Clustering Data Penyakit Jantung Menggunakan K-MEANS dalam Sistem Informasi Kesehatan
DOI:
https://doi.org/10.35473/jamastika.v5i1.4670Abstract
Pada kesempatan ini penelitian bertujuan untuk mengklasifikasikan data penyakit kardiovaskular menggunakan algoritma k-means dan mengintegrasikan hasilnya ke dalam sistem informasi kesehatan. Salah satu tantangan terbesar dalam pelayanan kesehatan adalah meningkatnya jumlah data pasien yang tidak dimanfaatkan secara optimal untuk analisis risiko. Setelah pra-pemrosesan, data dibersihkan dan dinormalisasi untuk klasifikasi. Jumlah kelompok ideal ditentukan menggunakan metode k-means, dan tiga kelompok risiko utama – rendah, sedang, dan tinggi – diidentifikasi. Klasifikasi ini mengungkapkan bahwa setiap kelompok memiliki karakteristik klinis spesifik seperti tekanan darah, kadar kolesterol, detak jantung, dan faktor risiko lainnya. Hasil klasifikasi diintegrasikan ke dalam sistem informasi kesehatan untuk menyediakan representasi visual bagi tenaga kesehatan untuk analisis risiko pasien. Studi ini menunjukkan efektivitas k-means dalam mengidentifikasi kelompok risiko penyakit kardiovaskular dan potensinya sebagai alat pendukung keputusan dalam sistem informasi kesehatan. Lebih lanjut, hasil ini membuka arah penelitian baru, seperti membandingkan berbagai metode klasifikasi dan mengembangkan sistem peringatan dini berbasis penambangan data.
Kata kunci : klasifikasi, k-means, penyakit kardiovaskular, penambangan data, sistem informasi Kesehatan
The goal of this research is to use the k-means algorithm to categorize cardiovascular disease data and incorporate the findings into a health information system. The growing volume of patient data that is not being used to its full potential for risk analysis is one of the largest issues facing the healthcare industry. The data was cleaned and normalized for categorization after preprocessing. The k-means approach was used to estimate the optimal number of clusters, and three primary risk groups—low, medium, and high—were identified. This classification revealed that each cluster has specific clinical characteristics such as blood pressure, cholesterol levels, heart rate, and other risk factors. The classification results were integrated into a health information system to provide healthcare professionals with a visual representation for patient risk analysis. This study demonstrates the effectiveness of k-means in identifying cardiovascular disease Risk clusters and their potential as a tool for decision-making in health information systems. Furthermore, these results open new research directions, such as comparing various classification methods and developing data mining-based early warning systems.
Keywords: classification, k-means, cardiovascular disease, data mining, health information system
References
Aulia, W., Siahaan, A. P. U., Marlina, L., Khairul, & Iqbal, M. (2024). K-Means Clustering Algorithm Analysis for Grouping Patient Medical Record Data Based on Disease Type. Jurnal Info Sains: Informatika Dan Sains, 14(04), 832–843. https://doi.org/10.54209/infosains.v14i04
Ayaz, M., Pasha, M. F., Le, T. Y., Alahmadi, T. J., Abdullah, N. N. B., & Alhababi, Z. A. (2023). A Framework for Automatic Clustering of EHR Messages Using a Spatial Clustering Approach. Healthcare (Switzerland), 11(3). https://doi.org/10.3390/healthcare11030390
Azil, A. A., Yusof, Z. Y. M., & Marhazlinda, J. (2023). Clustering of Health and Oral Health-Compromising Behaviours in Army Personnel in Central Peninsular Malaysia. Healthcare (Switzerland), 11(5), 1–17. https://doi.org/10.3390/healthcare11050640
D, C., Ranganathan, Vi. A., Shailesh, T., J, A., N, A., & T, P. P. (2025). Deep learning based hybrid residual attention and echo state network for high-accuracy heart disease prediction. F1000Research, 14, 650. https://doi.org/10.12688/f1000research.165575.2
Ekemeyong Awong, L. E., & Zielinska, T. (2023). Comparative Analysis of the Clustering Quality in Self-Organizing Maps for Human Posture Classification. Sensors, 23(18). https://doi.org/10.3390/s23187925
Farahnakian, F., Nicolas, F., Farahnakian, F., Nevalainen, P., Sheikh, J., Heikkonen, J., & Raduly-Baka, C. (2023). A Comprehensive Study of Clustering-Based Techniques for Detecting Abnormal Vessel Behavior. Remote Sensing, 15(6), 1–34. https://doi.org/10.3390/rs15061477
Haryanto, H., Winarto, H., & Juliane, C. (2024). Application of Data Mining Techniques in Healthcare: Identifying Inter-Disease Relationships through Association Rule Mining. Journal of World Science, 3(5), 520–529. https://doi.org/10.58344/jws.v3i5.597
Hassan, J., Saeed, S. M., Deka, L., Uddin, M. J., & Das, D. B. (2024). Applications of Machine Learning (ML) and Mathematical Modeling (MM) in Healthcare with Special Focus on Cancer Prognosis and Anticancer Therapy: Current Status and Challenges. Pharmaceutics, 16(2). https://doi.org/10.3390/pharmaceutics16020260
Huang, J. (2024). Heart Disease Prediction Based on the Random Forest Algorithm. Daml 2023, 511–516. https://doi.org/10.5220/0012798700003885
Mohamed, W., Rezk, M. R. A., Soliman, A., Piccinetti, L., & Sakr, M. M. (2024). Publisher Sustainability for Regions. 6(3), 85–97.
Nur, I. M. (2024). Application of the K-Means ++ Method for Grouping Health Services Based on Districts in West Java Province. Eksakta: Journal of Sciences And Data Analysis, 5(1), 96–102. https://journal.uii.ac.id/Eksakta/article/view/31930
Osman, A. H., Ibrahim, A. O., Alsadoon, A., Alzahrani, A. A., Barukub, O. M., Abulfaraj, A. W., & Alharbi, N. M. (2024). Breaking new ground in cardiovascular heart disease Diagnosis K-RFC: An integrated learning approach with K-means clustering and Random Forest classifier. In AIMS Mathematics (Vol. 9, Issue 4, pp. 8262–8291). https://doi.org/10.3934/math.2024402
Udhan, S., & Patil, B. (2021). A systematic review of Machine learning techniques for Heart disease prediction. International Journal of Next-Generation Computing, 186(63), 229–239. https://doi.org/10.55730/1300-0152.2766
Wala, J., Herman, H., & Umar, R. (2024). Implementasi K-Means Clustering pada Pengelompokan Pasien Penyakit Jantung. JISKA (Jurnal Informatika Sunan Kalijaga), 9(3), 205–216. https://doi.org/10.14421/jiska.2024.9.3.205-216
Wala, J., Herman, H., Umar, R., & Suwanti, S. (2024). Heart Disease Clustering Modeling Using a Combination of the K-Means Clustering Algorithm and the Elbow Method. Scientific Journal of Informatics, 11(4), 903–914. https://doi.org/10.15294/sji.v11i4.14096
