Analyzing Tuberculosis Reactivation in Patients with Rheumatoid Arthritis and Ankylosing Spondylitis Treated with Biological Therapy Using Machine Learning Methods

• Published in: Applied sciences Vol. 11; no. 23; p. 11400
• Main Authors: Mircea-Vicoveanu, Andra-Maria, Rezuș, Elena, Leon, Florin, Curteanu, Silvia
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-12-2021
• Subjects: Algorithms; Ankylosing spondylitis; Arthritis; Biological products; Classification; Decision trees; Deep learning; Disease; Gene expression; Generalized linear models; Immunotherapy; Infections; Learning algorithms; Machine learning; machine learning algorithms; Medical diagnosis; Nonsteroidal anti-inflammatory drugs; Patients; Rheumatoid arthritis; Support vector machines; Tuberculosis
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app112311400

This study is based on the consideration that the patients with rheumatoid arthritis and ankylosing spondylitis undergoing biological therapy have a higher risk of developing tuberculosis. The QuantiFERON-TB Gold test result was the output of the models and a series of features related to the patients and their treatments were chosen as inputs. A distribution of patients by gender and biological therapy, followed at the time of inclusion in the study, and at the end of the study, is made for both rheumatoid arthritis and ankylosing spondylitis. A series of classification algorithms (random forest, nearest neighbor, k-nearest neighbors, C4.5 decision trees, non-nested generalized exemplars, and support vector machines) and attribute selection algorithms (ReliefF, InfoGain, and correlation-based feature selection) were successfully applied. Useful information was obtained regarding the influence of biological and classical treatments on tuberculosis risk, and most of them agreed with medical studies.