Comparative evaluation of a language model and human specialists in the application of European guidelines for the management of inflammatory bowel diseases and malignancies.

BACKGROUND: Society guidelines on colorectal dysplasia screening, surveillance, and endoscopic management in inflammatory bowel disease (IBD) are complex, and physician adherence to them is suboptimal. We aimed to evaluate the use of ChatGPT, a large language model, in generating accurate guideline-based recommendations for colorectal dysplasia screening, surveillance, and endoscopic management in IBD in line with European Crohn's and Colitis Organization (ECCO) guidelines. METHODS: 30 clinical scenarios in the form of free text were prepared and presented to three separate sessions of ChatGPT and to eight gastroenterologists (four IBD specialists and four non-IBD gastroenterologists). Two additional IBD specialists subsequently assessed all responses provided by ChatGPT and the eight gastroenterologists, judging their accuracy according to ECCO guidelines. RESULTS: ChatGPT had a mean correct response rate of 87.8%. Among the eight gastroenterologists, the mean correct response rates were 85.8% for IBD experts and 89.2% for non-IBD experts. No statistically significant differences in accuracy were observed between ChatGPT and all gastroenterologists (P=0.95), or between ChatGPT and the IBD experts and non-IBD expert gastroenterologists, respectively (P=0.82). CONCLUSIONS: This study highlights the potential of language models in enhancing guideline adherence regarding colorectal dysplasia in IBD. Further investigation of additional resources and prospective evaluation in real-world settings are warranted.

The Association Between Low Body-Mass Index and Serious Post-endoscopic Adverse Events.

BACKGROUND: Low body mass index (LBMI) was associated with longer colonoscopy procedure time and procedural failure, and commonly considered to be a risk factor for post-endoscopic adverse events, but evidence is lacking. AIM: We aimed to assess the association between serious adverse events (SAE) and LBMI. METHODS: A single center retrospective cohort of patients with LBMI (BMI ≤ 18.5) undergoing an endoscopic procedure was matched (1:2 ratio) to a comparator group (19 ≤ BMI ≤ 30). Matching was performed according to age, gender, inflammatory bowel disease or malignancy diagnoses, previous abdomino-pelvic surgery, anticoagulation therapy and type of endoscopic procedure. The primary outcome was SAE, defined as bleeding, perforation, aspiration or infection, following the procedure. The attribution between each SAE and the endoscopic procedure was determined. Secondary outcomes included each complication alone and endoscopy-attributed SAEs. Univariate and multivariate analyses were applied. RESULTS: 1986 patients were included (662 in the LBMI group). Baseline characteristics were mostly similar between the groups. The primary outcome occurred in 31/662 (4.7%) patients in the LBMI group and in 41/1324 (3.1%) patients in the comparator group (p = 0.098). Among the secondary outcomes, infections (2.1% vs. 0.8%, p = 0.016) occurred more frequently in the LBMI group. Multivariate analysis revealed an association between SAE and LBMI (OR 1.76, 95% CI 1.07-2.87), male gender, diagnosis of malignancy, high-risk endoscopic procedure, age > 40 years, and ambulatory setting. CONCLUSION: Low BMI was associated with higher post-endoscopic serious adverse events. Special attention is required when performing endoscopy in this fragile patient population.

The Association Between Opioid Use and Opioid Type and the Clinical Course and Outcomes of Acute Pancreatitis.

OBJECTIVES: Basic science studies suggest that opioids aggravate disease severity and outcomes in acute pancreatitis. We sought to determine the association of opioid use and opioid type with the clinical course and outcome of acute pancreatitis. METHODS: In this retrospective single-center observational study, we included all adult patients admitted with acute pancreatitis between 2008 and 2021. Patients were classified into 3 groups based on analgesia type: morphine, noonmorphine opioid, and nonopioid. RESULTS: We included 2308 patients. Of the patients, 343 (14.9%) were treated with morphine, 733 (31.8%) were treated with nonmorphine opioids, and 1232 (53.4%) patients were in the nonopioid group. The incidence of 30-day mortality did not differ significantly between study groups: 3.9%, 2.9%, and 4.4% in the nonopioid, nonmorphine-opioid, and morphine groups, respectively ( P = 0.366).In multivariate analysis, the composite end point consisting of 30-day mortality, invasive ventilation, emergent abdominal surgery, and need for vasopressors was significantly more likely to occur in the morphine group than in the nonopioid group (adjusted odds ratio, 1.69; 95% confidence interval, 1.1-2.598; P = 0.01). CONCLUSIONS: Mortality among acute pancreatitis patients did not differ significantly between patients receiving morphine, nonmorphine opioids, and nonopioids. However, morphine treatment was associated with higher rates of some serious adverse events.

COVID-19 in Patients with Inflammatory Bowel Disease: The Israeli Experience.

BACKGROUND: Crohn's disease (CD) and ulcerative colitis (UC) are chronic, immune-mediated inflammatory bowel diseases (IBD) affecting millions of people worldwide. IBD therapies, designed for continuous immune suppression, often render patients more susceptible to infections. The effect of the immune suppression on the risk of coronavirus disease-19 (COVID-19) is not fully determined yet. OBJECTIVE: To describe COVID-19 characteristics and outcomes and to evaluate the association between IBD phenotypes, infection outcomes and immunomodulatory therapies. METHODS: In this multi-center study, we prospectively followed IBD patients with proven COVID-19. De-identified data from medical charts were collected including age, gender, IBD type, IBD clinical activity, IBD treatments, comorbidities, symptoms and outcomes of COVID-19. A multivariable regression model was used to examine the effect of immunosuppressant drugs on the risk of infection by COVID-19 and the outcomes. RESULTS: Of 144 IBD patients, 104 (72%) were CD and 40 (28%) were UC. Mean age was 32.2 ± 12.6 years. No mortalities were reported. In total, 94 patients (65.3%) received biologic therapy. Of them, 51 (54%) at escalated doses, 10 (11%) in combination with immunomodulators and 9 (10%) with concomitant corticosteroids. Disease location, behavior and activity did not correlate with the severity of COVID-19. Biologics as monotherapy or with immunomodulators or corticosteroids were not associated with more severe infection. On the contrary, patients receiving biologics had significantly milder infection course (p = 0.001) and were less likely to be hospitalized (p = 0.001). Treatment was postponed in 34.7% of patients until recovery from COVID-19, without consequent exacerbation. CONCLUSION: We did not witness aggravated COVID-19 outcomes in patients with IBD. Patients treated with biologics had a favorable outcome.

Does early corticosteroid therapy affect prognosis in IBD patients hospitalized with Clostridioides difficile infection?

BACKGROUND: Corticosteroids (CS) therapy to Clostridioides difficile infection (CDI) in inflammatory bowel disease (IBD) flares may worsen CDI outcomes. AIM: Assess the impact of early CS exposure on outcomes of IBD patients diagnosed with CDI. METHODS: Retrospective study of IBD patients admitted with first-time CDI between 2002 and 2018. Comparisons were made based on CS exposure 48 h from admission. Patients were further subdivided to 5 groups based on CS-antibiotics temporal exposure. The primary outcome was all-cause mortality or colectomy within 3 months. Secondary outcomes were colectomy and mortality rates at 1 year, length of stay, readmissions, bacteremia, and diarrhea improvement by day 7/discharge. Cox proportional hazard model and Kaplan-Meier curves were used to assess the effects on survival. Logistic and ordinal regressions were used to assess primary and secondary outcomes. RESULTS: One hundred thirteen patients (64 CD, 46 UC, and 3 IBDU) were included, 82 (72.5%) received early CS. At baseline, CRP was significantly lower and albumin was higher in the group not exposed to early CS. At 3 months, 4 (4.8%) patients required colectomy and 6 (5.8%) died (p = NS). Length of stay was significantly reduced among patients not exposed to early CS. All other endpoints were not associated with CS exposure. In subgroup analysis, the primary outcome was not significantly different among the sub-groups. Mortality rate at 1 year was significantly lower in patients who did not receive antibiotics for CDI. CONCLUSION: Early CS therapy in IBD patients hospitalized with CDI is not associated with worse clinical outcomes. However, additional prospective research is required.

[COMPARISON OF QUALITY OF COLONOSCOPY IN AN ACADEMIC HOSPITAL VS. A COMMUNITY HOSPITAL OUTPATIENT SERVICE].

BACKGROUND: Extensive use of colonoscopy in hospitals and community clinics has highlighted the need to assess the quality of the procedures in order to reduce costs and increase their efficiency. OBJECTIVES: This institutional review board (IRB)-approved study aimed to compare the quality of colonoscopies performed in a teaching hospital to those performed at a community health service. METHODS: Demographic information, time of procedure, indications, quality of bowel preparation, premedication, depth of examination, polyp detection, biopsies and followup recommendations were retrospectively obtained from 700 colonoscopy reports from the Rambam Healthcare Campus and 824 colonoscopy reports from Elisha. This data was compared to relevant literature benchmarks. RESULTS: There was no statistically significant difference between the hospital vs. community endoscopy services in the patients' demographics, depth of examination (92.4% vs. 94.1% complete), polyp detection rate (29.1% vs. 26.8%) and biopsies in patients with diarrhea (75% vs. 67%). Indications for colonoscopy differed: gastrointestinal bleeding was more common at the hospital, while screening was more common in the community. Premedication varied: more fentanyl and dormicum and less propofol were used in the community. Good bowel preparation was more frequent in the community (68.8% vs. 47.2% in hospital, p<0.0001). Follow-up recommendations were documented more often in the community (74% vs. 53% in hospital, p<0.0001). The range for many quality indicators (QIs) varied greatly amongst physicians. CONCLUSIONS: Remediation of weaker areas seems feasible through upgrading electronic medical records and increasing awareness of quality indicators (Qis). Colonoscopies performed in both hospital and community services were of good quality compared to the relevant literature, with significant variations in some QIs.

[Quality indicators in colonoscopy].

BACKGROUND: Extensive use of colonoscopy has highlighted the need to assess the quality of the procedures in order to reduce costs and increase efficiency. AIMS: (1) To assess quality indicators of colonoscopies performed by specialist physicians in Rambam HeaLth Care Campus; (2) To improve the quality of colonoscopies using the data collected. METHODS: Data was collected retrospectively from reports of 700 colonoscopies performed by 7 gastroenterology specialists in Rambam Health Care Campus. The data collected was compared to relevant Literature benchmarks for accepted quality indicators. RESULTS: A total of 95.3% of procedures had appropriate indications. Good or excellent bowel preparation was documented for 57.4% of procedures with a range for individual physicians from 18.2%-84%. Completion rate was 92.4% (range 89.9%-97%). Overall polyp detection rate was 29.1% (range 17%-45%). Polyp detection rate in screening colonoscopies was 13.2% for women and 26.1% for men. Biopsies were taken in 90.3% of colonoscopies performed for inflammatory bowel disease (IBD) follow-up and in 75% of colonoscopies performed in patients with chronic diarrhea. Follow-up recommendations were noted in 82.6% of procedures with any indication for follow-up (range 70%-92.5%). CONCLUSIONS: Colonoscopies are performed in Rambam Health Care Campus in an effective manner with regard to completion rate and polyp detection. High rates of intermediate or poor bowel preparation, suboptimal rates of taking biopsies and making follow-up recommendations were noted. Significant variations among participating physicians were noted. Conclusions led to operative changes in practice, including improving computerized reports, standardizing assessments of preparation and initiating a continuous quality improvement program.