Clustering of Myopia Patients Based on Severity Level, Geographic Area, Age, and Gender Using the K-Means Algorithm: A Case Study of Indra Optik Blitar
DOI:
https://doi.org/10.32664/j-intech.v14i03.2455Kata Kunci:
Feature Weighting, Knowledge Discovery In Database, K-Means Clustering, Myopia, OPtuna, Patient SegmentationAbstrak
Indra Optik Blitar manages a large volume of patient medical record data that has not yet been utilized to support strategic decision-making. This study aims to cluster myopia refractive error patients based on their severity level, region, age, and gender characteristics using the K-Means algorithm, and to evaluate the quality of the resulting clusters using the Silhouette Coefficient. The research process follows the Knowledge Discovery in Database (KDD) framework, encompassing data selection, preprocessing, feature engineering, Min-Max Scaling normalization, and clustering execution. From 14,863 raw data entries, 6,821 valid records were obtained after three filtering layers: demographic, geographic, and clinical. Feature engineering was performed by converting four raw refraction variables into a single Worst_SE (Worst Spherical Equivalent) variable and transforming district address data into latitude and longitude coordinates. Feature weighting was automatically optimized using the Optuna framework with the Tree-structured Parzen Estimator (TPE) algorithm through 100 optimization trials. The optimal number of clusters was determined using a combination of the Elbow Method and Silhouette Coefficient, resulting in K = 5. The K-Means algorithm with K-Means++ initialization achieved convergence at iteration 20, producing five clusters with distinctive characteristics. Evaluation using the Silhouette Coefficient yielded an average score of 0.4144, which, given the high dimensionality and heterogeneity of the combined clinical, demographic, and geographic features, represents a moderately well-separated cluster structure suitable for practical application. The five clusters formed represent patient segments that differ clinically, demographically, and geographically, providing a data-driven foundation for Indra Optik Blitar to design more targeted marketing strategies, eye health socialization programs, and social assistance initiatives.
Referensi
[1] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques. 2011.
[2] B. A. Holden et al., “Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050,” Ophthalmology, 2016, doi: 10.1016/j.ophtha.2016.01.006.
[3] B. P. S. K. Blitar, Indikator Kesejahteraan Rakyat Kota Blitar 2022. 2022. [Online]. Available: https://blitarkota.bps.go.id/id/publication/2022/12/28/ace8c12becce9e280e0a2a82/welfare-indicators-in-blitar-municipality-2022.html
[4] Dinas Komunikasi Informatika Statistik dan Persandian Kabupaten Blitar, “Jumlah penduduk.”
[5] I. Kamila, U. Khairunnisa, and Mustakim, “Perbandingan algoritma K-Means dan K-Medoids untuk pengelompokan,” J. Ilmiah Rekayasa dan Manajemen Sistem Informasi, 2019, doi: 10.24014/rmsi.v5i1.7381.
[6] A. Ali, “Klasterisasi data rekam medis pasien menggunakan metode K-Means clustering di Rumah Sakit Anwar Medika Balong Bendo Sidoarjo,” MATRIK: J. Manajemen, Tek. Inform. dan Rekayasa Komputer, 2019, doi: 10.30812/matrik.v19i1.529.
[7] M. Rizki and M. Mulyawan, “Penerapan metode K-Means clustering pada data penjualan Optik Chantika,” JATI (J. Mahasiswa Tek. Inform.), 2023, doi: 10.36040/jati.v7i2.6562.
[8] R. C. de Amorim, “A survey on feature weighting based K-Means algorithms,” J. Classif., 2016, doi: 10.1007/s00357-016-9208-4.
[9] M. O. Armandari, N. S. S. Ambarwati, and N. Hidayah, “Analisis kebutuhan bahan ajar dalam pembelajaran metode penelitian terapan di program studi kosmetik dan perawatan kecantikan,” Academy of Education Journal, 2024, doi: 10.47200/aoej.v15i2.2493.
[10] S. Setyaningtyas, B. I. Nugroho, and Z. Arif, “Tinjauan pustaka sistematis pada data mining: Studi kasus algoritma K-Means clustering,” J. Teknoif Tek. Inform. Institut Teknologi Padang, 2022, doi: 10.21063/jtif.2022.V10.2.52-61.
[11] D. I. Flitcroft et al., “IMI - Defining and Classifying Myopia: A Proposed Set of Standards for Clinical and Epidemiologic Studies,” Invest. Ophthalmol. Vis. Sci., 2019, doi: 10.1167/iovs.18-25957.
[12] A. Hashemi, M. Khabazkhoob, and H. Hashemi, “High prevalence of refractive errors in an elderly population; a public health issue,” BMC Ophthalmol., 2023, doi: 10.1186/s12886-023-02791-x.
[13] T. Lestari, Anggunan, T. Triwahyuni, and R. Syuhada, “Studi Faktor Risiko Kelainan Miopia Di Rumah Sakit Pertamina Bintang Amin,” Jurnal Ilmiah Kesehatan Sandi Husada, 2020, doi: 10.35816/jiskh.v11i1.275.
[14] P. Oktarima, S. Caesarya, I. Irfani, M. W. Kuntorini, F. K. Memed, and D. V Ginting, “Hubungan usia dan jenis kelamin dengan jenis kelainan refraksi pada anak di Pusat Mata Nasional Rumah Sakit Mata Cicendo,” Oftalmologi: J. Kesehatan Mata Indonesia, 2021, doi: 10.11594/ojkmi.v3i2.15.
[15] V. Galvis, A. Tello, P. A. Camacho, L. M. Gómez, J. J. Rey, and A. A. Serrano, “Definition of refractive errors for research studies: Spherical equivalent could not be enough,” J. Optometry, 2021, doi: 10.1016/j.optom.2020.10.003.
[16] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A next-generation hyperparameter optimization framework,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2019. doi: 10.1145/3292500.3330701.
[17] P. J. Rousseeuw, “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis,” J. Comput. Appl. Math., 1987, doi: 10.1016/0377-0427(87)90125-7.
[18] D. A. Jethva, S. M. Khamkar, A. A. Pachchhapur, and S. Kulkarni, “Customer segmentation analysis using K-means algorithm with Elbow method and Dendrogram,” in Proceedings of the 2023 6th International Conference on Advances in Science and Technology (ICAST), 2023. doi: 10.1109/ICAST59062.2023.10454952.
[19] M. S. Rahman, T. D. Sarkar, and M. Y. Emon, “Comprehensive geospatial and statistical analysis of restaurant distribution using K-means clustering in machine learning technology,” in Proceedings of the 2024 4th International Conference Advancement in Electronics and Communication Engineering (AECE), 2024. doi: 10.1109/AECE62803.2024.10911593.
[20] M. I. Mashur and Y. Salim, “Analisis performa metode cluster K-Means pada dataset Ocular Disease Recognition,” Indonesian J. Data and Science, 2022, doi: 10.56705/ijodas.v3i1.47.
[21] N. P. Sutramiani, I. M. T. Arthana, P. F. Lampung, S. Aurelia, M. Fauzi, and I. W. A. S. Darma, “The performance comparison of DBSCAN and K-Means clustering for MSMEs grouping based on asset value and turnover,” J. Information Systems Engineering and Business Intelligence, 2024, doi: 10.20473/jisebi.10.1.13-24.
[22] Suharmanto, W. S. Utami, N. Pratiwi, and F. Muhammad, “Penerapan data mining menggunakan algoritma K-Means untuk clustering perokok usia lebih dari 15 tahun,” Bulletin of Information Technology (BIT), 2023, doi: 10.47065/bit.v4i4.1067.
[23] Y. R. N. Manobi, A. De Kweldju, and J. P. P. Naibaho, “Clustering HIV Screening Data in Teluk Bintuni Using K-Means,” J-INTECH, 2026, doi: 10.32664/j-intech.v14i02.2368.
[24] D. Wijayanto, R. Marco, A. Sidauruk, and M. Sulistiyono, “The effect of SMOTE and Optuna hyperparameter optimization on TabNet performance for heart disease classification,” J. Sisfokom (Sistem Informasi dan Komputer), 2025, doi: 10.32736/sisfokom.v14i2.2348.
[25] C. Shi, B. Wei, S. Wei, W. Wang, H. Liu, and J. Liu, “A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm,” EURASIP J. Wirel. Commun. Netw., 2021, doi: 10.1186/s13638-021-01910-w.
[26] P. Vania and B. N. Sari, “Perbandingan metode Elbow dan Silhouette untuk penentuan jumlah klaster yang optimal pada clustering produksi padi menggunakan algoritma K-Means,” J. Ilmiah Wahana Pendidikan, 2023, doi: 10.5281/zenodo.10081332.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 J-INTECH ( Journal of Information and Technology)
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
