Multinomial Logistic Regression and Support Vector Machine for Osteoarthritis Classification

C. Aroef, R. P. Yuda, Z. Rustam, J. Pandelaki

Research output: Contribution to journalConference articlepeer-review

6 Citations (Scopus)


Everyone joints go through a cycle of damage and repair during their lifetime, but sometimes the body's process to repair our joints can cause changes in their shape or structure. When these changes happen, it's known as osteoarthritis. Osteoarthritis is the most common form of arthritis, affecting millions of people worldwide. Osteoarthritis causes pain, swelling, stiffness in the areas, and decreased the ability to move for the sufferers. Therefore it requires accurate method of classification. Many methods have been used to classify osteoarthritis, but this study will apply Multinomial Logistic Regression and Super Vector Machine (SVM) as the machine learning methods. We used CT scan result data from RSUPN dr. Cipto Mangunkusumo, Central Jakarta. The results show the SVM provides better results than Multinomial Logistic Regression in terms of classification accuracy. The highest accuracy of SVM reaches around 85%, while Multinomial Logistic Regression only 71%.

Original languageEnglish
Article number012012
JournalJournal of Physics: Conference Series
Issue number1
Publication statusPublished - 20 Dec 2019
EventMathematics, Informatics, Science and Education International Conference 2019, MISEIC 2019 - Surabaya, Indonesia
Duration: 28 Sept 2019 → …


Dive into the research topics of 'Multinomial Logistic Regression and Support Vector Machine for Osteoarthritis Classification'. Together they form a unique fingerprint.

Cite this