Introduction

The mainstay of treatment of Zenker’s diverticulum is cricopharyngeal myotomy. Although flexible endoscopic septotomy is widely implemented, complete myotomy is difficult to assess resulting in recurrence rates of 11%. On the other hand, ZD peroral endoscopic myotomy allows complete myotomy visual confirmation, at the expense of procedure length and complexity. To overcome these limitations, a hybrid technique that allies FES simplicity and fastness to zPOEM efficacy is proposed: 1-septum isolation with overtube; 2-standard FES until middle of the diverticulum; 3-muscular septum isolation by zPOEM until the base of the diverticulum; 4-complete myotomy; 5-residual mucosal flaps section; 6-mucosotomy closure with TTS clips. We aim to demonstrate the feasibility, effectiveness and safety of the hybrid zPOEM technique for the treatment of ZD.

Aims & Methods

A retrospective analysis including patients with ZD treated by hybrid zPOEM procedure from April 2021 to February 2023 was made. Technical success, early clinical success (dysphagia score ≤ 1), adverse events and recurrence rates were evaluated.

Results

11 patients (male 54.5%, mean age 72.9 years) underwent hybrid zPOEM procedure for treatment of ZD (mean size 23.18mm, range 15-30mm). The procedure was technically successful in all patients, with a mean procedure time of 21.6 minutes. Early clinical success was achieved in all patients, although 1 patient maintained occasional regurgitation due to incomplete mucosal flaps section. Mean symptoms scores improved from baseline for dysphagia (1.5 vs 0), regurgitation (1.5 vs 0.1), halitosis (0.5 vs 0), cough (0.5 vs 0) and hoarseness (0.3 vs 0). During a mean follow-up time of 10 months, no recurrence was recorded. No intra- or post-procedure AE were recorded.

Conclusion

Hybrid zPOEM technique is a fast, safe and effective procedure, where, by combining classic FES and zPOEM, one can have the best of both techniques. This procedure should be considered as a first-line therapeutic option in third-space-endoscopy experienced centers.

References

Zhang LY, Nieto J, Ngamruengphong S, Repici A, Khashab MA. Zenker’s diverticulum: advancing beyond the tunnel. VideoGIE. 2021;6(12):562–7
Lupu A, Lafeuille P, Yzet C, Benech N, Jacques J, Rivory J, et al. Hybrid peroral endoscopic myotomy for large Zenker’s diverticulum. Endoscopy. 2022;54:E862–3.
Krishnan A, Ichkhanian Y, Runge TM, Khashab MA. Hybrid endoscopic approach for submucosal tunneling septum division for Zenker s diverticulum. Endoscopy. 2020;52(12):E457–8.

Clinical Case Summary

Familial intrahepatic cholestasis is a heterogeneous group of genetic diseases with autosomal recessive transmission. BSEP (Bile-Salt Export Pump) is the main bile acid export pump in hepatocytes. Mutations in the gene encoding BSEP, ABCB11, are associated with heterogeneous clinical phenotypes ranging from diseases with a benign course to severe forms requiring liver transplantation. Here we report the case of a 17-year-old girl admitted to our Clinic because of severe jaundice and itching. She reported a similar episode 2 years earlier with spontaneous recovery. Family history is positive for cholelithiasis. On admission, laboratory tests showed: total and direct bilirubin values of 24.5 mg/dl and 18.9 mg/dl, AST 307 IU/L and ALT 238 IU/L, respectively. GammaGT was normal. Viral, autoimmune, metabolic causes, and biliary obstruction were excluded. Liver biopsy showed a picture of hepatocellular and intracanalicular cholestasis with cholestatic rosettes, inflammatory activity, and mild portal and pericellular fibrosis. Immunohistochemical staining for BSEP showed only weak diffuse expression. Genetic testing documented compound heterozygosity of the ABCB11 gene with the variants c.1460G>A - p(Arg487His) of paternal origin and c2599C>T -(Gln867*) of maternal origin. Genetic testing of relatives is also ongoing. The patient was treated with ursodesoxycholic acid, cholestyramine and cetirizine for 4 months with disappearance of jaundice and pruritus and normalization of bilirubin levels. Follow-up at 1 year was free of events without therapy. This is the first time that the c2599C>T -(Gln867*) variant has been described in a patient with familial intrahepatic cholestasis. Application of the "temporal test" will allow this new variant to be attributed to the BRIC2 form rather than PFIC2.

Introduction

The use of artificial intelligence (AI) systems for decision support has recently gained great popularity in the medicine.¹ However, recent studies have shown possible limitations emerging from the interaction between humans and AI. Among these, the term “automation bias (AB)” refers to human errors deriving from over-relying on AI’s false alarms such that the human changes a correct initial interpretation.² AB is poorly investigated in the medical field and was never tested in the gastroenterological setting.

Aims & Methods

The aim of the study was to investigate the impact of AI on human diagnostic performance in gastrointestinal endoscopy, including AB.
Ninety high-quality endoscopic videoclips (16 seconds) extracted from small bowel (SB) capsule endoscopy (N=60) and proctosigmoidoscopy (N=30) were edited with the addition of a mock AI system designed with diagnostic accuracy, sensitivity and specificity of 80%, 86% and 75%. The ground truth was settled on the agreement of 9 established experts about the presence of SB lesions with significant hemorrhagic potential according to the Saurin classification (30 videoclips), inflammatory lesions relevant for the diagnosis of SB Crohn's disease according to the Lewis score (30 videoclips) and assessing the Ulcerative Colitis (UC) Endoscopic Index of Severity (30 videos). The videoclips were randomly divided into three sessions and submitted around Europe to fully trained endoscopist, trainees and endoscopic technicians. Participants were instructed to the accuracy measures of AI annotations and scored each videoclip first without, then with AI support. Participants’ performances with and without AI were calculated. Subgroup analyses were made after stratification by participants’ experience level in each endoscopic setting and test performances.

Results

A total of 12.660 videoclips (both with and without AI) were visualized in 422 sessions (182, 118 and 122 participants completed the first, second and third session, respectively). A strong and significant difference between the respondents' performance (N=281) when they were unaided by AI (average accuracy (M)=0.78, [0.77, 0.79] and when they were supported by the AI (M=0.81, [0.80, 0.82], paired t-test, t(276)=11.2, p<0.001) was found. Size effect and the evidence in favour of a significant positive effect of AI were large, 0.67 (Cohen's D) and very large (Bayes Factor>100), respectively. Interestingly, no significant difference between trainees and specialists both in regard to their performance, either unaided, M=0.77 [0.74, 0.79] vs M=0.78, [0.77, 0.79] or aided M=0.80 [0.78, 0.82] vs M=0.81 [0.80, 0.82] and their accuracy improvement (M=0.03, [0.02, 0.05] vs M=0.03, [0.02, 0.04] (unaided t-value=-0.89, p=0.37; aided t-value=-0.69, p=0.49, difference t-value=0.54, p=0.59) were found. A strong leveller effect emerged, with low-performers improving their accuracy much more than top-performers (average improvement 5%, [0.04, 0.06] vs 1%, [0.00, 0.02], paired T test, t=6.53, p<0.001). Nine percent of the final decisions involved disregarding correct AI advice in favour of incorrect human judgment, while AB occurred in 2% of cases.

Conclusion

In this study, the application of AI to assess SB bleeding, SB inflammatory lesions, and UC activity brings significant improvement in diagnostic accuracy, with the benefit appearing to be greater in the low-performers. However, in rare cases, AI may induce diagnostic errors due to AB. Future studies directly evaluating the impact of AI in real-life clinical settings are needed to confirm these data.

References

1. Cabitza F, Campagner A, Angius R, Natali C, Reverberi C. 2023. AI Shall Have No Dominion: on How to Measure Technology Dominance in AI-supported Human decision-making. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 354, 1–20. https://doi.org/10.1145/3544548.3581095
2. Reverberi, C., Rigon, T., Solari, A. et al. Experimental evidence of effective human–AI collaboration in medical decision-making. Sci Rep 12, 14952 (2022). https://doi.org/10.1038/s41598-022-18751-2