Clinical Case Summary

EUS-BD is an alternative therapeutic approach in case of unsuccessful biliary drainage by ERCP (1,2). Our aim is to report another possible indication of EUS-BD as a salvage treatment in a case of post-ERCP perforation around the papilla.
This is a case-report of a 79-years-old woman admitted for obstructive jaundice with bilirubin levels of 18 mg/dL. A MRI displayed marked dilation of intrahepatic bile ducts, gallbladder and choledochus (18-mm) until its distal part where and abrupt stop and a regular stricture was observed. An ERCP failed to cannulate the common bile duct. After a precut procedure, retroperitoneal extravasation of the contrast was observed. After consultation with the surgical team and fully information to the family of the patient about therapeutic alternatives, an EUS-BD was performed immediately after the ERCP as a therapeutic approach aiming to treat simultaneously the perforation and the obstructive jaundice without delay.
EUS-BD was performed according to the standardized technique with a transgastric approach. The intrahepatic bile duct was puncture with a 19-gauge needle. A 0.025” guide-wire was inserted and the fistula was created using a 6French cystostome with pure current. After exchanging the guide-wire for another of 0.035” and passing it to the duodenum, a 6-cm long, fully-covered metal stent was deployed at the stricture as antegrade fashion.
A further CT-scan displayed no collections with decreasing of the bile duct dilation. The clinical outcome of the patient was uneventful, being discharged one-week after the EUS-BD.
One month later, a scheduled pancreaticoduodenectomy was performed. The surgical specimen showed a 4-mm wide distal cholangiocarcinoma.
EUS-BD with fully-covered metal stenting was effective to both drainage and covering perforation site. EUS-BD could be deemed as another potential indication in selected cases as an immediate rescue therapy after ERCP adverse events such as perforation.

References

Nakai Y, Isayama H, Wang HP, Rerknimitr R, Khor C, Yasuda I, et al. International consensus statements for endoscopic management of distal biliary stricture. J Gastroenterol Hepatol. 2020;35(6):967-79.
Huh G, Park DH. EUS-guided transhepatic biliary drainage for next-generation ERCPists. Gastrointest Endosc. 2022;95(3):452-4.

Disclosure

Rafael Romero-Castro is consultant to Cook Medical since February 28th, 2023.

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

Introduction

Urgency is not an IBD Patient Reported Outcome (PRO) in the STRIDE II but it has been assessed at baseline and as an outcome measure in recent pivotal RCTs with newer biologicals and targeted synthetic small molecules in both Crohn’s disease CD) and ulcerative colitis (UC). However, although it is reasonable to assume that UC patients or CD patients with rectal involvement may complain for severe urgency, urgency has been assessed even in patients with Crohn’s ileitis (iCD).

Aims & Methods

The aim of this study was to assess whether urgency is reported by iCD patients with flares or quiescent disease in a Real-World (RW) setting. This prospective, pilot, RW study included CD patients with solely L1 phenotype. L1 location was documented by ileocolonoscopy, histology and, imaging (MRE, US, or capsule endoscopy). Patients with colonic and/or rectal disease, perianal involvement and complicated ileal disease were excluded. Patients were interviewed by office visits during disease flare [HBI>5, CRP <5mg/dl, faecal calprotectin (FC)>250μg/g faecal tissue and SES-CD for terminal ileum >3 if colonoscopy was performed within a month prior to the visit) and during clinical remission (HBI<5, CRP <5mf/dl and FC <200μg/g and ileal SES-CD=0, in a recent ileocolonoscopy). The presence of and severity of urgency was recorded by a Symptom Rating Score of 0-10 (absent to very severe). The presence and severity of abdominal pain, the number and consistency of stools, nocturnal stools, blood and/or mucus in the stools, and the feeling of inadequate evacuation were sought by a structed questionnaire.

Results

During a 15-month period, 85 iCD patients [45 males, median age (range) 33 (18-65) years, median (range) disease duration 9 (0.6-25) years] were enrolled in the study. Patients were receiving a wide range of treatments, including anti-TNF agents (n=35), ustekinumab (N=25), vedolizumab (N=5), azathioprine (n=10), budesonide (n=5) and mesalazine (n=15). Fifty patients had a flare, 65 were in remissionand 30 patients were interviewed sequentially in flare and remission of disease. All patients in disease flare reported abnormal classical PROs of CD. Moderate to severe urgency [median score 5, range 4-8] was reported by 5/50 (10%) patients with disease flare, 8/65 (12%) patients with disease remission and 2/30 (6.5%) patients who were interviewed during flare and remission of disease. 3/50 patients with urgency during a flare of CD did not report urgency during disease remission. Six of the 8 patients who were interviewed only with iCD in remission and reported urgency had concurrently typical Irritable Bowel Symptoms (IBS, abdominal pain relieved by defecation, alternating diarrhoea/constipation, inadequate bowel emptying).

Conclusion

This prospective, pilot, real-world study shows that the reliability of urgency as classical PRO in patients with iCD is questioned and raises doubts whether urgency should be included in the spectrum of PROs for patients with iCD both in RCTs and in RW studies. Validation of the terminology in different ethnic languages may also pose additional barriers in patient understanding and reporting the symptom in the presence of additional IBS-type symptoms. Large studies are needed to assess if urgency is present in patients with iCD and how reliably is reported especially in multinational RCTs.

Disclosure

Dr GJ Mantzaris: Research grants: AbbVie, Genesis, Merck Sharp & Dohme, Takeda; advisor/speaker: AbbVie, Aenorasis, Dr Falk, Ferring, Hospira, Janssen, Merck Sharp & Dohme, MYLAN, Pfizer, Takeda, Vianex.
Dr A Loukou: Nothing to declare

Clinical Case Summary

Secondary aortoenteric fistula (AEF) is an abnormal connection between the aorta and gastrointestinal tract (GT) resulting from reconstructive surgery for an abdominal aortic aneurysm (AAA), including open repair surgery and endovascular treatment. Despite the low incidence (1.6 to 4%) [1–4], it is life-threatening and has a high mortality rate (24 to 45.8%) [5–6].
A 79- year-old man reported to the emergency department of our hospital with overt bleeding from the stoma. The patient had a history of open Dacron graft repair for a ruptured AAA eight months previosly, which became complicated on the 5th postoperative day by sigmoid ishemia that required an emergency Hartmann procedure.
His blood pressure was 90/60 mmHg, heart rate 93/minute and hemoglobin level 7.5 g/dL.
The patient was admitted to our department. He underwent upper and lower endoscopy and no bleeding lesions were found. After endoscopy the patient presented another episode of overt bleeding from the stoma and we decided to perform Small-bowel capsule endoscopy (SBCE) which showed activ bleeding within the proximal ileum. The contrast-enhanced CT demostrated an aneurysm sac enlargement, a close proximity of the small bowel loops with the aneurysm sac in the pelvic cavity and a suspected leakage at the distal part of the aneurysm sac.
The patient was therefore admitted to the Surgical Derpatment and underwent an emergency endovascular repair of the leakage caused by distal detachment of the aorto-aortic prosthesis using a bifurcated stant graft. No more bleeding from the stoma occurred and the patient was discharged three days later with a diagnosis of distal aortic anastomosis leakage with aorto-ileal fistula.
The duplex ultrasound of the graft after one, three and six months showed no sign of endoleak.
This case shows that the SBCE may be useful in patients with history of recostructive surgery for AAA who manifest overt bleeding from the GT and no lesions are found in upper and lower endoscopy.

References

1.Wilson WR, Bower TC, Creager MA, Amin-Hanjani S, O’Gara PT, Lockhart PB, Darouiche RO, Ramlawi B, Derdeyn CP, Bolger AF, et al. Vascular Graft Infections, Mycotic Aneurysms, and Endovascular Infections: A Scientific Statement From the American Heart Association. Circulation. 2016;134(20): e412–60
2.Champion MC, Sullivan S, Coles J, Goldbach M, Watson WC. Aortoenteric fistula. Incidence, presentation recognition, and management. Ann Surg. 1982;195(3):314–7
3.Hallett JW Jr, Marshall DM, Petterson TM, Gray DT, Bower TC, Cherry KJ Jr, Gloviczki P, Pairolero PC. Graft-related complications after abdominal aortic aneurysm repair: reassurance from a 36-year population-based experience. J Vasc Surg. 1997;25(2):277–84. discussion 285-276
4.Chenu C, Marcheix B, Barcelo C, Rousseau H. Aorto-enteric fistula after endovascular abdominal aortic aneurysm repair: case report and review. Eur J Vasc Endovasc Surg. 2009;37(4):401–6
5.Malik MU, Ucbilek E, Sherwal AS. Critical gastrointestinal bleed due to secondary aortoenteric fistula. J Community Hosp Intern Med Perspect. 2015;5(6):29677
6.Gnus J, Ferenc S, Koscielna M, Paprocka-Borowicz M, Dawidczyk P, Dziewiszek M, Witkiewicz W. Secondary Aortoenteric Fistula After Abdominal Aortic Graft Implementation in Our Own Material. Adv Clin Exp Med. 2016;25(6):1265–71

Clinical Case Summary

The detection and management of overt gastrointestinal (GI) bleeding may be challenging, especially in case of limited resources, as during the COVID-19 pandemic. This case report shows how artificial intelligence (AI) technology applied to capsule endoscopy (CE) can contribute to this challenge.
In August 2020, a 80 year-old male patient was hospitalized for symptomatic iron-deficiency anemia three weeks after cardiovascular surgery and the start of dual antiplatelet therapy (DAPT). Since esophagogastroduodenoscopy (EGD) and ileocolonoscopy excluded any source of GI bleeding and the patient was stable, he was discharged. Two months later, the patient returned to the Emergency Department (ED) presenting with melena, and CE was recommended to rule out suspected small bowel bleeding.
Due to COVID-19, CE was not promptly scheduled. After two months, the patient was readmitted to the ED for persistent anemia (Hgb 7g/dL) and melena, without hemodynamic instability. Outpatient CE (Navicam SB system –AI tech embedded, Ankon, China) was performed two days later. The following morning the video was downloaded in 10 minutes and promptly reviewed in AI-assisted modality. After few seconds, active bleeding originating from the duodenum or proximal jejunum was detected. The patient was called back and an urgent EGD was performed after 4 hours from CE review. An actively bleeding Dieulafoy’s lesion was found in the third portion of the duodenum and treated with mechanical hemostasis. At 30-months follow-up, no episodes of re-bleeding occurred and Hgb was stable at 11 g/dL.
AI technology by Navicam SB system allows a rapid download of CE videos and offers a prompt detection of bleeding sources in patients with overt GI bleeding, leading to timely endoscopic management. This may potentially improve the long-term patients’ outcome and reduce the hospital stay, being particularly important in case of limited resources, as experienced during the COVID-19 pandemic.