Background: Hypertension is a significant comorbidity in rheumatoid arthritis (RA), yet its prediction and management remain underexplored in this population.

Objectives: This study aimed to utilize machine learning (ML) algorithms to predict hypertension and identify its key clinical determinants in RA patients, while also examining the relationship between hypertension and disease activity measured by the Disease Activity Score in 28 joints (DAS28).

Methods: A retrospective cohort study included 1,773 RA patients from the Kuwait Registry for Rheumatic Diseases (2013–2023). Five ML models, including LightGBM and Random Forest, were evaluated for their ability to predict hypertension. Logistic regression was employed to assess the impact of hypertension on DAS28.

Results: LightGBM was the most effective model (ROC AUC: 0.737), with fasting blood sugar (FBS), creatinine, BMI, and disease duration emerging as top predictors. Logistic regression revealed hypertension significantly predicts DAS28 (OR 1.74; p=0.020). Hypertension increased the likelihood of moderate-to-high disease activity (OR 1.74; 95% CI: 1.10–2.77; p=0.020). Gender-specific logistic regression revealed unique associations, with rheumatoid factor positivity strongly predicting high DAS28 scores in males (OR 2.67; p=0.042) and hypertension showing a robust association with high DAS28 in females (OR 1.81; p=0.002).

Conclusion: ML approaches provide robust predictive capabilities for hypertension and DAS28, enabling personalized care strategies for RA patients. These findings underscore the potential of ML to support personalized care strategies, improve hypertension management, and enhance overall RA outcomes. Future research may integrate diverse clinical and lifestyle factors to refine prediction models and facilitate their clinical implementation.

REFERENCES: [1] DeMizio DJ, Geraldino-Pardilla LB. Autoimmunity and Inflammation Link to Cardiovascular Disease Risk in Rheumatoid Arthritis. Rheumatology and Therapy. 2019;7: 19–33.

[2] England B, Thiele G, Anderson D, Mikuls T. Increased cardiovascular risk in rheumatoid arthritis: mechanisms and implications. BMJ. 2018; k1036. doi:10.1136/bmj.k1036.

[3] Al-Ahmari AK. Prevalence of Hypertension and Its Associated Risk Factors Among Patients with Rheumatoid Arthritis in the Kingdom of Saudi Arabia. International Journal of General Medicine. 2022;Volume 15: 6507–6517.

[4] Ahmed O, Krishnamurthy V, Kaba RA, Tahir H. The management of cardiovascular disease risk in patients with rheumatoid arthritis. Expert Opinion on Pharmacotherapy. 2022;23: 947–958.

[5] Jagpal A, Navarro-Mill\’ an I. Cardiovascular co-morbidity in patients with rheumatoid arthritis: a narrative review of risk factors, cardiovascular risk assessment and treatment. BMC Rheumatology. 2018;2.

[6] Fragoulis GE, Panayotidis I, Nikiphorou E. Cardiovascular Risk in Rheumatoid Arthritis and Mechanistic Links: From Pathophysiology to Treatment. Current Vascular Pharmacology. 2020;18: 431–446.

[7] Liao KP, Solomon DH. Traditional cardiovascular risk factors, inflammation and cardiovascular risk in rheumatoid arthritis. Rheumatology. 2012;52: 45–52.

[8] Rawla P. Cardiac and vascular complications in rheumatoid arthritis. Rheumatology. 2019;57: 27–36.

[9] MacEachern SJ, Forkert ND. Machine learning for precision medicine. Genome. 2021;64: 416–425.

[10] Aparna Hiren Patil Kose, K. Mangaonkar. Application of machine learning in rheumatoid arthritis diseases research: Review and future directions. Combinatorial chemistry & high throughput screening. 2023.

[11] Al-Herz A, Al-Awadhi A, Saleh K, Al-Kandari W, Hasan E, Ghanem A, et al. A comparison of rheumatoid arthritis patients in Kuwait with other populations: results from the KRRD registry. British Journal of Medicine and Medical Research. 2016;14: 1–11.

Acknowledgements: The authors acknowledge the Kuwait Registry for Rheumatic Diseases (KRRD) for providing data for this study. This research was funded by the Kuwait Foundation for the Advancement of Sciences (KFAS) under the project titled “KFAS Project: CN22-14SL-1653.” Additional support was provided by the AUK Open Access Publishing Fund.

Disclosure of Interests: None declared.

© The Authors 2025. This abstract is an open access article published in Annals of Rheumatic Diseases under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ ). Neither EULAR nor the publisher make any representation as to the accuracy of the content. The authors are solely responsible for the content in their abstract including accuracy of the facts, statements, results, conclusion, citing resources etc.