Classification of Anxiety Levels of IGD Patients at RSU Royal Prima Medan Using Support Vector Machine (SVM) Algorithm

Kharisma Gunanta Ginting; Nugroho Prasetyo; Al Vino Gunawan; Magdalena Sihombing; Adli Abdillah Nababan

doi:10.34148/teknika.v14i2.1243

Authors

Kharisma Gunanta Ginting Informatics Engineering Department, Universitas Prima Indonesia, Medan, North Sumatra, Indonesia
Nugroho Prasetyo Informatics Engineering Department, Universitas Prima Indonesia, Medan, North Sumatra, Indonesia
Al Vino Gunawan Informatics Engineering Department, Universitas Prima Indonesia, Medan, North Sumatra, Indonesia
Magdalena Sihombing Informatics Engineering Department, Universitas Prima Indonesia, Medan, North Sumatra, Indonesia
Adli Abdillah Nababan Informatics Engineering Department, Universitas Prima Indonesia, Medan, North Sumatra, Indonesia

DOI:

https://doi.org/10.34148/teknika.v14i2.1243

Keywords:

SMOTE, Support Vector Machine, Anxiety Classification, Oversampling, Emergency Installation

Abstract

The level of patient anxiety in the Emergency Department (ED) is an important indicator that affects the diagnosis and medical management process. However, the classification of anxiety levels is often hampered by data imbalance, which can reduce the accuracy of predictive models. This study aims to develop a patient anxiety level classification model in the ED using the Support Vector Machine (SVM) algorithm with the application of the Synthetic Minority Oversampling Technique (SMOTE) to address the class imbalance issue. The data used consists of 734 patient samples divided into 80% training data and 20% testing data, including physiological parameters such as systolic and diastolic blood pressure, respiratory rate, heart rate, and demographic data such as age and gender. The preprocessing process includes imputing missing values and normalizing numerical features so that the model can learn optimally. Performance evaluation shows that the use of SMOTE increases classification accuracy from 95% to 97%, as well as improving precision, recall, and F1-score metrics at almost all anxiety levels. Visualization of the relationships between numerical features also reveals significant correlation patterns between physiological variables and patient anxiety levels. The results of this study confirm the effectiveness of SMOTE in addressing data imbalance, thus producing a more accurate anxiety level classification model that can serve as an aid in clinical decision-making. Thus, the developed model has significant clinical utility potential as a diagnostic aid that can accelerate and improve the accuracy of patient management in the emergency department, thereby supporting the overall improvement of healthcare service quality.

Downloads

Download data is not yet available.

References

[1] RSU Royal Prima Medan, "Profile of Royal Prima Hospital," [Online]. Available: https://royalprima.com/. [Accessed 3 March 2025].

[2] F. Lainsamputty and M. Wuisang, "Hubungan antara Kecemasan dan Karakteristik Pasien di Instalasi Gawat Darurat Rumah Sakit di Sulawesi Tengah," Journal of Islamic Medicine, vol. VI, no. 01, pp. 28-38, 2022, doi: https://doi.org/10.18860/jim.v6i1.15331.

[3] L. Fan, "Effect of Brand Image, Service Quality and Facilities on Hospitalization Patients' Satisfaction at Rs Royal Prima Medan," International Journal of Research in Engineering and Science (IJRES), vol. XI, no. 3, pp. 346-350, 2023, doi: http://dx.doi.org/10.52155/ijpsat.v34.1.4529.

[4] H. Yu , X. Mujun, L. Xin, Z. Ping, F. Limei, L. Aming and L. Xinquan, "Short Sleep Duration as a Risk Factor for Depression, Anxiety and Fatigue in Patients with Leukemia," Neuropsychiatric Disease and Treatment , no. 18, p. 1573–1582 , 2022, doi: https://doi.org/10.2147/ndt.s362229

[5] A. P. d. M. Simplício, P. C. d. A. Viola, L. C. d. C. Lavôr and e. a. , "Unhealthy Dietary Pattern Associated with Common Mental Disorders in Adults and Older Adults: A Population-based Study," Bentham Science Publishers, vol. XX, pp. 1155-1164, 2024, doi: https://doi.org/10.2174/1573401319666230503155748

[6] T. Kechine, T. Ali, T. Worku, L. Abdisa and T. A. Yadeta, "Anxiety and Associated Factors Among Clients on Highly Active Antiretroviral Therapy (HAART) in Public Hospitals of Southern Ethiopia: A Multi-Center Cross-Sectional Study," Psychology Research and Behavior Management, vol. XV, p. 3889–3900, 2022, doi: https://doi.org/10.2147/prbm.s385630.

[7] T. Anjarsari, I. R. I. Astutik and U. Indahyanti, "Deteksi Dini Gangguan Kecemasan Menggunakan Metode Naïve Bayes," JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika, vol. VII, no. 04, pp. 1198 - 1210, 2022, doi: https://doi.org/10.29100/jipi.v7i4.3197.

[8] M. Andrian, N. Aristiya, S. Rahayu and A. Novita, "Efektifitas Pemberian Terapi Slow Deep Breathing dan Terapi Dzikir Terhadap Penurunan Tingkat Kecemasan Pada Pasien di IGD," Jurnal Ners, vol. VIII, no. 02, pp. 1042 - 1048, 2024.

[9] D. M. Abdullah and A. M. Abdulazeez, "Machine Learning Applications based on SVM Classification: A Review," Qubahan Academic Journal , vol. I, no. 02, pp. 81-90, 2021, doi: https://doi.org/10.48161/qaj.v1n2a50.

[10] N. W. Utami and N. N. Saptiari, "Penerapan Data Mining Untuk Klasifikasi Penyebab Kematian Menggunakan Algoritma Support Vector Machine," Jurnal Ilmiah Ilmu Terapan Universitas Jambi, vol. IV, no. 02, pp. 234-240, 2020, doi: https://doi.org/10.22437/jiituj.v4i2.13268.

[11] M. Furqan, R. Kurniawan and K. I. HP, "Evaluasi Performa Support Vector Machine Classifier Terhadap Penyakit Mental," Jurnal Sistem Informasi Bisnis , vol. X, no. 02, pp. 203-210, 2020, doi: https://doi.org/10.21456/vol10iss2pp203-210.

[12] R. d. Filippis and A. A. Foysal, "Comprehensive analysis of stress factors afecting students: a machine learning approach," Discover Artifcial Intelligence, 2024, doi: https://doi.org/10.1007/s44163-024-00169-6.

[13] C. Chakraborty, M. Bhattacharya, S. Pal and S.-S. Lee, "From machine learning to deep learning: Advances of the recent data-driven paradigm shift in medicine and healthcare," Elsevier B.V, 2023, doi: https://doi.org/10.1016/j.crbiot.2023.100164.

[14] R. R. Pérez and J. Bajorath, "Evolution of Support Vector Machine and Regression Modeling in Chemoinformatics and Drug Discovery," Journal of Computer-Aided Molecular Design, p. 355–362, 2022, doi: https://doi.org/10.1007/s10822-022-00442-9.

[15] M. Yamamoto, E. Bagarinao, I. Kushima and e. a. , "Support vector machine-based classification of schizophrenia patients and healthy controls using structural magnetic resonance imaging from two independent sites," PLoS ONE, 2020, doi: https://doi.org/10.1371/journal.pone.0239615.

[16] S. Rabbani, D. Safitri, N. Rahmadhani and e. a. , "Comparative Evaluation of SVM Kernels for Sentiment lassification in Fuel Price Increase Analysis," MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. III, no. 2, pp. 153-160, 2023, doi: https://doi.org/10.57152/malcom.v3i2.897.

[17] R. Wardoyo, I. M. A. Wirawan and I. G. A. Pradipta, "Oversampling Approach Using Radius-SMOTE for Imbalance Electroencephalography Datasets," Emerging Science Journal, pp. 382-398, 2022, doi: https://doi.org/10.28991/ESJ-2022-06-02-013.

[18] H. Hairani, T. Widiyaningtyas and D. D. Prasetya, "Addressing Class Imbalance of Health Data: a Systematic Literature Review on Modified Synthetic Minority Oversampling Technique (SMOTE) Strategies," International Journal On Informatics Visualization, pp. 1310-1318, 2024, doi: https://dx.doi.org/10.62527/joiv.8.3.2283.

[19] R. Sujitha and B. Paramasivan, "Optimal progressive classification study using SMOTE-SVM for stages of lung disease," Automatika, pp. 807-814, 2023, doi: https://doi.org/10.1080/00051144.2023.2218167.

[20] S. Sreenivasa, "Radial Basis Function (RBF) Kernel: The Go-To Kernel," Towards Data Science, 12 October 2020, Available: https://towardsdatascience.com/.

[21] GeeksforGeeks (Tim Editorial), "Radial Basis Function Kernel – Machine Learning," GeeksforGeeks, 06 May 2024, Available: https://www.geeksforgeeks.org/.