Record Dataset Terhadap Algoritma Klasifikasi Berdasarkan Data Customer Churn,” J. Ilm. Inform., vol. 6, no. 1, pp. 1–10, Jun. 2021, doi: 10.35316/jimi.v6i1.1223.
[13] A. A. Robbani, A. M. Siregar, and D. S. Kusumaningrum, “Klasifikasi Penderita Penyakit Diabetes Menggunakan Algoritma C4.5,” Sci. Student J. Information, Technol. Sci., vol. 3, no. 1, pp. 76–82, 2022, [Online]. Available: https://journal.ubpkarawang.ac.id/mahasiswa/index.php/ssj/article/view/424/338
[14] G. A. Syafarina, “Penerapan Algoritma Neural Network Dalam Menentukan Prioritas Pengembangan Jalan Di Provinsi Kalimantan Selatan,” Technol. J. Ilm., vol. 7, no. 2, pp. 80–88, Jun. 2016, doi: 10.31602/tji.v7i2.618.
[15] A. Nuroctaviani, E. P. Satia, and D. Sonia, “Analisis Penggunaan Telemedicine pada Pendaftaran Rekam Medis Klinik Pratama Medika Antapani,” Cerdika J. Ilm. Indones., vol. 1, no. 8, pp. 910–916, Aug. 2021, doi: 10.36418/cerdika.v1i8.149.
[16] P. K. Arieska and N. Herdiani, “Pemilihan Teknik Sampling Berdasarkan Perhitungan Efisiensi Relatif,” J. Stat. Univ. Muhammadiyah Semarang, vol. 6, no. 2, pp. 166–171, 2018.
[17] H. Azis, P. Purnawansyah, F. Fattah, and I. P. Putri, “Performa Klasifikasi K-NN dan Cross Validation Pada Data Pasien Pengidap Penyakit Jantung,” Ilk. J. Ilm., vol. 12, no. 2, pp. 81–86, Aug. 2020, doi: 10.33096/ilkom.v12i2.507.81-86.
[18] M. Utomo and R. Prathivi, “Perbandingan Algoritma Support Vector Machine dan Decision Tree untuk Klasifikasi Performa Perusahaan,” Build. Informatics, Technol. Sci., vol. 6, no. 1, pp. 105–114, 2024, doi: https://doi.org/10.47065/bits.v6i1.5278.
[19] R. Yuliani, “Penerapan Algoritma C4.5 Berbasis AdaBoost untuk memprediksi Financial Distress Perusahaan,” Universitas Islam Negeri Sultan Syarif Kasim Riau, 2020.
[20] P. Rochjati, Skrining antenatal pada ibu hamil: pengenalan faktor risiko: deteksi dini ibu hamil risiko tinggi. Surabaya: Airlangga University Press, 2023.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Adinda Bunga Alfianah, Mudafiq Riyan Pratama, Muhammad Yunus, Veronika Vestine
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
