Implementasi Algoritma Decision Tree dan Random Forest dalam Prediksi Perdarahan Pascasalin
Main Article Content
Abstract
Perdarahan Postpartum (PPP) merupakan salah satu kegawatdaruatan pada persalinan yang dapat menyebabkan kematian di negara maju dan negara berkembang. Salah satu pencegahan terjadiya PPP dengan melakukan prediksi pada ibu bersalin dengan mempertimbangkan faktor faktor risiko menggunakan pendekatan model Machine Learning (ML). Algoritma Random Forest (RF) dan Decision Tree (DT) merupakan algoritma yang digunakan dalam prediksi kejadian PPP. Tujuan dari penelitian ini adalah mengembangkan kinerja dari Algoritma RF dan Algoritma RF untuk mengklasifikasi kejadian PPP. Hasil analisis Berdasarkan hasil analisis univariat yang ditunjukkan pada tabel 1 didapatkan ibu yang memiliki paritas > 4 sebanyak 102 orang (20,4%), jarak kehamilan ibu yang ≤ 2 tahun sebanyak 310 orang (62%), ibu pasca bersalin yang mengalami anemia sebanyak 124 orang (24,8%), ibu yang melahirkan bayi makrosomia sebanyak 60 orang (12 %), ibu yang mengalami komplikasi persalinan sebanyak 229 orang (45,8 %),ibu yang mengalami kehamilan ganda sebanyak 16 orang (3,2%), umur ibu yang berisiko sebanyak 132 orang (26,4%). Perbandingan tingkat akurasi algoritma RF mencapai 0,830 dibandingkan dengan algoritma DT sebesar 0.820, AUC RF 0.74. Hal ini menunjukan bahwa Algoritma RF mempunya perfomance metric lebih naik dibandingkan dengan algoritma DT. Algoritma Random Forest dapat dianggap sebagai salah satu algoritma representatif ML, yang dikenal karena kemudahannya dan efektivitasnya
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[2] A. Sunder et al., “Maternal Obesity: An Obstetric Risk,” Cureus, vol. 14, no. 9, pp. 1–9, 2022, doi: 10.7759/cureus.29345.
[3] K. C. Wormer, R. T. Jamil, and S. B. Bryant, “Acute Postpartum Hemorrhage,” StatPearls, May 2022.
[4] WHO, WHO recommendations: Uterotonics for the prevention of postpartum haemorrhage. 2018.
[5] Kemenkes, profil kesehatan Indonesia 2019. 2019.
[6] Kemenkes, Profil Kesehatan Indonesia Tahun 2020. 2020.
[7] Kemenkes RI., Profil Kesehatan Indonesia. 2021.
[8] B. Boujarzadeh, A. Ranjbar, F. Banihashemi, V. Mehrnoush, F. Darsareh, and M. Saffari, “Machine learning approach to predict postpartum haemorrhage: A systematic review protocol,” BMJ Open, vol. 13, no. 1, pp. 1–4, 2023, doi: 10.1136/bmjopen-2022-067661.
[9] G. Stiglic, P. Kocbek, N. Fijacko, M. Zitnik, K. Verbert, and L. Cilar, “Interpretability of machine learning-based prediction models in healthcare,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 10, no. 5, p. e1379, Sep. 2020, doi: 10.1002/WIDM.1379.
[10] W. Febriani, G. W. Nurcahyo, and S. Sumijan, “Diagnosa Penyakit Rubella Menggunakan Metode Fuzzy Tsukamoto,” J. Sistim Inf. dan Teknol., 2019, doi: 10.35134/jsisfotek.v1i3.4.
[11] S. E. Dunkerton, Y. B. Jeve, N. Walkinshaw, E. Breslin, and T. Singhal, “Predicting Postpartum Hemorrhage (PPH) during Cesarean Delivery Using the Leicester PPH Predict Tool: A Retrospective Cohort Study,” Am. J. Perinatol., vol. 35, no. 2, pp. 163–169, 2018, doi: 10.1055/s-0037-1606332.
[12] J. Liu et al., “Machine learning-based prediction of postpartum hemorrhage after vaginal delivery: combining bleeding high risk factors and uterine contraction curve,” Arch. Gynecol. Obstet., vol. 306, no. 4, pp. 1015–1025, 2022, doi: 10.1007/s00404-021-06377-0.
[13] J. Kang et al., “Prediction model for massive transfusion in placenta previa during cesarean section,” Yonsei Med. J., vol. 61, no. 2, pp. 154–160, 2020, doi: 10.3349/ymj.2020.61.2.154.
[14] nur andi fahira, abd rahman, and herman kurniawan, “12622-39746-1-Pb,” J. Kesehat. Tadulako, vol. 5, no. 1, pp. 26–31, 2019.
[15] A. Kristianingsih, H. Mukhlis, and E. Ermawati, “Faktor-faktor yang berhubungan dengan kejadian perdarahan postpartum di RSUD Pringsewu,” J. Wellnes, vol. 2, no. February, pp. 309–313, 2020.
[16] N. M. Abdulkareem and A. M. Abdulazeez, “Machine Learning Classification Based on Radom Forest Algorithm: A Review,” Int. J. Sci. Bus., vol. 5, no. 2, pp. 128–142, 2021, doi: 10.5281/zenodo.4471118.
[17] U. Erdiansyah, A. Irmansyah Lubis, and K. Erwansyah, “Komparasi Metode K-Nearest Neighbor dan Random Forest Dalam Prediksi Akurasi Klasifikasi Pengobatan Penyakit Kutil,” J. Media Inform. Budidarma, vol. 6, no. 1, p. 208, 2022, doi: 10.30865/mib.v6i1.3373.
[18] S. Oktarian, S. Defit, and Sumijan, “Clustering Students’ Interest Determination in School Selection Using the K-Means Clustering Algorithm Method,” J. Inf. dan Teknol., vol. 2, pp. 68–75, 2020, doi: 10.37034/jidt.v2i3.65.
[19] 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 November, 2022, doi: 10.1371/journal.pone.0276525.
[20] S. Syafwandi, D. Setyo Sembodo, A. Tua Munthe, and A. Sumarno, “Analysis of The Use of Sawdust Waste As Concrete Mixture Add Material Against Workability and Compressive Strength Concrete With Three Concrete Treatment Methods,” Int. J. Eng. Sci. Inf. Technol., vol. 1, no. 2, 2021, doi: 10.52088/ijesty.v1i2.109.
[21] K. K. Venkatesh et al., “Machine Learning and Statistical Models to Predict Postpartum Hemorrhage,” Obstet. Gynecol., vol. 135, no. 4, pp. 935–944, 2020, doi: 10.1097/AOG.0000000000003759.
[22] M. Schonlau and R. Y. Zou, “The random forest algorithm for statistical learning,” Stata J., vol. 20, no. 1, pp. 3–29, 2020, doi: 10.1177/1536867X20909688.
[23] P. Probst and A. L. Boulesteix, “To tune or not to tune the number of trees in random forest,” J. Mach. Learn. Res., vol. 18, pp. 1–8, 2018.
[24] D. Maisa Putra, O. Oktamianiza, M. Yuniar, and W. Fadhila, “Study Literature Review On Returning Medical Record Documents Using HOT-FIT Method,” Int. J. Eng. Sci. Inf. Technol., vol. 1, no. 1, 2021, doi: 10.52088/ijesty.v1i1.102.
[25] F. Wu, X. Liu, Y. Wang, X. Li, and M. Zhou, “Research on Evaluation Model of Hospital Informatization Level Based on Decision Tree Algorithm,” Secur. Commun. Networks, vol. 2022, 2022, doi: 10.1155/2022/3777474.
[26] B. Charbuty and A. Abdulazeez, “Classification Based on Decision Tree Algorithm for Machine Learning,” J. Appl. Sci. Technol. Trends, vol. 2, no. 01, pp. 20–28, 2021, doi: 10.38094/jastt20165.
[27] W. Deng, Y. Guo, J. Liu, Y. Li, D. Liu, and L. Zhu, “A missing power data filling method based on improved random forest algorithm,” Chinese J. Electr. Eng., vol. 5, no. 4, pp. 33–39, 2019, doi: 10.23919/CJEE.2019.000025.
[28] Y. Zhang, X. Wang, N. Han, and R. Zhao, “Ensemble Learning Based Postpartum Hemorrhage Diagnosis for 5G Remote Healthcare,” IEEE Access, vol. 9, pp. 18538–18548, 2021, doi: 10.1109/ACCESS.2021.3051215.
[29] V. Mehrnoush, A. Ranjbar, M. V. Farashah, F. Darsareh, M. Shekari, and M. S. Jahromi, “Prediction of postpartum hemorrhage using traditional statistical analysis and a machine learning approach,” AJOG Glob. Reports, vol. 3, no. 2, p. 100185, 2023, doi: 10.1016/j.xagr.2023.100185.
[30] C. Iwendi et al., “COVID-19 patient health prediction using boosted random forest algorithm,” Front. Public Heal., vol. 8, no. July, pp. 1–9, 2020, doi: 10.3389/fpubh.2020.00357.