Introduction

Crohn’s disease (CD) is a chronic inflammatory disorder of the gastrointestinal tract often complicated by intestinal strictures. Accurate differentiation between inflammatory and fibrotic strictures is essential for guiding therapeutic strategies but remains challenging with current diagnostic tools. The capability of greyscale intestinal ultrasound (IUS) alone for characterizing inflammation versus fibrosis in CD strictures is not accurate enough to be used in clinical practice. This study investigates the diagnostic utility of advanced ultrasound techniques, including shear wave elastography (SWE), MV-Flow Doppler, and the Limberg score (LS), in the evaluation of strictures in patients with CD.

Aims & Methods

A prospective cross-sectional study enrolled 15 consecutive patients with ileal and ileocolonic CD scheduled for surgery due to symptomatic strictures. Each patient underwent intestinal ultrasound, including SWE, MV-Flow Doppler imaging, and LS assessment of the stenotic segment, within one week before surgery. Histopathological analysis of resected bowel specimens was then performed to grade inflammation and fibrosis according to a semiquantitative scoring system. Statistical analysis evaluated the correlation between ultrasound parameters and histological findings.

Results

SWE reliably differentiated fibrotic grades, with mean stiffness values significantly increasing from mild to severe fibrosis (P = 0.014). A cutoff of 24.85 kPa distinguished mild from moderate/severe fibrosis with 83.33% sensitivity and 88.89% specificity (AUC = 0.944). Conversely, SWE did not significantly distinguish between grades of inflammation (P = 0.643). MV-Flow Doppler values strongly correlated with histological inflammation grades (P = 0.007), with mean microvascular percentages increasing from 8.1% (mild inflammation) to 36.2% (severe inflammation). The LS also demonstrated high diagnostic accuracy for severe inflammation (AUC = 0.910, sensitivity 80.0%, specificity 90.0%).

Conclusion

This study underscores the complementary roles of SWE, MV-Flow, and LS in characterizing strictures in CD. SWE excels in assessing fibrosis, while MV-Flow and LS provide sensitive measures of inflammation. The integration of these modalities with conventional greyscale IUS offers a comprehensive and non-invasive approach to optimize diagnosis and management of CD strictures. Future research should validate these findings in larger, multicenter studies and explore their longitudinal applications.

Clinical Case Summary

A 24-year-old male presented with jaundice and mild vertigo after a 10-day prodrome (asthenia, nausea, headache, fever). Ibuprofen (1200 mg/d) was taken for these symptoms only during the first 5 days. Labs revealed acute hepatocellular injury and elevated cholestasis (AST 215, ALT 862, FA 134, GGT 126 IU/L), marked mixed hyperbilirubinemia (Total 13.5 mg/dL, Direct 7.58 mg/dL) and coagulopathy (INR 1.59). Ultrasound showed hepatosplenomegaly. Viral hepatitis (HAV/HBV/HCV/CMV) and autoimmune/metabolic causes were excluded. Epstein-Barr Virus (EBV) serology showed low-titer positive VCA IgM but negative VCA IgG, EBNA IgG, and serum EBV DNA PCR, indicating recent non-active infection. Given ibuprofen timing and high RUCAM score, drug-induced liver injury (DILI) with a hepatocellular pattern was suspected. Liver biopsy confirmed acute hepatitis with lymphomonocytic infiltrate, necrosis and canalicular cholestasis. Despite improving liver function tests post-ibuprofen cessation, he developed worsening vertigo, severe ataxia, nausea, vomiting, hypophonia, necessitating nasogastric feeding/bed confinement. Cerebrospinal fluid (CSF) showed mild mononuclear pleocytosis (16 cells/mm³); a multiplex PCR pathogen panel (including EBV) was negative. Brain MRI/EEG were normal. Post-infectious EBV acute cerebellar ataxia was diagnosed concurrently with DILI, based on timing post-recent EBV, exclusion of active neurological infection (negative CSF PCR, normal imaging), mild pleocytosis, and supported by later IgG seroconversion. IV methylprednisolone treatment, chosen for clinical severity, led to significant neurological improvement within days and eventual recovery after physiotherapy. This case highlights the significant challenges of diagnosis and management of concomitant DILI and recent EBV infection with neurological sequelae, requiring careful differentiation of liver damage patterns (hepatocellular DILI vs cholestatic EBV) and optimal management of neurological symptoms.

References

Illustrative Material References:
- Liver biopsy histology slides (highlighting lymphomonocytic infiltrate, necrosis, and canalicular cholestasis characteristic of DILI).
- Table/Graph showing serial Liver Function Tests (AST, ALT, Bilirubin) over time, depicting injury peak and recovery trend.
- Table summarizing sequential Epstein-Barr Virus (EBV) serology results (VCA IgM, VCA IgG, EBNA IgG) demonstrating seroconversion.
- Table summarizing Cerebrospinal fluid (CSF) analysis results (cell count, protein, glucose, negative multiplex PCR).
- Representative Brain MRI images (axial/sagittal views) confirming absence of structural lesions or encephalitis signs.

Introduction

Among immune-related adverse events (irAEs) caused by immune checkpoint inhibitors (ICIs), gastrointestinal irAEs (GI-irAEs) are relatively rare, and their risk factors and prognostic implications remain unclear.

Aims & Methods

We retrospectively analyzed 1,104 patients who initiated ICI therapy at our institution between January 2016 and December 2022 and for whom survival data were available. GI-irAEs were defined as colitis with an increase of ≥3 bowel movements/day from baseline in the absence of other causes, or symptomatic gastritis confirmed histologically. Risk factors and prognostic impact of GI-irAEs were evaluated.

Results

The median duration of ICI therapy was 107 days. The cohort included 754 males (68%) with a median age of 69 years. The primary tumor types were lung cancer (32%), gastrointestinal cancers (19%), urothelial carcinoma (13%), head and neck cancer (13%), and melanoma (11%). The overall response rate was 27.8%, and the disease control rate was 49.0%. irAEs of any grade occurred in 310 patients (28%), and GI-irAEs were observed in 30 patients (2.7%). In univariate logistic regression analysis, use of anti-CTLA-4 antibody, combination ICI therapy, a prognostic nutritional index (PNI) ≥ 40, and platelet-to-lymphocyte ratio (PLR) ≥ 1.8 were associated with an increased risk of GI-irAEs. In multivariate analysis, only anti-CTLA-4 antibody use remained a significant risk factor (odds ratio: 9.2; 95% CI: 1.9–45). Kaplan–Meier analysis revealed that patients with GI-irAEs had significantly longer overall survival (OS) compared to those without irAEs in the overall cohort (median OS: 22.9 vs. 12.6 months, P < 0.0001). However, this difference was not observed in landmark analyses at 4 and 8 weeks post-treatment. Subgroup analysis based on PNI showed that in patients with PNI ≥ 40, those with GI-irAEs had significantly longer OS than those without irAEs (median not reached vs. 19.3 months, P = 0.0003). In contrast, in patients with PNI < 40, GI-irAE cases tended to have shorter OS than non-irAE cases (8.2 vs. 9.3 months). This trend was consistent in landmark analyses at 4 and 8 weeks.

Conclusion

The impact of GI-irAEs on prognosis appears to differ depending on the patient’s nutritional status. Particular caution is warranted for patients in poor general condition receiving ICIs, especially those involving anti-CTLA-4 antibodies, as GI-irAEs may serve as a poor prognostic factor in this population.

Introduction

Artificial intelligence (AI) characterization (CADx) systems for colonic polyps exhibit high diagnostic accuracy. However, they may only support, not replace, clinical decision-making and little is known of this human-AI interaction – even less so with trainee endoscopists. This issue is difficult to explore, but data from a study investigating CADx-supported trainee endoscopists compared to AI-blinded experts could give insight.

Aims & Methods

This analysis draws on data from a prospective observational study comparing the diagnostic performance of CADx-supported trainee endoscopists (using GI Genius®, Medtronic) to expert endoscopists blinded to AI support. Two key scenarios were explored: (a) instances in which the CADx system produced a ‘no prediction’ output, and (b) cases where trainees actively overruled AI-generated diagnoses. These were assessed to examine the impact of AI absence and human-AI discordance on diagnostic accuracy.

Results

The baseline cohort included 11 trainees performing 225 colonoscopies, mean age 63.8 years (SD 12.7), 48.9% male patients. Baseline ADR was 57.8%. Of 630 resected lesions (median size 3 mm, IQR 2;4), 40.0% were in the rectosigmoid, and 53.6% were non-adenomatous. CADx failed to provide a prediction in 19.2% (n=121) of cases. These ‘no prediction’ polyps were smaller (median 3 mm, p=0.048) and more often located in the right colon (72% vs. 58%, p=0.005. In the absence of AI support, trainee diagnostic accuracy declined significantly by 12.8% (63.6% vs. 76.4%, p=0.007). Interestingly, expert endoscopists—despite being blinded to AI—also performed worse on these polyps (64.7% vs. 73.9%, p=0.045), suggesting an inherent difficulty in classifying these lesions.
Trainees overruled AI suggestion leading to discordant diagnoses in 9.0% (57/630) of polyps, comprised of 20 (35.1%) non-adenomatous, and 37 (64.9%) adenomatous lesions. Trainees incorrectly overruled AI in 59.6% (34/57), which mostly consisted of downgrading lesions to NICE 1. Discordant polyps did not differ in size (3 mm vs. 3 mm, p=0.413), but were more often located proximally (77.2% vs. 58.1%, p=0.005). The difference in false negative rate (FNR) between trainees and AI was 62.16% (81.07% vs. 18.92%, p<0.0001), demonstrating a risk of missed adenomas when trainees override AI. Blinded expert endoscopists achieved identical overall diagnostic accuracy in those polyps as the AI system (59.6%). However, their error profiles differed – In this subset, blinded experts and AI performed equally in overall accuracy (59.6%), although with differing error profiles: AI showed a numerically lower FNR (18.9% vs. 35.1%, Δ16.2%, p=0.17), offset by a higher false positive rate (80.0% vs. 50.0%).

Conclusion

CADx systems generate ‘no prediction’ outputs in a substantial proportion of polyps, significantly impairing trainee diagnostic performance. These cases may represent inherently more challenging lesions. Despite CADx’s high accuracy, trainees overrule AI in almost every tenth polyp, most often incorrectly downstaging polyps. Structured training on appropriate use of CADx, emphasizing both its capabilities and limitations, may enhance clinical effectiveness. Further research on human-AI interaction and trust is warranted, as these factors will be critical for successful integration of CADx into routine endoscopic practice.

Disclosure

The original study (AC-CADx) received technical support by Medtronic. Medtronic was not involved in the design of the study or analysis of the data, neither in the original study nor this exploratory analysis.