Model Klasifikasi Usia Kematian Neonatal (≤1 Hari dan >1 Hari) Berbasis Machine Learning
DOI:
https://doi.org/10.30606/rjti.v5i1.4302Keywords:
Prediksi, Neonatal, Usia, Model, Machine LearningAbstract
Periode neonatal, khususnya dalam 24 jam pertama kehidupan, merupakan fase kritis dengan risiko morbiditas dan mortalitas tinggi. Identifikasi pola klinis yang membedakan neonatus usia ≤1 hari dan >1 hari penting untuk mendukung pengambilan keputusan klinis berbasis data. Tujuan penelitian ini yaitu membandingkan performa beberapa algoritma machine learning dalam mengklasifikasikan usia neonatus serta mengidentifikasi faktor klinis yang paling berkontribusi. Penelitian analitik observasional ini menggunakan data sekunder rekam medis neonatus sebanyak 41 kasus di rumah sakit X di kota Semarang. Variabel prediktor meliputi jenis kelamin, usia gestasi, berat badan, tinggi badan, jumlah diagnosa sekunder, diagnosa utama, dan cara melahirkan. Lima algoritma diuji: Logistic Regression, Support Vector Machine (RBF), Random Forest, HistGradientBoosting, dan XGBoost. Evaluasi dilakukan menggunakan Stratified K-Fold Cross Validation dengan metrik akurasi, presisi makro, recall makro, dan F1 score. Analisis faktor terpenting dilakukan menggunakan Random Forest. Random Forest menunjukkan performa terbaik dengan akurasi 0,686 dan F1 tertimbang 0,610 ± 0,182. HistGradientBoosting dan SVM mencapai akurasi 0,657, sedangkan Regresi Logistik dan XGBoost masing-masing 0,595 dan 0,557. Usia gestasi merupakan faktor paling berpengaruh, diikuti tinggi badan, jumlah diagnosa sekunder, dan berat badan. Beberapa diagnosa utama terkait gangguan pernapasan juga termasuk dalam faktor penting. Random Forest memberikan kombinasi akurasi dan stabilitas terbaik dalam memprediksi usia kematian bayi baru lahir.
Downloads
References
L. Hug, M. Alexander, D. You, and L. Alkema, “National, regional, and global levels and trends in neonatal mortality between 1990 and 2017, with scenario-based projections to 2030: A systematic analysis,†Lancet Glob. Health, vol. 7, no. 6, pp. e710–e720, 2019.
M. J. Sankar, C. K. Natarajan, R. R. Das, R. Agarwal, A. Chandrasekaran, and V. K. Paul, “When do newborns die? A systematic review of timing of overall and cause-specific neonatal deaths in developing countries,†Lancet Glob. Health, vol. 4, no. 10, pp. e700–e711, 2016.
World Health Organization, “Newborn mortality fact sheet,†Geneva, Switzerland: WHO, 2023.
R. L. Goldenberg, J. F. Culhane, J. D. Iams, and R. Romero, “Epidemiology and causes of preterm birth,†Lancet, vol. 371, no. 9606, pp. 75–84, 2008.
H. Blencowe et al., “National, regional, and worldwide estimates of preterm birth rates in the year 2010,†Lancet, vol. 379, no. 9832, pp. 2162–2172, 2012.
B. J. Stoll et al., “Trends in care practices, morbidity, and mortality of extremely preterm neonates, 1993–2012,†JAMA, vol. 314, no. 10, pp. 1039–1051, 2015.
A. Rajkomar, J. Dean, and I. Kohane, “Machine learning in medicine,†N. Engl. J. Med., vol. 380, no. 14, pp. 1347–1358, 2019.
A. L. Beam and I. S. Kohane, “Big data and machine learning in health care,†JAMA, vol. 319, no. 13, pp. 1317–1318, 2018.
C. Cortes and V. Vapnik, “Support-vector networks,†Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995.
A. Esteva et al., “A guide to deep learning in healthcare,†Nat. Med., vol. 25, no. 1, pp. 24–29, 2019.
E. J. Topol, “High-performance medicine: The convergence of human and artificial intelligence,†Nat. Med., vol. 25, no. 1, pp. 44–56, 2019.
L. Breiman, “Random Forests,†Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
J. H. Friedman, “Greedy function approximation: A gradient boosting machine,†Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001.
G. Varoquaux, “Cross-validation failure: Small sample sizes lead to large error bars,†NeuroImage, vol. 180, pp. 68–77, 2018.
E. W. Steyerberg, Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating, 2nd ed. Cham, Switzerland: Springer, 2019.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,†in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2016, pp. 785–794.
G. Biau and E. Scornet, “A Random Forest guided tour,†Test, vol. 25, no. 2, pp. 197–227, 2016.
J. Lever, M. Krzywinski, and N. Altman, “Points of significance: Cross-validation,†Nat. Methods, vol. 13, no. 8, pp. 703–704, 2016.
G. S. Collins, J. B. Reitsma, D. G. Altman, and K. G. M. Moons, “Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement,†BMJ, vol. 350, p. g7594, 2015.
S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,†in Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 30, 2017, pp. 4765–4774.
T. G. Dietterich, “Ensemble methods in machine learning,†in Multiple Classifier Systems, Lecture Notes in Computer Science, vol. 1857, 2000, pp. 1–15.
R. Caruana and A. Niculescu-Mizil, “An empirical comparison of supervised learning algorithms,†in Proc. 23rd Int. Conf. Mach. Learn. (ICML), 2006, pp. 161–168.
W. S. Noble, “What is a support vector machine?†Nat. Biotechnol., vol. 24, no. 12, pp. 1565–1567, 2006.
C. Molnar, Interpretable Machine Learning, 2nd ed., 2022. [Online]. Available: https://christophm.github.io/interpretable-ml-book/
L. Wynants et al., “Prediction models for diagnosis and prognosis of COVID-19 infection: Systematic review and critical appraisal,†BMJ, vol. 369, p. m1328, 2020.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nugraheni Kusumawati, Hugi Cerlyawat, Yanita Sri Mulyani, Evina Widianawati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Riau Jurnal Teknik Informatika provides open access to anyone so that the information and findings in these articles are useful for everyone. This journal's article content can be accessed and downloaded for free, free of charge, following the creative commons license used.
Riau Jurnal Teknik Informatika is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
