Pendekatan Machine Learning untuk Menganalisis Faktor-Faktor yang Berkontribusi Terhadap Kesalahan Pengkodean ICD-10 di Semen Padang Hospital
DOI:
https://doi.org/10.25047/j-remi.v7i3.6775Keywords:
ICD-10 Coding, Machine Learning, Electronic Medical Record, Neural Network, Coding AccuracyAbstract
ICD-10 coding errors remain a major challenge in healthcare facilities, affecting the validity of morbidity data, the accuracy of BPJS Kesehatan claims processing, and the quality of health information management. This study aimed to identify the main factors contributing to ICD-10 coding errors and evaluate the effectiveness of machine learning algorithms in detecting such errors. Electronic medical record data were analyzed through data cleaning, preprocessing, descriptive analysis, and machine learning modeling. Three algorithms were applied: Random Forest, Support Vector Machine (SVM), and Neural Network. Model performance was evaluated using accuracy, precision, and sensitivity metrics. The findings revealed an ICD-10 coding error rate of 33.8%, primarily caused by nonspecific diagnoses and insufficient clinical information. Among the tested models, the Neural Network achieved the highest accuracy (72%), followed by SVM (68%) and Random Forest (60%). These results suggest that machine learning techniques can effectively support the early detection of ICD-10 coding errors and enhance the quality of health data management. The adoption of machine learning–based predictive models may improve coding accuracy and facilitate evidence-based decision-making in health information management.
References
[1] E. Nurmambetova et al., “Developing an Inpatient Electronic Medical Record Phenotype for Hospital-Acquired Pressure Injuries: Case Study Using Natural Language Processing Models,” JMIR AI, vol. 2, pp. 1–15, Mar. 2023, doi: 10.2196/41264.
[2] I. Kartika and A. Sukawan, “Akurasi Pengodean Injury dan External Causes Berdasarkan ICD-10 dan ICD-9 CM di Rumah Sakit Jasa Kartini,” J. Manaj. Inf. Kesehat. Indones., vol. 13, no. 2, pp. 206–211, 2025, doi: https://doi.org/10.33560/jmiki.v13i2.676.
[3] R. Andriani, “Akurasi Kode ICD-10 Kasus Pemeriksaan Kehamilan Pada Rekam Medis Elektronik,” JMIAK J. Manaj. Inf. dan Adm. Kesehat., vol. 4, no. 2, pp. 59–68, 2021, doi: https://doi.org/10.32585/jmiak.v4i2.2015.
[4] E. S. D. Hastuti and M. Ali, “Faktor-faktor yang Berpengaruh pada Akurasi Kode diagnosis di Puskesmas Rawat Jalan Kota Malang,” J. Kedokt. Brawijaya, vol. 30, no. 3, pp. 228–234, Feb. 2019, doi: 10.21776/ub.jkb.2019.030.03.12.
[5] D. Ekawati, A. A. Nuryadin, S. Windarti, and A. Zulfikar, “Peran Coder Terkait Keakuratan Pengkodean ICD-10 Pada Pelaksanaan Sistem INA-CBG’s Rumah Sakit TK. II 14.05.01 Pelamonia Makassar,” J. Manaj. Bisnis dan Kesehat., vol. 1, no. 2, Oct. 2024, doi: 10.70817/jmbk.v1i2.13.
[6] M. O. D. Putri and E. Krisnawati, “Literature Review Analisis Faktor yang Mempengaruhi Ketepatan Pemberian Kodefikasi Penyakit,” J. Manaj. Inf. Kesehat., vol. 1, no. 1, pp. 8–16, Jan. 2026, doi: 10.36916/j-mika.v1i1.382.
[7] X. Diao et al., “Automated ICD coding for primary diagnosis via clinically interpretable machine learning,” Int. J. Med. Inform., vol. 153, pp. 1–9, Sep. 2021, doi: 10.1016/j.ijmedinf.2021.104543.
[8] S.-M. Wang et al., “Using Deep Learning for Automatic Icd-10 Classification from Free Text Data,” Eur. J. Biomed. Informatics, vol. 16, pp. 1–10, 2020, doi: 10.24105/ejbi.2020.16.1.1.
[9] M. Almagro, R. Martínez, S. Montalvo, and V. Fresno, “A cross-lingual approach to automatic ICD-10 coding of death certificates by exploring machine translation,” J. Biomed. Inform., vol. 94, pp. 1–7, Jun. 2019, doi: 10.1016/j.jbi.2019.103207.
[10] C. Sen, B. Ye, J. Aslam, and A. Tahmasebi, “From Extreme Multi-label to Multi-class: A Hierarchical Approach for Automated ICD-10 Coding Using Phrase-level Attention,” arXiv Prepr. arXiv2102.09136, pp. 1–9, 2021, doi: https://doi.org/10.48550/arXiv.2102.09136.
[11] L. Zhou, C. Cheng, D. Ou, and H. Huang, “Construction of a semi-automatic ICD-10 coding system,” BMC Med. Inform. Decis. Mak., vol. 20, no. 1, pp. 1–12, Dec. 2020, doi: 10.1186/s12911-020-1085-4.
[12] B. Volkov and G. Kopanitsa, “Development of a Method for Automatic Matching of Unstructured Medical Data to ICD-10 Codes,” in Proceeding of the International Conference on Wearable Micro and Nano Technologies for Personalized Health, May 2024, pp. 93–97. doi: 10.3233/SHTI240065.
[13] Y. Kim, C. Li, B. Ye, A. Tahmasebi, and J. Aslam, “Supervised Learning in the Presence of Noise: Application in ICD-10 Code Classification,” arXiv Prepr. arXiv2103.07808, pp. 1–9, 2021.
[14] E. Cardillo and L. Frattura, “Assisted morbidity coding: the SISCO.web use case for identifying the main diagnosis in Hospital Discharge Records,” arXiv Prepr. arXiv2412.09651, pp. 51–78, 2024, doi: https://doi.org/10.48550/arXiv.2412.09651.
[15] S. Bowman, “Impact of Electronic Health Record Systems on Information Integrity: Quality and Safety Implications,” Perspect. Heal. Inf. Manag., vol. 10, no. 1c, pp. 1–19, 2013.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rury Moryanda, Nurul Abdillah, Denos Imam Fratama, Dicky Fatrias
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
