Characteristics and Treatment Outcomes of Small-bowel Angioectasia in Systemic Sclerosis Patients: A Retrospective Observational Study

Objective Systemic sclerosis (SSc) is defined as an autoimmune disease presenting with fibrosis of various organs and vascular endothelial damage. Vascular lesions, including small-bowel angioectasias, are also frequently detected in SSc patients. Polidocanol injection (PDI) is a safe and effective hemostatic treatment for gastrointestinal bleeding. We evaluated the outcomes of PDI for small-bowel angioectasia in SSc patients. Methods We retrospectively evaluated 65 consecutive SSc patients (61 women; mean age, 64.3 years old) who underwent capsule endoscopy (CE) and/or double-balloon endoscopy at Hiroshima University Hospital between April 2012 and December 2019. Patients Patients were stratified according to the presence of small-bowel angioectasia. Among patients who underwent CE during the same period, those with small-bowel angioectasia without concomitant diseases were compared with SSc patients with small-bowel angioectasia. Clinical and endoscopic characteristics, treatment outcomes, and the incidence of metachronous small-bowel angioectasia after PDI were evaluated. Results SSc patients with small-bowel angioectasia exhibited significantly lower hemoglobin levels and a significantly higher incidence of skin telangiectasia than those without small-bowel angioectasia. On a multivariate analysis of the presence of small-bowel angioectasia, anemia and skin telangiectasia were significant independent factors. SSc patients with small-bowel angioectasia included a higher proportion of women and exhibited a significantly higher incidence of metachronous small-bowel angioectasia than X. The characteristics of small-bowel angioectasia and outcomes of PDI were not significantly different between the two groups. No post-treatment rebleeding cases or adverse events were noted. Conclusion CE should be performed for SSc patients with anemia and/or skin telangiectasia. PDI is effective for SSc patients with small-bowel angioectasia.

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

Background and Objectives: Device-assisted enteroscopy (DAE) allows deep exploration of the small bowel and combines diagnostic and therapeutic capacities. Suspected mid-gastrointestinal bleeding is the most frequent indication for DAE, and vascular lesions, particularly angioectasia, are the most common etiology. Nevertheless, the diagnostic yield of DAE for the detection of these lesions is suboptimal. Deep learning algorithms have shown great potential for automatic detection of lesions in endoscopy. We aimed to develop an artificial intelligence (AI) model for the automatic detection of angioectasia DAE images. Materials and Methods: A convolutional neural network (CNN) was developed using DAE images. Each frame was labeled as normal/mucosa or angioectasia. The image dataset was split for the constitution of training and validation datasets. The latter was used for assessing the performance of the CNN. Results: A total of 72 DAE exams were included, and 6740 images were extracted (5345 of normal mucosa and 1395 of angioectasia). The model had a sensitivity of 88.5%, a specificity of 97.1% and an AUC of 0.988. The image processing speed was 6.4 ms/frame. Conclusions: The application of AI to DAE may have a significant impact on the management of patients with suspected mid-gastrointestinal bleeding.

Risk of Rebleeding in Patients with Small Bowel Vascular Lesions

Objective With recent advances in endoscopic modalities, small bowel vascular lesions (SBVLs) are often now detected in patients with gastrointestinal bleeding. Given the high invasiveness of endoscopic treatment, it is important to select patients at high risk for bleeding. To assess the risk of rebleeding in patients with SBVLs as a systemic disease rather than a gastrointestinal disease in relation to their general health. Methods We retrospectively analyzed the clinical data of 55 patients with SBVLs among patients with obscure gastrointestinal bleeding. The possible association between the clinical findings and the updated Charlson comorbidity index with rebleeding was evaluated. Results Gastrointestinal rebleeding occurred in 20 patients (36.4%) during the follow-up period. The presence of multiple comorbidities as indicated by an updated Charlson comorbidity index of ≥4 was a risk factor for rebleeding (hazard ratio, 3.64; p=0.004). Other risk factors were arteriosclerosis of the superior mesenteric artery and multiple SBVLs. Endoscopic hemostasis and the discontinuation of antithrombotic medications were not significantly associated with rebleeding. Patients with a high updated Charlson comorbidity index had a high risk of death of causes other than gastrointestinal rebleeding. Conclusion Gastrointestinal rebleeding is not a rare condition among patients with SBVLs. Patients with poor general health may therefore have a higher risk of rebleeding.

Initial endoscopic intervention is not associated with reduced risk of recurrent gastrointestinal bleeding in left ventricular assist device patients

Background

Left ventricular assist devices (LVADs) are increasingly used for mechanical support of end-stage heart failure. Gastrointestinal bleeding (GIB) confers a significant morbidity in LVAD patients, with rates of up to 30% at 5 years. We assessed predictors of index and recurrent GIB (rGIB) in LVAD patients to risk stratify patients and evaluate if endoscopic approach and intervention at index GIB impacted rGIB.

Methods

A retrospective chart review of all LVAD patients at our institution from 01/01/2006 to 31/10/2016 was completed. Predictors for index and recurrent GIB were analyzed. Multivariate logistic regression analysis was created using only statistically significant dependent variables and adjusted for demographic variables.

Results

A total of 77/214 (36%) patients developed GIB, and 38/214 (17.8%) developed rGIB. Destination therapy (P=0.01), longer duration of LVAD (P=0.03), and low albumin (<3.5 g/dL) (P<0.001) were associated with increased risk of index GIB. Charlson Comorbidity Index, heart failure etiology, and Medicare were predictors of index GIB on univariate analysis, but this was not seen on multivariate analysis. Performing an endoscopy with/without intervention, non- angioectasia lesions, and location of bleeding were not statistically significant predictors of rGIB. Longer duration of hospitalization appeared to be protective for rGIB on univariate analysis.

Conclusions

Index endoscopy and intervention is not associated with reduced risk of rGIB in LVAD patients. Several independent factors are associated with the risk of index GIB. Albumin is a potentially modifiable risk factor, and likely contributes to bleeding through poor nutrition. It is a surrogate marker for systemic illness, and may have pharmacologic implications.

Prevalence of Angiodysplasia Detected in Upper Gastrointestinal Endoscopic Examinations

Background This study was performed to examine the prevalence of asymptomatic angiodysplasia detected in upper gastrointestinal endoscopic examinations and of hereditary hemorrhagic telangiectasia (HHT) suspected cases. Methodology The study participants were 5,034 individuals (3,206 males, 1,828 females; mean age 53.5 ± 9.8 years) who underwent an upper gastrointestinal endoscopic examination as part of a medical check-up. The presence of angiodysplasia was examined endoscopically from the pharynx to duodenal second portion. HHT suspected cases were diagnosed based on the presence of both upper gastrointestinal angiodysplasia and recurrent nasal bleeding episodes occurring in the subject as well as a first-degree relative. Results Angiodysplasia was endoscopically detected in 494 (9.8%) of the 5,061 subjects. Those with angiodysplasia lesions in the pharynx, larynx, esophagus, stomach, and duodenum numbered 44, 4, 155, 322, and 12, respectively. None had symptoms of upper gastrointestinal bleeding or severe anemia. Subjects with angiodysplasia showed significant male predominance and were significantly older than those without. A total of 11 (0.2%) were diagnosed as HHT suspected cases by the presence of upper gastrointestinal angiodysplasia and recurrent epistaxis episodes from childhood in the subject as well as a first-degree relative. Conclusions Asymptomatic angiodysplasia was detected in 9.8% of the subjects who underwent screening upper gastrointestinal endoscopic examinations.

Clinical Impact of Small Bowel Capsule Endoscopy in Obscure Gastrointestinal Bleeding

Background and objectives: The most frequent indications for small bowel capsule endoscopy (SBCE) are obscure gastrointestinal bleeding (OGIB) and iron deficiency anemia (IDA). The aim of this study was to evaluate the diagnostic yield (DY) of SBCE in overt and occult OGIB, as well as its impact on the clinical outcome. Materials and Methods: This study retrospectively included all cases of OGIB investigated by SBCE in a tertiary care referral center, between 1st January 2016 and 31st December 2018. OGIB was defined by overt or occult gastrointestinal bleeding, with negative upper and lower endoscopy. Occult gastrointestinal bleeding was either proved by a fecal test or presumptively incriminated as a cause for IDA. DY was defined as the detection rate for what were thought to be clinically significant findings. DYs for overt and occult bleeding were assessed and compared. Gender, age, hemoglobin levels, NSAID consumption and the use of anticoagulants were recorded. Following SBCE results, individual therapeutic decisions were made, and follow-up data were recorded. Results: 224 SBCE examinations were performed for OGIB, of which 148 were for overt OGIB, and 76 for unexplained IDA. Positive findings were found in 139 patients, resulting in an overall DY for OGIB of 62%, higher in overt OGIB (75%) compared to IDA (37%). The most frequent findings were small bowel angioectasias (62.2% in overt OGIB and 78.5% in IDA). On multivariate logistic regression analysis, only hemoglobin level <10 g/dL and anticoagulants were the variables independently associated with positive findings. All patients received medical, endoscopic or surgical treatment and had good clinical outcome during follow-up. Conclusion: SBCE has a high diagnostic yield and a positive impact on management of patients with OGIB.

Artificial intelligence using a convolutional neural network for automatic detection of small-bowel angioectasia in capsule endoscopy images

BACKGROUND AND AIM

Although small-bowel angioectasia is reported as the most common cause of bleeding in patients and frequently diagnosed by capsule endoscopy (CE) in patients with obscure gastrointestinal bleeding, a computer-aided detection method has not been established. We developed an artificial intelligence system with deep learning that can automatically detect small-bowel angioectasia in CE images.

METHODS

We trained a deep convolutional neural network (CNN) system based on Single Shot Multibox Detector using 2237 CE images of angioectasia. We assessed its diagnostic accuracy by calculating the area under the receiver operating characteristic curve (ROC-AUC), sensitivity, specificity, positive predictive value, and negative predictive value using an independent test set of 10 488 small-bowel images, including 488 images of small-bowel angioectasia.

RESULTS

The AUC to detect angioectasia was 0.998. Sensitivity, specificity, positive predictive value, and negative predictive value of CNN were 98.8%, 98.4%, 75.4%, and 99.9%, respectively, at a cut-off value of 0.36 for the probability score.

CONCLUSIONS

We developed and validated a new system based on CNN to automatically detect angioectasia in CE images. This may be well applicable to daily clinical practice to reduce the burden of physicians as well as to reduce oversight.

Repeat capsule endoscopy in suspected gastrointestinal bleeding

Objectives: This study aims to review the utility of repeat capsule endoscopy (CE) with on-going concern of small bowel (SB) bleeding following initial SB investigation with CE. Materials and methods: A specifically designed database of CE examinations performed over 13 years, with hospital records, was retrospectively interrogated for patients undergoing multiple CEs to investigate iron deficiency anaemia (IDA) or suspected SB bleeding. Results: 1335/2276 (58.7%) of CEs were performed to investigate IDA or SB bleeding; 92 were repeat CEs carried out for ongoing clinical concern. The median time interval between initial and repeat CE procedures was 466.5 (range 1-3066) days. Twenty-four patients had initially normal CE; on repeat examination, abnormalities were detected in 11/24 (45.8%). 3/21 (14.2%) of patients with angioectasia on first CE had alternative causes for IDA or GI bleeding detected on repeat CE. Six patients with active bleeding, without an identifiable source on initial CE, undergoing repeat CE had a cause isolated in 5/6 (83.3%). Changing CE device did not affect diagnostic yield (DY) compared to repeat CE using the same device (27.5% to 26.8%). Conclusions: It is known that CE can miss clinically relevant and serious lesions. Our results suggest that patients with an initially negative or inconclusive CE frequently have a cause of SB bleeding detected on repeat CE. The DY of repeat CE is highest in those with bleeding on their initial CE (83.3%) and lower in those with initially normal examinations (45.8%) or when an alternative cause, such as angioectasia is seen (14.2%).

Mapping the distribution of small bowel angioectasias

Background: Angioectasias are a prominent cause of small bowel (SB) bleeding frequently identified during capsule endoscopy (CE). Subsequent management depends upon grade/severity and location. There is increasing evidence that the location of SB angioectasias is not random. We aimed to map the distribution of SB angioectasias, and assess whether this impacted clinical outcomes. Materials and methods: Retrospective study examining CEs performed over a 10-year period at a tertiary referral centre. Information regarding number, location, and Saurin classification (P0-2) of SB angioectasias was collected. Clinically significant angioectasias (P1/P2) and active SB bleeding were analysed further. Outcomes of patients with P2 angioectasias or active SB bleeding were recorded. Results: 164 SBCE examinations reported angioectasias. 554 P1-2 angioectasias and active bleeds were seen, 435 (78.52%) within the first tertile of SB transit time (SBTT). 277 (50%) angioectasias were identified within the first 10% of SBTT. 40/75 (53.3%) patients with >1 P2 angioectasia and/or active bleed were referred for intervention. Of initial interventions, 24 patients underwent upper GI endoscopy; 13 underwent double balloon enteroscopy (DBE). 9/37(24.3%) had no identifiable angioectasias on endoscopy. Of those receiving ablative therapy, 20/28 (71.4%) re-presented with iron-deficiency anaemia or bleeding. In this group, average angioectasia position was 15.6% of SBTT, compared with 7.9% in those who did not re-represent (p = 0.344). Patients who re-presented had an average 1.6 additional P1 angioectasias, compared with 7.6 amongst those who did not return (p = 0.017). Conclusions: Clinically significant angioectasias are overwhelmingly located within the proximal SB. The majority are within reach of conventional endoscopy. However, AEs are often multiple and many patients re-present following intervention.

Efficacy of video capsule endoscopy with flexible spectral imaging color enhancement at setting 3 for differential diagnosis of red spots in the small bowel

BACKGROUND

Red spots on the small bowel mucosa are observed in patients with angioectasia and enteritis. The present study investigated the effectiveness of capsule endoscopy (CE)-flexible spectral imaging color enhancement (FICE) as a method for differential diagnosis of the two conditions.

PATIENTS AND METHODS

The subjects were 30 patients who underwent CE and double-balloon endoscopy at Dokkyo Medical University Hospital between February 2007 and January 2013. Of these 30 patients, those diagnosed with angioectasia were assigned to Group A (n = 13) and those diagnosed with enteritis were assigned to Group E (n = 17).

RESULTS

Using FICE at setting 3 and comparing the color intensity of the red spots on a four-step scale (0-3), no statistically significant (P = 0.712) difference was found between the twogroups (Group A: 2.69 ± 0.48, Group E: 2.76 ± 0.56). Subjects were considered to show a positive blue sign when areas of blue were observed against the yellow-green background and surrounding the red spots. A comparison of the ratio of positive blue sign for both groups (Group A: 15.4% ± 37.6%, Group E: 94.1% ± 24.2%) showed a statistically significant increase in the ratio in Group E (P < 0.001).

CONCLUSION

The results of the present study suggest that blue sign may be effective in the differential diagnosis of angioectasia and enteritis in patients with red spots.