Analisis dan Klasifikasi Risiko Diabetes dengan Algoritma Support Vector Machine (SVM)
Keywords:
SVM, prediksi, diabetes, RMEAbstract
Penelitian ini bertujuan mengembangkan dan mengevaluasi model Machine Learning untuk prediksi risiko diabetes menggunakan data Rekam Medik Elektronik (RME) di rumah sakit. Sistem konvensional seringkali gagal mengekstraksi pola kompleks dan hubungan non-linier dari data RME, sehingga pendekatan Support Vector Machine (SVM) digunakan untuk mengatasi masalah ini. Dataset yang digunakan mencakup variabel seperti usia, indeks massa tubuh (IMT), tekanan darah, kadar glukosa, dan riwayat keluarga. Tahapan penelitian meliputi pengumpulan data, pra-pemrosesan, pemilihan fitur, pengembangan, pelatihan, dan evaluasi model SVM. Model SVM yang dikembangkan mencapai akurasi 85%, dengan presisi 87%, recall 83%, dan F1 score 0.85. Hasil penelitian menunjukkan bahwa SVM dapat mengidentifikasi pola dalam data kesehatan secara akurat, mempercepat diagnosis, dan meningkatkan prediksi risiko diabetes. Temuan ini berkontribusi dalam pengembangan alat bantu pengambilan keputusan yang lebih cepat dan akurat bagi tenaga kesehatan, serta meningkatkan metode diagnostik untuk deteksi dini risiko diabetes. Penelitian ini juga menyoroti pentingnya fitur seperti glukosa darah puasa, IMT, dan usia sebagai prediktor signifikan. Langkah selanjutnya adalah validasi eksternal dan integrasi ke dalam sistem pendukung keputusan klinis..
References
Amelec Viloria., Yaneth Herazo-Beltran,. Danelys Cabrera, & Omar Bonerge Pineda (2022). Diabetes Diagnostic Prediction Using Vector Support Machines. https://doi.org/10.1016/j.procs.2020.03.065.
Abu Wildan Mucholladin., Fitra Abdurrachman Bachtiar. & Muhammad Tanzil Furqon (2021). Klasifikasi Penyakit Diabetes menggunakan Metode Support Vector Machine. http://j-ptiik.ub.ac.id.
Burges, C. J. C. (1998). Data Mining and Knowledge Discovery, 2(2), 121–167. A Tutorial on Support Vector Machines for Pattern Recognition. doi:10.1023/a:1009715923555
Chollette C. Olisah., Lyndon Smith., & Melvyn Smith (2022). Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective. https://doi.org/10.1016/j.cmpb.2022.106773
Ch. Usha Kumari., A. Sampath Dakshina Murthy., B. Lakshmi Prasanna., M. Pala Prasad Reddy., & Asisa Kumar Panigrahy (2020). An automated detection of heart arrhythmias using machine learning technique: SVM. https://doi.org/10.1016/j.matpr.2020.07.088
Derek A. Pisner., & David M. Schnyer (2020). Chapter 6 - Support vector machine. https://doi.org/10.1016/B978-0-12-815739-8.00006-7
Deepti Sisodia., & Dilip Singh Sisodia (2018). Prediction of Diabetes using Classification Algorithms. https://doi.org/10.1016/j.procs.2018.05.122
Elias Dritsas, & Maria Trigka (2022). Data-Driven Machine-Learning Methods for Diabetes Risk Prediction. https:// doi.org/10.3390/s22145304
Edwin Frank, & Samon Daniel (2024). Integration of Machine Learning Models with Clinical Decision Support Systems. https://www.researchgate.net/publication/381829478_Integration_of_Machine_Learning_Models_with_Clinical_Decision_Support_Systems
Gowthami S., R Venkata Siva Reddy, & Mohammed Riyaz Ahmed (2023). Exploring the effectiveness of machine learning algorithms for early detection of Type-2 Diabetes Mellitus. https://doi.org/10.1007/s40747-021-00398-7
Himanshu Gupta., Hirdesh Varshney., Tarun Kumar Sharma., Nikhil Pachauri & Om Prakash Verma. (2022). The Identification of Diabetes Mellitus Subtypes Applying Cluster Analysis Techniques: A Systematic Review. https://doi.org/10.1007/s40747-021-00398-7
Himanshu Gupta., Hirdesh Varshney., Tarun Kumar Sharma., Nikhil Pachauri &Om Prakash Verma (2022). Comparative performance analysis of quantum machine learning with deep learning for diabetes prediction. https://doi.org/10.1007/s40747-021-00398-7
Jingyu Xue., Fanchao Min., & Fengying Ma (2020). Research on Diabetes Prediction Method Based on Machine Learning. doi:10.1088/1742-6596/1684/1/012062
K. Thaiyalnayaki (2018). Classification of Diabetes Using Deep Learning and SVM Techniques. http://dx.doi.org/10.31782/IJCRR.2021.13127
Leon Kopitar., primoz Kocbek., Leona cilar., Aziz Sheikh & Gregor Stiglic (2020). Early detection of type 2 diabetes mellitus using machine learning based prediction models. https://doi.org/10.1038/s41598-020-68771-z
L. J. Muhammad., Ebrahem A. Algehyne & Sani Sharif Usman (2020). Predictive Supervised Machine Learning Models for Diabetes Mellitus. https://doi.org/10.1007/s42979-020-00250-8
Md. Jamal Hossain, Md. Alâ€Mamun., & & Md. Rabiul Islam. (2004). Diabetes Mellitus, The Fastest Growing Global Public Healthconcern: Early Detection Should Be Focused. https://doi.org/10.1002/hsr2.2004
Nagy Ramadan, & Hesham Ahmed Hefny (2023). Healthcare predictive analytics using machine learning and deep learning techniques: a survey. https://doi.org/10.1186/s43067-023-00108-y
Rahul Katarya., & Sajal Jain (2020). Comparison of Different Machine Learning Models for diabetes detection. DOI: 10.1109/ICADEE51157.2020.9368899
V. Anuja Kumari., & R.Chitra (2013). Classification Of Diabetes Disease Using Support Vector Machine. Vol. 3, Issue 2, March -April 2013, pp.1797-1801
Victor Chang., Jozeene Bailey & Qianwen Ariel Xu,. Zhili Sun (2022). Pima Indians diabetes mellitus classification based on machine learning (ML) algorithms. https://doi.org/10.1007/s00521-022-07049-z
