Anomaly Detection of Hospital Claim Using Support Vector Regression
Luthfia Nurma Hapsari(1), Nur Rokhman(2*)
(1) Master Program of Computer Science, FMIPA UGM, Yogyakarta
(2) Department of Computer Science and Electronics, Universitas Gadjah Mada
(*) Corresponding Author
Abstract
BPJS Kesehatan plays a crucial role in providing affordable access to healthcare services and reducing individual financial burdens. However, deficit issues can disrupt the sustainability of the program, making anomaly detection highly important to conduct.
Previous research on unsupervised anomaly detection in BPJS Kesehatan revealed a limitation with Simple Linear Regression (SLR), which only accommodates linear relationships among independent variables and the target variable of BPJS Kesehatan claim values. Minister of Health Regulation No. 52 of 2016 identified eight influential non-linear independent variables, leading to the proposal of Support Vector Regression (SVR) to address SLR's shortcomings.
Research findings demonstrate SVR's superior anomaly detection performance over SLR. Interestingly, the SVR model excels in anomaly detection but lacks in prediction. Optimal tuning of SVR hyperparameters (C=9, epsilon=90, gamma=0.009, residual anomaly definition > 0.5*RMSE for both datasets) yields impressive metrics: Accuracy=0.97, Precision=0.84, Recall=0.97, and F1-Score=0.90. The anomaly detection results are expected to greatly support the sustainability of the BPJS Kesehatan program in Indonesia.
Keywords
Full Text:
PDFReferences
A. Ratnawati, W. bin Mislan Cokrohadisumarto, and N. Kholis, “Improving the satisfaction and loyalty of BPJS healthcare in Indonesia: a Sharia perspective,” Journal of Islamic Marketing, vol. 12, no. 7, pp. 1316–1338, 2020, doi: 10.1108/JIMA-01-2020-0005 [2] E. Afrina et al., “Defisit Jaminan Kesehatan Nasional (JKN): Mengapa dan Bagaimana Mengatasinya?,” 2020. [3] R. A. Fattah et al., “Incidence of catastrophic health spending in Indonesia: insights from a Household Panel Study 2018–2019,” Int J Equity Health, vol. 22, no. 1, Dec. 2023, doi: 10.1186/s12939-023-01980-w [4] N. Fathurrohman and A. Dewi, “Potential Fraud in The Primary Healthcare,” Jurnal Medicoeticolegal dan Manajemen Rumah Sakit, vol. 7, no. 3, 2018, doi: 10.18196/jmmr.7373 [5] H. K. Prakosa and N. Rokhman, “Anomaly Detection in Hospital Claims Using K-Means and Linear Regression,” IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 15, no. 4, p. 391, Oct. 2021, doi: 10.22146/ijccs.68160 [6] M. Meghana, S. Radhika, and V. S. Kumari, “Anomaly Detection for Vertical Plant Wall System using Novel Support Vector Machine in comparison with Linear Regression for improving accuracy,” Institute of Electrical and Electronics Engineers (IEEE), Jun. 2023, pp. 1–5. doi: 10.1109/iconstem56934.2023.10142459 [7] Q. Ai, S. Liu, L. He, and Z. Xu, “Stein Variational Gradient Descent with Multiple Kernel,” Jul. 2021, doi: 10.1007/s12559-022-10069-5. Available: http://arxiv.org/abs/2107.09338 [8] H. Lee, G. Li, A. Rai, and A. Chattopadhyay, “Real-time anomaly detection framework using a support vector regression for the safety monitoring of commercial aircraft,” Advanced Engineering Informatics, vol. 44, Apr. 2020, doi: 10.1016/j.aei.2020.101071 [9] T. Wang, X. Cao, Y. Li, Y. Zhai, and G. Ye, “Real-time anomaly data detection method based on mixed kernel function PSO-SVR,” AIP Adv, vol. 13, no. 6, Jun. 2023, doi: 10.1063/5.0140105 [10] I. Ivan, T. Roman, G. Michal, Z. Khrystyna, and L. Nataliia, “Input Doubling Method based on SVR with RBF kernel in Clinical Practice: Focus on Small Data.” Procedia Computer Science, 2021. doi: 10.1016/J.PROCS.2021.03.075 [11] K. Tscharke, S. Issel, and P. Debus, “Semisupervised Anomaly Detection using Support Vector Regression with Quantum Kernel,” Aug. 2023, doi: 10.1109/QCE57702.2023.00075. Available: http://arxiv.org/abs/2308.00583 [12] E. S. Fatahillah Pakpahan, T. Valentine, A. Arixson, and S. A. Batubara, “Analisis Hukum Terhadap Tindakan Pidana Penipuan yang Menyalahgunakan BPJS Kesehatan Berdasarkan KUHP,” Syntax Literate ; Jurnal Ilmiah Indonesia, vol. 6, no. 10, p. 4967, Oct. 2021, doi: 10.36418/syntax-literate.v6i10.4370 [13] S. Kurniawan, H. Sutra Disemadi, and A. Purwanti, “Urgensi Pencegahan Tindak Pidana Curang (Fraud) Dalam Klaim Asuransi Urgency of Fraud Prevention in Insurance Claims ARTICLE INFO ABSTRACT,” vol. 4, pp. 38–53, 2020, Available: http://ojs.uho.ac.id/index.php/holrev/ [14] M. P. Deisenroth, Mathematics for Machine Learning. Cambridge University Press, 2020. [15] L. Fahrmeir, T. Kneib, S. Lang, and B. D. Marx, “The Classical Linear Model,” in Regression, Berlin, Heidelberg: Springer Berlin Heidelberg, 2021, pp. 85–190. doi: 10.1007/978-3-662-63882-8_3 [16] M. Awad and R. Khanna, “Support Vector Regression,” in Efficient Learning Machines, Berkeley, CA: Apress, 2015, pp. 67–80. doi: 10.1007/978-1-4302-5990-9_4 [17] M. U. Ndubuaku, A. Anjum, and A. Liotta, “Unsupervised Anomaly Thresholding from Reconstruction Errors,” 2019, pp. 123–129. doi: 10.1007/978-3-030-34914-1_12 [18] M. A. Mondal and Z. Rehena, “Road Traffic Outlier Detection Technique based on Linear Regression,” in Procedia Computer Science, Elsevier B.V., 2020, pp. 2547–2555. doi: 10.1016/j.procs.2020.04.276 [19] H. B. Moss, D. S. Leslie, and P. Rayson, “Using J-K fold Cross Validation to Reduce Variance When Tuning NLP Models,” Jun. 2018, Available: http://arxiv.org/abs/1806.07139 [20] L. Deecke, L. Ruff, R. A. Vandermeulen, and H. Bilen, “Deep Anomaly Detection by Residual Adaptation,” Oct. 2020, Available: http://arxiv.org/abs/2010.02310
DOI: https://doi.org/10.22146/ijccs.91857
Article Metrics
Abstract views : 1843 | views : 1240Refbacks
- There are currently no refbacks.
Copyright (c) 2024 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
View My Stats1