Early Risk Prediction of Rheumatoid ArthritisUsing a Hybrid Restricted Boltzmann Machine
Main Article Content
Abstract
Rheumatoid arthritis (RA) is a chronic autoimmunedisease that requires early detection to prevent permanent jointdamage. The main challenge in predicting RA risk lies in thecomplexity of clinical data, which is multidimensional and oftenimbalanced. This study employs a Hybrid Restricted BoltzmannMachine (H-RBM) approach to improve the accuracy of earlyRA risk prediction. The RBM method is used as a featureextractor to map non-linear relationships within clinical data,which is then combined with three classification algorithms:Support Vector Machine (SVM), Random Forest (RF), andLogistic Regression (LR). The research data was sourced fromKaggle, comprising 4,425 samples that were balanced using theSynthetic Minority Oversampling Technique (SMOTE). Testingwas conducted with three data split ratios (70:30, 80:20, and90:10) using GridSearchCV for hyperparameter tuning. Theexperimental results show that the RBM-SVM model dominatesabsolutely with the highest performance at the 90:10 ratio,yielding an accuracy of 99.82%, an AUC score of 1.0000, and arecall of 100%. The perfect recall rate indicates that the modelis capable of identifying all positive patients without any missedcases (zero false negatives). Meanwhile, the RBM-RF and RBM-LR models achieved optimal performance at an 80:20 ratio withaccuracies of 93.95% and 83.42%, respectively. Overall, RBMintegration proved significant in extracting more informativelatent information compared to raw clinical features, therebymaking a crucial contribution to a precise RA early detectiondecision support system
Article Details
References
[1] M. Ellen M. Gravallese and M. D. Gary S. Firestein, “Rheumatoid Arthritis—Common Origins, Divergent Mechanisms,” N. Engl. J. Med., vol. 388, p. 6, 2023, doi: 10.1056/NEJMra2103726.
[2] S. Alivernini, G. S. Firestein, and I. B. Mcinnes, “Review: The Pathogenesis of Rheumatoid Arthritis,” Immunity, vol. 55, no. 12, pp. 2255–2270, 2022, doi: 10.1016/j.immuni.2022.11.009.
[3] N. I. Butt, B. Waris, and U. Waris, “Delayed Diagnosis and Treatment of Rheumatoid Arthritis: A Preventable Path to Disability,” Am. J. Diagnostic Imaging, 2025, doi: 10.5455/ajdi.20250531043655.
[4] S. Amiroch, “Machine Learning for the Prediction of Antiviral Compounds Targeting Avian Influenza A/H9N2 Viral Proteins,” 2022.
[5] A. J. W. Lim et al., “Robust SNP - based prediction of rheumatoid arthritis through machine - learning - optimized polygenic risk score,” pp. 1–17, 2023, doi: 10.1186/s12967-023-03939-5.
[6] J. Jose and D. V. Jose, “Deep learning algorithms for intrusion detection systems in the Internet of Things using the CIC-IDS 2017 dataset,” Int. J. Electr. Comput. Eng., vol. 13, no. 1, pp. 1134–1141, 2023, doi: 10.11591/ijece.v13i1.pp1134-1141.
[7] J. Jamil and S. Pulukadang, “Application of Deep Learning Methods in Education,” vol. 4, no. 6, pp. 1019–1038, 2025.
[8] M. Javeed, M. Gochoo, A. Jalal, and K. Kim, “HF-SPHR: Hybrid Features for Sustainable Physical Healthcare Pattern Recognition Using Deep Belief Networks,” 2021.
[9] Y. Amelia, “Comparison of Deep Learning and Machine Learning Methods for Classification (Trial on Breast Cancer Data),” pp. 109–114, 2018.
[10] R. R. Salam, M. F. Jamil, and Y. Ibrahim, “Sentiment Analysis of Cash Direct Assistance Distribution for Fuel Oil Using Support Vector Machines,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 3, no. April, pp. 27–35, 2023.
[11] G. Li, A. Zhang, Q. Zhang, D. Wu, and C. Zhan, “Pearson Correlation Coefficient-Based Performance Enhancement of a Broad Learning System for Stock Price Prediction,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69, no. 5, pp. 2413–2417, May 2022, doi: 10.1109/TCSII.2022.3160266,” Inst. of Electr. and Electron. Eng., vol. 69, no. 5, pp. 2413–2417, 2022, doi: 10.1109/TCSII.2022.3160266.
[12] Y. Zhang, L. Deng, and B. Wei, “Imbalanced Data Classification Based on Improved Random-SMOTE and Feature Standard Deviation,” MDPI, vol. 12, no. 11, pp. 1–17, 2024, doi: https://doi.org/10.3390/math12111709.
[13] V. R. Joseph, V. R. Joseph, and H. M. Stewart, “Optimal ratio for data splitting,” Stat. Anal. Data Min. ASA Data Sci. J., vol. 15, no. 4, pp. 531–538, 2022, doi: 10.1002/sam.11583.
[14] M. Sivakumar and S. Parthasarathy, “Trade-off between training and testing ratio in machine learning for medical image processing,” pp. 1–17, 2024, doi: 10.7717/peerj-cs.2245.
[15] A. Setiawan, A. A. Siregar, N. Setiawan, J. Nasution, and N. D. Putra, “Optimization of SVM and Random Forest Model Performance for Breast Cancer Classification Using Hyperparameter Tuning,” vol. 4, no. 3, pp. 2141–2149, 2026.
[16] B. Santoso, “Unsupervised Feature Extraction Using Restricted Boltzmann Machines: A Probabilistic Approach in Deep Learning Applications,” Journal of Informatics, vol. 18, pp. 45–58, 2023.
[17] J. Schl¨uter, “Restricted Boltzmann Machine Derivations,” no. 6, pp. 1–18, 2014.
[18] S. N. Khan, S. U. Khan, H. Aznaoui, and C. B. S¸ ahin, “Generalization of linear and non-linear support vector machines in multiple fields: a review,” vol. 4, no. 3, pp. 226–239, 2023, doi: 10.11591/csit.v4i3.pp226-239.
[19] E. Najjar, N. A. Alkhaykanee, and A. Majeed, “Classification of Arabic Documents with Five Classifier Models Using Machine Learning,” vol. 9, no. January, pp. 365–370, 2025.
[20] N. Alexander, R. Bria, and A. Witanti, “Analysis of Indonesian Public Sentiment Using the Support Vector Machine Algorithm Regarding the 2024 Presidential Election,” vol. 7, no. 6, 2024