Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists.

BACKGROUND: Real-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists. OBJECTIVE: To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. DESIGN: Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). SETTING: 6 centers across the United States. PARTICIPANTS: 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. INTERVENTION: Real-time use of CADx during routine colonoscopy. MEASUREMENTS: The primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided. RESULTS: The CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. LIMITATION: Decision making based on CADx might differ outside a clinical trial. CONCLUSION: CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. PRIMARY FUNDING SOURCE: Olympus America Corporation served as the clinical study sponsor.

Prevalence of Comorbid Factors in Patients With Recurrent Clostridioides difficile Infection in ECOSPOR III, a Randomized Trial of an Oral Microbiota-Based Therapeutic.

BACKGROUND: Although comorbidities are risk factors for recurrent Clostridioides difficile infection (rCDI), many clinical trials exclude patients with medical conditions such as malignancy or immunosuppression. In a phase 3, double-blind, placebo-controlled, randomized trial (ECOSPOR III), fecal microbiota spores, live (VOWST, Seres Therapeutics; hereafter "VOS," formerly SER-109), an oral microbiota therapeutic, significantly reduced the risk of rCDI at week 8. We evaluated the efficacy of VOS compared with placebo in patients with comorbidities and other risk factors for rCDI. METHODS: Adults with rCDI were randomized to receive VOS or placebo (4 capsules daily for 3 days) following standard-of-care antibiotics. In this post hoc analysis, the rate of rCDI through week 8 was assessed in VOS-treated participants compared with placebo for subgroups including (i) Charlson comorbidity index (CCI) score category (0, 1-2, 3-4, ≥5); (ii) baseline creatinine clearance (<30, 30-50, >50 to 80, or >80 mL/minute); (iii) number of CDI episodes, inclusive of the qualifying episode (3 and ≥4); (iv) exposure to non-CDI-targeted antibiotics after dosing; and (v) acid-suppressing medication use at baseline. RESULTS: Of 281 participants screened, 182 were randomized (59.9% female; mean age, 65.5 years). Comorbidities were common with a mean overall baseline age-adjusted CCI score of 4.1 (4.1 in the VOS arm and 4.2 in the placebo arm). Across all subgroups analyzed, VOS-treated participants had a lower relative risk of recurrence compared with placebo. CONCLUSIONS: In this post hoc analysis, VOS reduced the risk of rCDI compared with placebo, regardless of baseline characteristics, concomitant medications, or comorbidities.

A Phase 1b Safety Study of SER-287, a Spore-Based Microbiome Therapeutic, for Active Mild to Moderate Ulcerative Colitis.

BACKGROUND & AIMS: Firmicutes bacteria produce metabolites that maintain the intestinal barrier and mucosal immunity. Firmicutes are reduced in the intestinal microbiota of patients with ulcerative colitis (UC). In a phase 1b trial of patients with UC, we evaluated the safety and efficacy of SER-287, an oral formulation of Firmicutes spores, and the effects of vancomycin preconditioning on expansion (engraftment) of SER-287 species in the colon. METHODS: We conducted a double-blind trial of SER-287 in 58 adults with active mild-to-moderate UC (modified Mayo scores 4-10, endoscopic subscores ≥1). Participants received 6 days of preconditioning with oral vancomycin (125 mg, 4 times daily) or placebo followed by 8 weeks of oral SER-287 or placebo. Patients were randomly assigned (2:3:3:3) to groups that received placebo followed by either placebo or SER-287 once weekly, or vancomycin followed by SER-287 once weekly, or SER-287 once daily. Clinical end points included safety and clinical remission (modified Mayo score ≤2; endoscopic subscores 0 or 1). Microbiome end points included SER-287 engraftment (dose species detected in stool after but not before SER-287 administration). Engraftment of SER-287 and changes in microbiome composition and associated metabolites were measured by analyses of stool specimens collected at baseline, after preconditioning, and during and 4 weeks after administration of SER-287 or placebo. RESULTS: Proportions of patients with adverse events did not differ significantly among groups. A higher proportion of patients in the vancomycin/SER-287 daily group (40%) achieved clinical remission at week 8 than patients in the placebo/placebo group (0%), placebo/SER-287 weekly group (13.3%), or vancomycin/SER-287 weekly group (17.7%) (P = .024 for vancomycin/SER-287 daily vs placebo/placebo). By day 7, higher numbers of SER-287 dose species were detected in stool samples from all SER-287 groups compared with the placebo group (P < .05), but this difference was not maintained beyond day 7 in the placebo/SER-287 weekly group. In the vancomycin groups, a greater number of dose species were detected in stool collected on day 10 and all subsequent time points through 4 weeks post dosing compared with the placebo group (P < .05). A higher number of SER-287 dose species were detected in stool samples on days 7 and 10 from subjects who received daily vs weekly SER-287 doses (P < .05). Changes in fecal microbiome composition and metabolites were associated with both vancomycin/SER-287 groups. CONCLUSIONS: In this small phase 1b trial of limited duration, the safety and tolerability of SER-287 were similar to placebo. SER-287 after vancomycin was significantly more effective than placebo for induction of remission in patients with active mild to moderate UC. Engraftment of dose species was facilitated by vancomycin preconditioning and daily dosing of SER-287. ClinicalTrials.gov ID NCT02618187.