Deteksi Faktor Risiko Polycystic Ovarian Syndrome (PCOS) pada Wanita Menggunakan Algoritma Support Vector Machine
Abstrak
Polycystic Ovarian Syndrome (PCOS) merupakan gangguan hormonal yang umum terjadi pada perempuan usia produktif dan sering kali tidak terdiagnosis secara dini karena keterbatasan waktu dan biaya pemeriksaan laboratorium. Penelitian ini bertujuan untuk mendeteksi faktor risiko PCOS serta mengklasifikasikan pasien PCOS dan Non-PCOS menggunakan algoritma Support Vector Machine (SVM) dengan kernel Radial Basis Function (RBF). Dataset yang digunakan berasal dari sumber terbuka Kaggle dan terdiri dari 1000 data pasien dengan beberapa atribut klinis dan fisik. Tahapan penelitian meliputi preprocessing data, penanganan ketidakseimbangan kelas menggunakan Synthetic Minority Over-sampling Technique (SMOTE), optimasi hyperparameter menggunakan GridSearchCV, serta evaluasi kinerja model menggunakan metrik akurasi, presisi, recall, dan F1-Score. Hasil penelitian menunjukkan bahwa model SVM dengan kernel RBF mampu mengklasifikasikan pasien PCOS dan Non-PCOS dengan tingkat akurasi sebesar 97%. Selain itu, penelitian ini mengidentifikasi tiga faktor risiko yang paling berpengaruh terhadap PCOS, yaitu ketidakteraturan siklus menstruasi, Body Mass Index (BMI), dan kadar hormon testosteron. Dengan demikian, model yang diusulkan berpotensi menjadi sistem pendukung keputusan medis untuk deteksi dini PCOS secara lebih cepat dan efisien.
Kata kunci: pcos, support vector machine, kernel rbf, deteksi faktor risiko, klasifikasi pcos
Referensi
Kodipalli, Ashwini., and Devi, Susheela, “Prediction of PCOS and Mental Health Using Fuzzy Inference and SVM,” Frontiers in Publich Health., Vol. 9, November, 2021
(2025, 7 February), “Polycystic Ovary Syndrome”, WHO, [Online]. Available: https://www.who.int/news-room/factsheets/detail/polycystic-ovary-syndrome [Accessed: 5 November 2025]
Yamin, B., Kaneti, Venkata Ramana., P, Prema., C, Ambhika., Nalini, M., and R, Siva Subramanian, “Machine Learning-Driven PCOS Prediction for Early Detection and Tailored Interventions,” SSRG International JournalI of Electrical and Electronics Engineering, vol. 10(9) pp 61-75. September 2023
Nsugbe, Ejay, “An artificial intelligence-based decision support system for early diagnosis of polycystic ovaries syndrome,” Healthcare Analytics, vol.3 pp 2772-4425. Mar. 2023
Arifin, Zainul., Rahman, Dimas Fachri., Rintyarna, Bagus Setya., and Daryanto, “Penerapan Algoritma Support Vector Machine Berbasis Kernel Radial Function dalam Klasifikasi Sel Kanker,” BIOS : Jurnal Teknologi Informasi dan Rekayasa Komputer. vol. 4 no.2 pp. 100-106. Sept. 2023
(2024, 14 Oktober). “Memahami PCOS: Gejala, Penyebab, dan Perawatan yang Efektif”, MorulaIVF, [Online],Available: https://www.morulaivf.co.id/id/blog/pcosadalah/#:~:text=Memahami%20PCOS:%20Gejala%2C%20Penyebab%2C%20dan%20Perawatan%20yang%20Efektif&text=Artikel%20ini%20telah%20direview%20secara,%2C%20diabetes%2C%20dan%20%5B%E2%80%A6%5D&text=Ardianto%20Airlangga%2C%20SpOG,Polycystic%20Ovary%20Syndrome%20(PCOS)%20adalah%20gangguan%20hormonal%20yang%20umum%20terjadi,%2C%20diabetes%2C%2 0dan%20penyakit%20jantung , [Accessed: 5 November 2025]
(2025, 13 November), “Support Vector Machine (SVM) Algorithm,” Geeksforgeeks, [Online], Available: https://www.geeksforgeeks.org/machine-learning/support-vector-machine-algorithm/ , [Accessed: 8 November 2025]
Tiwari, Shamik., Kane, Lalit., Koundal, Deepika., Jain, Anurag., Alhudhaif, Adi., Polat, Kemal., Zaguia, Atef., Alenezi, Fayadh., and Althubiti, Sara A, “SPOSDS: A smart Polycystic Ovary Syndrome diagnostic system using machine learning,” Expert Systems With Applications. vol. 203, May, 2022
Priani, Wina., Sulistianingsih, Evy., and Imro’ah, Nurfitri, “Implementasi Teknik Oversampling SMOTE-NC Pada Algoritma K- Nearest Neighbor,” Buletin Ilmiah Math. Stat. dan Terapannya (Bimaster). vol. 14 no. 3. pp 272-281, 2025
Rina, (2023, 11 Juni), “Memahami Confussion Matrix: Accuracy, Precision, Recall, Specificity, dan F1-Score untuk Evaluasi Model Klasifikasi.” [Online], Available: https://esairina.medium.com/memahami-confusion-matrix-accuracy-precision-recall-specificity-dan-f1-score-610d4f0db7cf , [Accessed: 8 November 2025]
Akanbi, Kemi., Adepoju, Odunayo Gabriel., and Nti, Kofi Isaac. “Developing A System for Automatic Prediction of Polycystic Ovary Syndrome Using Machine Learning,” In 2024 The 7th International Conference on Machine Learning and Machine Intelligence (MLMI) (MLMI 2024). pp 20-26. Aug, 2024
Mridul, Aunik Hasan., Ahsan, Nowreen., Alam, Syeda Sadia., Afrose, Sonia., Sultana, Zakia., and kafi, Md. Tanvir Mahmud, “Polycystic Ovary Syndrome (PCOS) Disease Prediction Using Traditional Machine Learning and Deep Learning Algorithms,” International Journal of Computer Information Systems and Industrial Management Applications, vol. 16 pp 322-346. July, 2024
Silambarasan, E., Nirmala, G., and Mishara, Ishani, “Polycystic ovary syndrome detection using optimized and DenseNet,” International Journal of Information Technology. vol. 17 no. 2 pp 1039-1047, Mar. 2025
Thakre, Vaidehi., Vedpathak, Shreyas., Thakre, Kalpana., and Sonawani, Shilpa, “PCOcare: Detection and Prediction using Machine Learning Algorithms,” Bioscience Biotechnology Research Communications, vol. 13 no. 14 pp 240-244, Dec. 2020
Marshall, M.D. Ph.D., John C., and Dunaif, M.D, Andrea, “Should all woman with PCOS be treated for insulin resistance?,” Fertility and Sterility, vol. 97 no.1 pp. 18-22, 2012
Roe, MD, Andrea Hsu., and Dokras, MD, PhD, Anuja’ “The Diagnosis of Polycystic Ovary Syndrome in Adolescents,” Reviews in Obstetrics & Gynecology, vol. 4 no.2 pp. 45-51, 2011
Ade Aulia. (2023, 23 Agustus). Support Vector Machine (SVM) Untuk Klasifikasi Penyakit Diabetes | Machine Learning Project 3. [Video]. YouTube. https://youtu.be/kRTrwNWGsiA?si=BAPTRFNhwCYeHJXu
