Machine learning-based prediction model for responses of bDMARDs in patients with rheumatoid arthritis and ankylosing spondylitis.
Seulkee LeeSeonyoung KangYeonghee EunHong-Hee WonHyungjin KimJaejoon LeeEun-Mi KohHoon Suk ChaPublished in: Arthritis research & therapy (2021)
RF-method exhibited superior prediction performance for responses of bDMARDs to a conventional statistical method, i.e., logistic regression, in RA patients. In contrast, despite the comparable size of the dataset, machine learning did not outperform in AS patients. The most important features of both diseases, according to feature importance analysis were patient self-reporting scales.
Keyphrases
- machine learning
- ankylosing spondylitis
- end stage renal disease
- ejection fraction
- newly diagnosed
- chronic kidney disease
- rheumatoid arthritis
- magnetic resonance
- peritoneal dialysis
- artificial intelligence
- magnetic resonance imaging
- disease activity
- deep learning
- systemic lupus erythematosus
- patient reported
- adverse drug
- contrast enhanced