Correlation Between Concentrations of Fecal Calprotectin and Outcomes of Patients With Ulcerative Colitis in a Phase 2 Trial

BACKGROUND & AIMS: Accurate biomarkers of disease activity and therapeutic response can be valuable for clinical trials. We performed a post hoc analysis of data from a phase 2 trial to assess the relationship between the concentration of fecal calprotectin (FCP) and clinical and endoscopic outcomes of patients with moderate to severe ulcerative colitis receiving tofacitinib. METHODS: In a double-blind, placebo-controlled, phase 2 trial, 194 patients were assigned randomly to groups given tofacitinib (0.5, 3, 10, or 15 mg twice daily) or placebo. Clinical and endoscopic outcomes were assessed at week 8 using the Mayo scoring system. Receiver operating characteristics were used to evaluate the relationships between FCP concentration and clinical and endoscopic outcomes, and to determine the FCP cut-off concentration that correlated with patient outcome. RESULTS: Week 8 median concentrations of FCP were significantly lower in responders than in non-responders (P < .001): clinical response, 156 vs 725 mg/kg; clinical remission, 64 vs 617 mg/kg; endoscopic remission, 44 vs 489 mg/kg; and mucosal healing, 127 vs 753 mg/kg. Area-under-the-curve values for FCP receiver operating characteristic models were 0.80 for clinical remission, 0.81 for endoscopic remission, and 0.78 for mucosal healing. An FCP cut-off value of 150 mg/kg achieved the highest summation of sensitivity and specificity for clinical remission (0.68 and 0.79, respectively; k coefficient, 0.44) and endoscopic remission (0.79 and 0.75, respectively; k coefficient, 0.38). CONCLUSIONS: Concentrations of FCP correlate with clinical and endoscopic outcomes of patients with moderate to severe ulcerative colitis receiving tofacitinib, although at an individual level the agreement was moderate. FCP concentration with a cut-off value of 150 mg/kg had only fair to good accuracy in classifying clinical and endoscopic outcomes in a clinical trial.