PERBANDINGAN KINERJA SUPPORT VECTOR MACHINE, RANDOM FOREST, DAN LOGISTIC REGRESSION DALAM PREDIKSI KANKER PAYUDARA
DOI:
https://doi.org/10.54314/vkkzc687Keywords:
kanker payudara, machine learning, support vector machine, random forest, logistic regressionAbstract
Abstract: Breast cancer is one of the most common cancers among women, making early detection essential for improving treatment outcomes. Machine learning can support breast cancer classification by identifying patterns in medical data. This study compares Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR) to identify the model with the best performance and stability. The study used a breast cancer dataset comprising 569 samples and 30 numerical features. The research process included data preprocessing, removal of irrelevant attributes, feature transformation and standardization, class imbalance handling using the Synthetic Minority Over-sampling Technique (SMOTE), feature selection using SelectKBest with an ANOVA F-test, and hyperparameter optimization. Model performance was evaluated using accuracy, precision, recall, F1-score, ROC-AUC, and cross-validation. Test results showed that SVM and LR achieved 98.25% accuracy, 97.62% precision, 97.62% recall, and a 97.62% F1-score. SVM achieved the highest ROC-AUC at 99.74%, followed by LR at 99.70%. RF obtained 95.61% accuracy and 90.48% recall. LR demonstrated the best cross-validation stability. Therefore, LR offers a balanced candidate for a decision support system prototype, while SVM provides superior discrimination on test data. External validation is required before clinical application.
Keyword: Breast Cancer; Machine Learning; Support Vector Machine; Random Forest; Logistic Regression.
Abstrak: Kanker payudara merupakan salah satu jenis kanker yang paling umum di kalangan wanita, sehingga deteksi dini sangat penting untuk meningkatkan hasil pengobatan. Pembelajaran mesin dapat mendukung klasifikasi kanker payudara dengan mengidentifikasi pola dalam data medis. Penelitian ini membandingkan Support Vector Machine (SVM), Random Forest (RF), dan Regresi Logistik (LR) untuk mengidentifikasi model dengan kinerja dan stabilitas terbaik. Penelitian ini menggunakan dataset kanker payudara yang terdiri dari 569 sampel dan 30 fitur numerik. Proses penelitian meliputi prapemrosesan data, penghapusan atribut yang tidak relevan, transformasi dan standarisasi fitur, penanganan ketidakseimbangan kelas menggunakan Teknik Synthetic Minority Over-sampling (SMOTE), seleksi fitur menggunakan SelectKBest dengan uji F ANOVA, serta optimisasi hiperparameter. Kinerja model dievaluasi menggunakan akurasi, presisi, recall, skor F1, AUC kurva ROC, dan validasi silang. Hasil pengujian menunjukkan bahwa SVM dan LR mencapai akurasi 98,25%, presisi 97,62%, recall 97,62%, dan skor F1 sebesar 97,62%. SVM mencapai nilai ROC-AUC tertinggi sebesar 99,74%, diikuti oleh LR sebesar 99,70%. RF memperoleh akurasi sebesar 95,61% dan recall sebesar 90,48%. LR menunjukkan stabilitas validasi silang terbaik. Oleh karena itu, LR menawarkan kandidat yang seimbang untuk prototipe sistem pendukung keputusan, sementara SVM memberikan kemampuan diskriminasi yang lebih unggul pada data uji. Validasi eksternal diperlukan sebelum penerapan klinis.
Kata kunci: Kanker Payudara; Machine Learning; Support Vector Machine; Random
Forest; Logistic Regression.
Downloads
References
Arnold M, Morgan E, Rumgay H, Mafra A, Singh D, Laversanne M, et al. Current and future burden of breast cancer: Global statistics for 2020 and 2040. The Breast. 2022;66:15–23. doi: 10.1016/j.breast.2022.08.010. https://doi.org/10.1016/j.breast.2022.08.010
Momenimovahed Z, Salehiniya H. Epidemiological characteristics of and risk factors for breast cancer in the world. Breast Cancer (Dove Med Press). 2019;11:151–64. doi: 10.2147/BCTT.S176070. https://doi.org/10.2147/BCTT.S176070
Patrício M, Pereira J, Crisóstomo J, Matafome P, Gomes M, Seiça R, et al. Using Resistin, glucose, age and BMI to predict the presence of breast cancer. BMC Cancer. 2018;18:29. doi: 10.1186/s12885-017-3877-1. https://doi.org/10.1186/s12885-017-3877-1
Ed-daoudy A, Maalmi K. Breast cancer classification with reduced feature set using association rules and support vector machine. Netw Model Anal Health Inform Bioinforma. 2020;9:34. doi: 10.1007/s13721-020-00237-8. https://doi.org/10.1007/s13721-020-00237-8
Vaka AR, Soni B, Reddy SK. Breast cancer detection by leveraging machine learning. ICT Express. 2020;6(4):320–4. doi: 10.1016/j.icte.2020.04.009. https://doi.org/10.1016/j.icte.2020.04.009
Shanbehzadeh M, Kazemi-Arpanahi H, Bolbolian Ghalibaf M, Orooji A. Performance evaluation of machine learning for breast cancer diagnosis: A case study. Informatics in Medicine Unlocked. 2022;31:101009. doi: 10.1016/j.imu.2022.101009. https://doi.org/10.1016/j.imu.2022.101009
Rashed AEE, Elmorsy AM, Atwa AEM. Comparative evaluation of automated machine learning techniques for breast cancer diagnosis. Biomed Signal Process Control. 2023;86:105016. doi: 10.1016/j.bspc.2023.105016. https://doi.org/10.1016/j.bspc.2023.105016
Naji MA, El Filali S, Aarika K, Benlahmar EH, Abdelouhahid RA, Debauche O. Machine learning algorithms for breast cancer prediction and diagnosis. Procedia Comput Sci. 2021;191:487–92. doi: 10.1016/j.procs.2021.07.062. https://doi.org/10.1016/j.procs.2021.07.062
Arooj S, Atta-ur-Rahman, Zubair M, Khan MF, Alissa K, Khan MA, et al. Breast cancer detection and classification empowered with transfer learning. Front Public Health. 2022;10:924432. doi: 10.3389/fpubh.2022.924432. https://doi.org/10.3389/fpubh.2022.924432
Cervantes J, Garcia-Lamont F, Rodríguez-Mazahua L, Lopez A. A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing. 2020;408:189–215. doi: 10.1016/j.neucom.2019.10.118. https://doi.org/10.1016/j.neucom.2019.10.118
Asri H, Mousannif H, Al Moatassime H, Noel T. Using machine learning algorithms for breast cancer risk prediction and diagnosis. Procedia Comput Sci. 2016;83:1064–9. doi: 10.1016/j.procs.2016.04.224. https://doi.org/10.1016/j.procs.2016.04.224
Andriansyah D, Fridayanthie EW. Optimization of Support Vector Machine and XGBoost methods using feature selection to improve classification performance. J Inform Telecommun Eng. 2023;6(2). doi: 10.31289/jite.v6i2.8373. https://doi.org/10.31289/jite.v6i2.8373
Azis AIS, Idris ISK, Santoso B, Mustofa YA. Pendekatan machine learning yang efisien untuk prediksi kanker payudara. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi). 2019;3(3):458–69. doi: 10.29207/resti.v3i3.1347. https://doi.org/10.29207/resti.v3i3.1347
Chairunisa R, Adiwijaya K, Astuti W. Perbandingan CART dan Random Forest untuk deteksi kanker berbasis klasifikasi data microarray. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi). 2020;4(5):805–12. doi: 10.29207/resti.v4i5.2083. https://doi.org/10.29207/resti.v4i5.2083
Resmiati R, Arifin T. Klasifikasi pasien kanker payudara menggunakan metode Support Vector Machine dengan Backward Elimination. Sistemasi. 2021;10(2):381. doi:10.32520/stmsi.v10i2.1238. https://doi.org/10.32520/stmsi.v10i2.1238
Kusuma J, Hayadi BH, Wanayumini W, Rosnelly R. Komparasi metode Multi Layer Perceptron (MLP) dan Support Vector Machine (SVM) untuk klasifikasi kanker payudara. MIND Journal. 2022;7(1):51–60. doi: 10.26760/mindjournal.v7i1.51-60. https://doi.org/10.26760/mindjournal.v7i1.51-60
Rahmayani OS, Permana RH, Witdiawati W. Early detection of breast cancer according to fertile age women. Media Keperawatan Indonesia. 2020;3(1):32–7. doi: 10.26714/mki.3.1.2020.32-37. https://doi.org/10.26714/mki.3.1.2020.32-37
Bharat A, Pooja N, Reddy RA. Using machine learning algorithms for breast cancer risk prediction and diagnosis. In: 2018 IEEE Third International Conference on Circuits, Control, Communication and Computing (I4C). 2018. doi: 10.1109/CIMCA.2018.8739696. https://doi.org/10.1109/CIMCA.2018.8739696
Simatupang S, Ramadhansyah R., Tumanggor R., Tan ER., Fajar SA. Prediction of Heart Disease Risk Based on Patient Health History Using the Support Vector Machine (SVM) Algorithm. Zero : Jurnal Sains, Matematika, dan Terapan. http://jurnal.uinsu.ac.id/index.php/zero/article/view/26087
Rustianna Tumanggor, Theresia Anggriani H, Elshadddai Tabitha Siadari, Dita Togatorop, Dina Eudia Meha. Pelatihan Sadari Dan Pemeriksaan IVA Sebagai Upaya Deteksi Dini Kanker Di Wilayah Perdesaan: Studi Kasus Di Desa Tanjung Anom. Sevaka [Internet]. 2025 Aug. 4 [cited 2025 Dec. 29];3(3):1-10. https://journal.stikescolumbiasiamdn.ac.id/index.php/Sevaka/article/view/472
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rustianna Tumanggor, Septian Simatupang, Dior Manta Tambunan (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
