The Association Between Arthralgia and Vedolizumab Using Natural Language Processing

Area of Science:

• Gastroenterology
• Pharmacovigilance
• Biostatistics

Background:

• Vedolizumab's gut-selective action raises questions about arthralgia risk in inflammatory bowel disease (IBD).
• Limited studies compare arthralgia risk between vedolizumab and tumor necrosis factor inhibitors (TNFi) due to coding challenges.
• Natural language processing (NLP) offers a novel approach to identify arthralgia in clinical notes.

Purpose of the Study:

• To evaluate the utility of NLP for identifying arthralgia in IBD patient clinical notes.
• To compare the risk of arthralgia between vedolizumab and TNFi in IBD patients.
• To assess potential safety concerns regarding joint pain with vedolizumab therapy.

Main Methods:

• Retrospective study of an electronic medical record (EMR)-based IBD cohort from two tertiary care centers.
• Utilized NLP to define arthralgia as the primary outcome.
• Employed inverse probability of treatment weighting and Cox regression to compare arthralgia risk between vedolizumab and TNFi groups.

Main Results:

• The study included 367 patients on vedolizumab and 1218 on TNFi.
• Vedolizumab users were older and had higher immunomodulator use.
• No significantly increased risk of arthralgia was observed with vedolizumab compared to TNFi (HR, 1.20; 95% CI, 0.97-1.49).

Conclusions:

• This large observational study did not find a significantly increased risk of arthralgia with vedolizumab compared to TNFi.
• NLP proved effective in identifying arthralgia within clinical notes.
• Findings suggest vedolizumab is not associated with a higher risk of joint pain than TNFi in IBD patients.