ABSTRACT
BACKGROUND: Vedolizumab is an effective therapy for ulcerative colitis (UC), but costly and slow to work. New clinical responses occur after 30 weeks of therapy. AIMS: To enable physicians, patients, and insurers to predict whether a patient with UC will respond to vedolizumab at an early time point after starting therapy. METHODS: The clinical study data request website provided the phase 3 clinical trial data for vedolizumab. Random forest models were trained on 70% and tested on 30% of the data to predict corticosteroid-free endoscopic remission at week 52. Models were constructed using baseline data, or data through week 6 of vedolizumab therapy from 491 subjects. RESULTS: The AuROC for prediction of corticosteroid-free endoscopic remission at week 52 using baseline data was only 0.62 (95% CI: 0.53-0.72), but was 0.73 (95% CI: 0.65-0.82) when using data through week 6. A total of 47% of subjects were predicted to be remitters, and 59% of these subjects achieved corticosteroid-free endoscopic remission, in contrast to 21% of the predicted non-remitters. A week 6 prediction using FCP ≤234 µg/g was nearly as accurate. CONCLUSIONS: A machine learning algorithm using laboratory data through week 6 of vedolizumab therapy was able to accurately identify which UC patients would achieve corticosteroid-free endoscopic remission on vedolizumab at week 52. Application of this algorithm could have significant implications for clinical decisions on whom to continue on this costly medication when the benefits of the vedolizumab are not clinically apparent in the first 6 weeks of therapy.
Subject(s)
Algorithms , Antibodies, Monoclonal, Humanized/therapeutic use , Colitis, Ulcerative/diagnosis , Colitis, Ulcerative/drug therapy , Endoscopy, Gastrointestinal , Adrenal Cortex Hormones/therapeutic use , Adult , Clinical Trials, Phase III as Topic , Cohort Studies , Female , Humans , Male , Middle Aged , Predictive Value of Tests , Prognosis , Remission Induction , Retrospective Studies , Treatment Outcome , Young AdultABSTRACT
The prevalence of heterotopic gastric mucosa of the upper esophagus (inlet patch) has a wide range depending on the method and detail of examination. The inlet patch is believed to be a congenital malformation that rarely leads to symptoms. We aimed to quantify the prevalence of the inlet patch in a non-referred population and determine if there are any risk factors or associated symptoms. Men between ages 50 and 79 presenting for routine colonoscopy at two clinical sites were recruited to undergo an upper endoscopy. Endoscopists were prompted to examine for the presence of the inlet patch. Of the 822 enrolled patients, 795 had data regarding the presence of an inlet patch. Of these, 55 (6.9%) had an inlet patch identified. Education was inversely associated (odds ratio [OR] advanced degree vs. high school or less = 0.310; 95% confidence interval [CI] = 0.111, 0.869), and tobacco use was positively associated with the presence of an inlet patch (current vs. never smokers OR = 2.87; 95% CI = 1.23, 6.69; former vs. never smokers OR = 1.93; 95% CI = 0.922, 4.02). No association between the inlet patch and symptoms of heartburn, globus, or dysphagia was found. In a cross-sectional study of colon cancer screenees, inlet patches were common and were not associated with symptoms. Tobacco use appears to be associated with the presence of an inlet patch.