Capsule endoscopy: is there a role for nurses as physician extenders?

Artificial intelligence within the small bowel: are we lagging behind?

PURPOSE OF REVIEW

The use of artificial intelligence in small bowel capsule endoscopy is expanding. This review focusses on the use of artificial intelligence for small bowel pathology compared with human data and developments to date.

RECENT FINDINGS

The diagnosis and management of small bowel disease has been revolutionized with the advent of capsule endoscopy. Reading of capsule endoscopy videos however is time consuming with an average reading time of 40 min. Furthermore, the fatigued human eye may miss subtle lesions including indiscreet mucosal bulges. In recent years, artificial intelligence has made significant progress in the field of medicine including gastroenterology. Machine learning has enabled feature extraction and in combination with deep neural networks, image classification has now materialized for routine endoscopy for the clinician.

SUMMARY

Artificial intelligence is in built within the Navicam-Ankon capsule endoscopy reading system. This development will no doubt expand to other capsule endoscopy platforms and capsule endoscopies that are used to visualize other parts of the gastrointestinal tract as a standard. This wireless and patient friendly technique combined with rapid reading platforms with the help of artificial intelligence will become an attractive and viable choice to alter how patients are investigated in the future.

Capsule endoscopy - Recent developments and future directions

INTRODUCTION

Capsule endoscopy (CE) is an established modality in the diagnostic algorithm of small bowel (SB) pathology. Its use has expanded for investigation of upper and lower gastrointestinal diseases with similar prototypes.

AREAS COVERED

This review covers the role and recent advances of CE, as a non-invasive investigative tool.

EXPERT OPINION

The use of upper gastrointestinal CE is useful in patients who require surveillance for varices particularly in the current era of the COVID-19 pandemic. It has also shown high accuracy in the detection of upper gastrointestinal hemorrhage in patients presenting with a suspicion of hemorrhage. Findings on CE help to guide further management by device-assisted enteroscopy. The data on colon CE suggest comparable diagnostic accuracy to colonoscopy for polyp detection; however, more evidence is required in the high-risk group. Crohn's CE has become an integral part of the management of patients with Crohn's disease offering a comparative assessment tool post escalation of therapy. Artificial intelligence within CE has demonstrated similar if not better diagnostic yield compared to the human with a significantly shorter reading time. Artificial intelligence is likely to be in-built within CE reading platforms over the next few years minimizing reporting time and human error.

Training in video capsule endoscopy: Current status and unmet needs

Since its introduction to clinical practice nearly 20 years ago, wireless capsule endoscopy has revolutionized the landscape in the diagnosis and management of small bowel diseases. Over the past 10 years, capsule endoscopy has evolved beyond the small intestine and a range of capsules are now available to examine the esophagus, stomach and colon. Because of its ease of use, tolerability, paucity of complications and ability to visualize the entire gastrointestinal tract, capsule endoscopy has entered the mainstream of clinical practice. This review of the literature summarizes the current state of capsule training and highlights the limited data available to assess reader competence and standards expected of an independent practitioner. There are neither standardized teaching strategies nor national or international metrics for accreditation of physicians and non-physicians interested in mastering this examination. Summating the few publications, there appears to be consensus that diagnostic expertise improves with experience, and that trainees should be fully supervised for at least 20 full case studies. Formative and summative assessment is advisable and the number of taught cases should not be the sole determinant of competence. The review also highlights differences in recommendations from major national gastroenterology societies. Finally, the authors discuss areas of unmet needs in teaching and learning for capsule endoscopy.

Adherence to European Society of Gastrointestinal Endoscopy recommendations of endoscopists performing small bowel capsule endoscopy in Italy

BACKGROUND

The European Society of Gastrointestinal Endoscopy (ESGE) has recently issued a technical review focused on small bowel capsule endoscopy (SBCE).

AIM

To compare SBCE current practice in Italy to ESGE technical recommendations.

MATERIAL AND METHODS

A dedicated per-centre semi-quantitative questionnaire was prepared by a group of SBCE experts. One-hundred-fifty Centres were invited to participate in the data collection concerning SBCEs performed between June 2016 and June 2017. Data were compared with ESGE recommendations.

RESULTS

120 Centres participated in the data collection. Current practices agreed with ESGE recommendations in 56.3% (9/16) of the issues evaluated. Differences between ESGE recommendations and current practice concerned the management of patients with pacemakers or cardiac implantable defibrillators (which was in agreement with ESGE recommendations in 31.7% and 15.8% of Centres, respectively), the SBCE setting (only 51% of SBCEs were performed as outpatients procedures), the assessment of capsule excretion (timing and modality were in agreement with ESGE recommendation in 20.0% of Centres), and in the involvement of trained nurses or fellows in training as pre-readers (7/120; 5.8%).

CONCLUSIONS

Although SBCE is widely used and largely available in Italy, there are still some technical, practical and organizational issues that can be modified to bridge the gap between current practice and ESGE guideline recommendations.

Optimising the performance and interpretation of small bowel capsule endoscopy

Small bowel capsule endoscopy has become a commonly used tool in the investigation of gastrointestinal symptoms and is now widely available in clinical practice. In contrast to conventional endoscopy, there is a lack of clear consensus on when competency is achieved or the way in which capsule endoscopy should be performed in order to maintain quality and clinical accuracy. Here we explore the evidence on the key factors that influence the quality of small bowel capsule endoscopy services.

Systematic review and meta-analysis of the performance of nurses in small bowel capsule endoscopy reading

INTRODUCTION

Increasing demands on healthcare systems mean that nurses are taking on more roles as physician extenders. Capsule endoscopy (CE) is a laborious procedure where specialist nurses could reduce physician workload and rationalise resource utilisation. The aim of this review and meta-analysis is to consolidate data on nurses' performance in small bowel CE (SBCE).

MATERIALS AND METHODS

A comprehensive literature search was conducted for randomised controlled trials and comparative studies on nurses in SBCE reading compared to physicians. We examined the performance of nurses compared to SBCE-trained physicians.

RESULTS

Sixteen relevant studies were identified, with 820 SBCE examinations involving 20 nurses. 11/16 studies reported the numbers of SBCE findings detected. Overall, the pooled proportion of all findings reported by physicians and nurses was 86%. Studies involving nurses with endoscopic experience showed a summative detection rate of 89%. 7/16 studies reported the number of videos where there was agreement between the nurse and physicians for overall findings/diagnosis. The overall proportion of videos with agreement was 68%. In studies where nurses had endoscopy experience, the proportion of videos with agreement was 71%.

CONCLUSION

Our meta-analysis supports a more active role for nurses in SBCE reading. We suggest nurses can function as independent CE readers in general, given adequate training and formal credentialing.

Capsule endoscopy of the small bowel

Capsule endoscopy (CE) is a first line small bowel investigative modality which provides more sensitive mucosal imaging than comparators. It is a non-invasive, non-irradiating tool well tolerated by patients. The risk of retention of the capsule can be minimised by ensuring luminal patency using the Agile patency device. Research continues into how to minimise missed pathology and variability in the identification of pathology or interpretation of images. The consensus is that bowel preparation using laxatives improves visibility and diagnostic yield. Research includes the development of image recognition software, both to eliminate sequentially identical images to improve viewing speed and to select or enhance images likely to represent pathology. However, careful reading by experienced capsule endoscopists remains the benchmark. This should be performed at a speed comfortable to the viewer, probably at a maximum of 15 frames per second. Some prior experience of endoscopy appears to be helpful for novice capsule endoscopists and formal training on a hands-on training course seems to improve pathology recognition, for novices and for those with CE experience.

Singular Value Decomposition Based Features for Automatic Tumor Detection in Wireless Capsule Endoscopy Images

Wireless capsule endoscopy (WCE) is a new noninvasive instrument which allows direct observation of the gastrointestinal tract to diagnose its relative diseases. Because of the large number of images obtained from the capsule endoscopy per patient, doctors need too much time to investigate all of them. So, it would be worthwhile to design a system for detecting diseases automatically. In this paper, a new method is presented for automatic detection of tumors in the WCE images. This method will utilize the advantages of the discrete wavelet transform (DWT) and singular value decomposition (SVD) algorithms to extract features from different color channels of the WCE images. Therefore, the extracted features are invariant to rotation and can describe multiresolution characteristics of the WCE images. In order to classify the WCE images, the support vector machine (SVM) method is applied to a data set which includes 400 normal and 400 tumor WCE images. The experimental results show proper performance of the proposed algorithm for detection and isolation of the tumor images which, in the best way, shows 94%, 93%, and 93.5% of sensitivity, specificity, and accuracy in the RGB color space, respectively.

Optimizing lesion detection in small-bowel capsule endoscopy: from present problems to future solutions

This review presents issues pertaining to lesion detection in small-bowel capsule endoscopy (SBCE). The use of prokinetics, chromoendoscopy, diagnostic yield indicators, localization issues and the use of 3D reconstruction are presented. The authors also review the current status (and future expectations) in automatic lesion detection software development. Automatic lesion detection and reporting, and development of an accurate lesion localization system are the main software challenges of our time. The 'smart', selective and judicious use (before as well as during SBCE) of prokinetics in combination with other modalities (such as real time and/or purge) improves the completion rate of SBCE. The tracking of the capsule within the body is important for the localization of abnormal findings and planning of further therapeutic interventions. Currently, localization is based on transit time. Recently proposed software and hardware solutions are proposed herein. Moreover, the feasibility of software-based 3D representation (attempt for 3D reconstruction) is examined.

Video capsule endoscopy in the emergency department: a prospective study of acute upper gastrointestinal hemorrhage

STUDY OBJECTIVE

Video capsule endoscopy has been used to diagnose gastrointestinal hemorrhage and other small bowel diseases but has not been tested in an emergency department (ED) setting. The objectives in this pilot study are to demonstrate the ability of emergency physicians to detect blood in the upper gastrointestinal tract with capsule endoscopy after a short training period, measure ED patient acceptance of capsule endoscopy, and estimate the test characteristics of capsule endoscopy to detect acute upper gastrointestinal hemorrhage.

METHODS

During a 6-month period at a single academic hospital, eligible patients underwent video capsule endoscopy (Pillcam Eso2; Given Imaging) in the ED. Video images were reviewed by 4 blinded physicians (2 emergency physicians with brief training in capsule endoscopy interpretation and 2 gastroenterologists with capsule endoscopy experience).

RESULTS

A total of 25 subjects with acute upper gastrointestinal hemorrhage were enrolled. There was excellent agreement between gastroenterologists and emergency physicians for the presence of fresh or coffee-ground blood (0.96 overall agreement; κ=0.90). Capsule endoscopy was well tolerated by 96% of patients and showed an 88% sensitivity (95% confidence interval 65% to 100%) and 64% specificity (95% confidence interval 35% to 92%) for the detection of fresh blood. Capsule endoscopy missed 1 bleeding lesion located in the postpyloric region, which was not imaged because of expired battery life.

CONCLUSION

Video capsule endoscopy is a sensitive way to identify upper gastrointestinal hemorrhage in the ED. It is well tolerated and there is excellent agreement in interpretation between gastroenterologists and emergency physicians.

AUTOMATIC DETECTION OF SIMILARITIES AND DIFFERENCES BETWEEN SMALL BOWEL POLYPS AND ULCERS WITH A DATA MINING APPROACH IN WIRELESS CAPSULE ENDOSCOPY VIDEOS

Over the past decade Wireless Capsule Endoscopy (WCE) technology has become a very useful tool for diagnosing diseases within the human digestive tract. Using WCE physicians can examine the digestive tract in a minimum invasive way searching for pathological abnormalities such as bleeding, polyps, ulcers and Crohn's disease. In order for WCE to be more effective for gastroenterologists, engineers have developed software methods to automatically detect these diseases at high successful rate. Using proposed a synergistic methodology for automatic discovering polyps (protrusions) and ulcers in WCE video frames, a data mining approach is used that offers useful information about ulcers, polyps and normal tissues and their visual similarities. Finally, results of the methodology are given and statistical comparisons are also presented relevant to other works.

Training in Capsule Endoscopy: Are We Lagging behind?

Capsule endoscopy (CE) is a new modality to investigate the small bowel. Since it was invented in 1999, CE has been adopted in the algorithm of small bowel investigations worldwide. Reporting a CE video requires identification of landmarks and interpretation of pathology to formulate a management plan. There is established training infrastructure in place for most endoscopic procedures in Europe; however despite its wide use, there is a lack of structured training for CE. This paper focuses on the current available evidence and makes recommendations to standardise training in CE.

Provision of service and training for small bowel endoscopy in the UK

OBJECTIVE

To determine the location and use of small bowel endoscopy services in the UK and to analyse training uptake to assess future demand and shape discussions about training and service delivery.

DESIGN

Surveys of British Society of Gastroenterology (BSG) members by web-based and personal contact were conducted to ascertain capsule endoscopy practice and numbers of procedures performed. This was compared with expected numbers of procedures calculated using BSG guidelines, hospital episode statistics and published data of capsule endoscopy in routine practice. Analysis of data from two national training courses provided information about training.

RESULTS

45% of UK gastroenterology services offered in-house capsule endoscopy. 91.3% of survey responders referred patients for capsule endoscopy; 67.7% felt that local availability would increase referrals. Suspected small bowel bleeding and Crohn's disease were considered appropriate indications by the majority. Demand is increasing in spite of restricted use in 21.6% of centres. Only two regions performed more than the minimum estimate of need of 45 procedures per 250 000 population. Eight centres perform regular device-assisted enteroscopy; 14 services are in development. 74% of trainees were interested in training and of those training in image interpretation, 67% are doctors and 28% are nurses.

CONCLUSIONS

Capsule endoscopy is used by the majority of UK gastroenterologists but appears to be underused. Current demand for device-assisted enteroscopy seems likely to be matched if new services become established. Future demand is likely to increase, however, suggesting the need to formalise training and accreditation for both doctors and nurses.

Detection of small bowel polyps and ulcers in wireless capsule endoscopy videos

Over the last decade, wireless capsule endoscopy (WCE) technology has become a very useful tool for diagnosing diseases within the human digestive tract. Physicians using WCE can examine the digestive tract in a minimally invasive way searching for pathological abnormalities such as bleeding, polyps, ulcers, and Crohn's disease. To improve effectiveness of WCE, researchers have developed software methods to automatically detect these diseases at a high rate of success. This paper proposes a novel synergistic methodology for automatically discovering polyps (protrusions) and perforated ulcers in WCE video frames. Finally, results of the methodology are given and statistical comparisons are also presented relevant to other works.

Computer-aided learning in capsule endoscopy leads to improvement in lesion recognition ability

BACKGROUND

The rapid expansion in use of capsule endoscopy (CE) has led to discussion about training needs and provision. The lesion recognition skills required for CE are ideally suited to computer-based training.

OBJECTIVE

The aim of this study was to prospectively evaluate the educational effectiveness of a computer-based CE training and testing module on trainees with varying experience.

DESIGN

This was a prospective educational evaluation study.

SETTING

Academic endoscopy unit.

PATIENTS

This study involved 28 trainees of varying CE experience (medical students, gastroenterology trainees) and 4 CE experts.

INTERVENTION

Trainees (medical students and gastroenterology trainees) without CE experience completed a 60-question, computer-based test module consisting of 30-second video clips and multiple-choice questions. Without feedback, trainees then completed a comprehensive, menu-driven, computer-based CE training module. The test module was then completed a second time and feedback was given. Expert performance on the test module was benchmarked by 4 CE experts.

MAIN OUTCOME MEASUREMENTS

The first measure was the difference in baseline performance on the test module between trainees and experts (to determine construct validity). The second measure was a change in performance on the test module after training (to determine content validity of the training module).

RESULTS

A significant difference was noted in baseline performance (P < .001) among CE experts (mean 73.8% +/- 8.0%), gastroenterology trainees (49.5% +/- 10.9%), and medical students (29.5% +/- 3.3%). Performance improved significantly (P < .001) in both trainee groups after training (gastroenterology trainees' posttraining score 62.1% +/- 7.7%; medical students' 46.7% +/- 6.8%).

CONCLUSION

Computer-based learning has a potentially significant role in the development of a training syllabus for CE and in CE accreditation.

How should we train capsule endoscopy? A pilot study of performance changes during a structured capsule endoscopy training program

There are no validated training/accreditation guidelines for capsule endoscopy. We assessed the utility of a structured training program on two experienced gastroenterologists and one endoscopy nurse. Validated studies were standardized for difficulty in blocks of three. Trainees completed a standardized data sheet for each study reported (12 studies for the physicians, 22 studies for the nurse). After each block the trainer graded performance and highlighted learning points. Statistical analysis was performed. Physician trainees accurately identified landmarks throughout, while the nurse made errors even at the end of training. Improvement in lesion detection and diagnostic accuracy improved in the nurse, but in only one of the physician trainees, highlighting the variability in learning curves. Overall performance improved in all trainees but was most marked for the nurse trainee (correlation coefficient 0.41, P = 0.06). Improvements in lesion recognition and diagnosis can be demonstrated in senior trainees and nurses following a structured training program; however, there is considerable variability.

Can we reduce capsule endoscopy reading times?

BACKGROUND

Analyzing small-bowel capsule endoscopy (CE) images is time consuming.

OBJECTIVE

To determine the effect of reducing the number of images on reading time and interpretation of CE procedures.

DESIGN

Two techniques aimed at reducing the number of images to be viewed were studied. The number of images was reduced by removing every second image (study A) or by the Quickview mode (study B). In both studies, one endoscopist viewed the images in the conventional way, whereas another endoscopist viewed the reduced number of images.

SETTING

A single-center prospective study.

PATIENTS

Two hundred CE procedures, 100 consecutive procedures for each study.

MAIN OUTCOME MEASUREMENTS

Reading times for small-bowel images were recorded. Kappa (kappa) values were used to calculate interobserver agreement between viewing techniques. Diagnostic miss rates were calculated.

RESULTS

Median procedure reading times were significantly reduced by viewing half the number of images (10.2 minutes) or using the Quickview technique (4.4 minutes) compared with conventional viewing (17.0 minutes). Interobserver agreement was excellent (kappa = 0.91) in study A and good (kappa = 0.74) in study B. The diagnostic miss rate was 2% when half the number of images were viewed and 8% when the Quickview technique was used. Agreement between both techniques and conventional viewing was best when the indication for the procedure was suspected inflammatory bowel disease.

LIMITATION

Lack of a criterion standard.

CONCLUSIONS

Techniques that reduce the number of images examined in CE are time saving but are associated with considerable diagnostic miss rates. Such techniques may only be considered if inflammatory bowel disease is suspected.

Is formal training necessary for capsule endoscopy? The largest gastroenterology trainee study with controls

BACKGROUND

Little is known about the infrastructure to train gastroenterologists in capsule endoscopy. The level of capsule endoscopy exposure among trainees in the United Kingdom or Europe has also not been quantified.

AIMS AND METHODS

To assess the ability of 10 gastroenterology trainees with endoscopy experience to interpret 10 capsule endoscopy videos against five medical students, with an expert in capsule endoscopy as the gold standard. Parameters assessed included gastric emptying time, small bowel transit and the diagnosis made. A questionnaire survey assessed the level of capsule endoscopy exposure among United Kingdom trainees.

RESULTS

Trainees were better at determining the gastric emptying time (p=0.013) and more likely to record true positives compared to the students (p=0.037). They were also less likely to record false positives (p=0.005) and more likely to reach the correct diagnosis (p=0.001, OR 3.6, CI 1.8-7.4). Our survey found that, 65% of trainees had prior exposure to capsule endoscopy but only 13% had done capsule endoscopy reporting. Sixty seven percent felt capsule endoscopy should be incorporated into their training.

CONCLUSION

This study has shown that prior endoscopic experience enables trainees to interpret capsule endoscopy more accurately than medical students. However, there is a demand for focussed training which would enable trainees to reliably interpret pathology on capsule endoscopy.

Capsule endoscopy in the evaluation of gastrointestinal disease

PURPOSE OF REVIEW

The small bowel has been a technically difficult area to examine. Indirect modalities such as barium follow-through have the disadvantage of attendant radiation exposure. Capsule endoscopy, a novel wireless method of investigation of the small bowel, has acquired an important role in both adult and paediatric medicine.

RECENT FINDINGS

The clinical utility of capsule endoscopy has rapidly expanded since its approval by the Food & Drug Administration in the USA in 2001. It has developed an established role in adults, in the investigation of obscure gastrointestinal bleeding, small bowel Crohn's disease, complications of coeliac disease and surveillance of polyposis syndromes. Despite a lag in its use in paediatrics, capsule endoscopy offers an accurate and effective means of investigating the small bowel in children. It has opened up new horizons and permitted a noninvasive approach to identifying occult lesions in the small bowel of children when conventional imaging has been unhelpful.

SUMMARY

This review appraises the current literature to define the clinical indications and practical aspects of capsule endoscopy that are of interest to the paediatrician.