AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study.

BACKGROUND: Capsule endoscopy reading is time consuming, and readers are required to maintain attention so as not to miss significant findings. Deep convolutional neural networks can recognise relevant findings, possibly exceeding human performances and reducing the reading time of capsule endoscopy. Our primary aim was to assess the non-inferiority of artificial intelligence (AI)-assisted reading versus standard reading for potentially small bowel bleeding lesions (high P2, moderate P1; Saurin classification) at per-patient analysis. The mean reading time in both reading modalities was evaluated among the secondary endpoints. METHODS: Patients aged 18 years or older with suspected small bowel bleeding (with anaemia with or without melena or haematochezia, and negative bidirectional endoscopy) were prospectively enrolled at 14 European centres. Patients underwent small bowel capsule endoscopy with the Navicam SB system (Ankon, China), which is provided with a deep neural network-based AI system (ProScan) for automatic detection of lesions. Initial reading was performed in standard reading mode. Second blinded reading was performed with AI assistance (the AI operated a first-automated reading, and only AI-selected images were assessed by human readers). The primary endpoint was to assess the non-inferiority of AI-assisted reading versus standard reading in the detection (diagnostic yield) of potentially small bowel bleeding P1 and P2 lesions in a per-patient analysis. This study is registered with ClinicalTrials.gov, NCT04821349. FINDINGS: From Feb 17, 2021 to Dec 29, 2021, 137 patients were prospectively enrolled. 133 patients were included in the final analysis (73 [55%] female, mean age 66·5 years [SD 14·4]; 112 [84%] completed capsule endoscopy). At per-patient analysis, the diagnostic yield of P1 and P2 lesions in AI-assisted reading (98 [73·7%] of 133 lesions) was non-inferior (p<0·0001) and superior (p=0·0213) to standard reading (82 [62·4%] of 133; 95% CI 3·6-19·0). Mean small bowel reading time was 33·7 min (SD 22·9) in standard reading and 3·8 min (3·3) in AI-assisted reading (p<0·0001). INTERPRETATION: AI-assisted reading might provide more accurate and faster detection of clinically relevant small bowel bleeding lesions than standard reading. FUNDING: ANKON Technologies, China and AnX Robotica, USA provided the NaviCam SB system.

An Overview of the Evolution of Capsule Endoscopy Research-Text-Mining Analysis and Publication Trends.

There has been a steady increase (annual percentage growth rate of 19.2%, average of 18.3 citations per document) in capsule endoscopy (CE) publications from a global, interdisciplinary research community on a growing range of CE applications over the last 20+ years. We here present the status of CE as a field of research, tracing its evolution over time and providing insight into its potential for diagnostics, prevention and treatment of gastrointestinal (GI) tract diseases. To portray the development of the CE research landscape in the 2000-2021 time span, we analyzed 5764 scientific publications. Analyses were performed using the R language and environment for statistical computing and graphics and VOSviewer, a software developed for scientific literature analysis by scientometricians. The aim of this paper is to provide a wide comprehensive analysis of the trends in CE publications. We thus performed subgroup analysis on the selected papers, including indications, annual percentage growth rate, average citations per document, most publications from research areas/interdisciplinary field of the articles, geography, collaboration networks through institutions, specific clinical keywords and device type. The firm increase in CE publications over the last two decades highlights the overall strength of the technology in GI applications. Furthermore, the introduction to the field of artificial intelligence (AI) tools has been promoting a range of technological advances that keep on affecting the diagnostic potential of CE.

PillCamColon2 after incomplete colonoscopy - A prospective multicenter study.

AIM: To evaluate the ability of PillCamColon2 to visualize colonic segments missed by incomplete optical colonoscopy (OC) and to assess the diagnostic yield. METHODS: This prospective multicentre study included 81 patients from nine centres who underwent second-generation colon capsule endoscopy (CCE) following incomplete OC performed by an experienced gastroenterologist (> 1000 colonoscopies). Patients with stenosis were excluded. According to patient preferences, CCE was performed the following day (protocol A) after staying on clear liquids and 0.75 L Moviprep in the morning or within 30 d after new split-dose Moviprep (protocol B). Boosts consisted of 0.75 L and 0.25 L Moviprep, and phospho-soda was given as a rescue if the capsule was not excreted after seven hours. RESULTS: Seventy-four patients were analysed (51% of them in group A; 49% in group B). Bowel cleansing was adequate in 67% of cases, and CCE could visualize colonic segments missed by incomplete colonoscopy in 90% of patients under protocol A and 97% of patients under protocol B (P = 0.35, n.s.). Significant polyps including adenocarcinoma were detected in 24% of cases. Detection rates for all polyps and significant polyps per patient were similar in both protocols. Polyps were found predominantly in the right colon (86%) in segments that were not reached by OC. Extracolonic findings - such as reflux esophagitis, suspected Barrett esophagus, upper GI-bleeding, gastric polyps, gastric erosions and angiectasia - were detected in eight patients. PillCamColon2 capsule was retained in the ileum of one patient (1.4%) without symptoms and removed during an uneventful resection for unknown Crohn's disease that was diagnosed as the cause of anemia, which was the indication for colonoscopy. CCE was well tolerated. One patient suffered from self-limiting vomiting after consuming the phospho-soda. CONCLUSION: Second-generation CCE using a low-volume preparation is useful after incomplete OC, and it allows for the detection of additional relevant findings, but cleansing efficiency could be improved.

A global perspective on capsule endoscopy.

A search of the internet today to quantify the estimated value of capsules from a global perspective, easily delivers figures stating around $200 million in 2014 to about $400 million by 2020, which would be approximately 10% of the gastrointestinal endoscopic market. Is this a steep rise within just six years or could the capsule market do even better? What chances does this offer and what are the key aspects for future success? By 2020, more than 1 billion people are aged sixty or older and around one third of them will live in what the UN calls "more developed regions". Naturally, this brings an increased demand for colorectal cancer screening and surgery. But keeping in mind that basically every healthcare system, in any country, is already operating at its limits, how do we secure future treatment for a growing community? Surely more competition will steadily bring down prices for capsules. However, that does not ease the amount of time that is spent to properly read any video and issue a valid diagnosis for every patient. This article intends to give an overview about the current global market for capsule endoscopy (CE) with a perspective on typical patients, their indications, and how the capsules are used and by whom. Further aspects, such as standardization of training, reading and future trends will also be elaborated on.

Re-assessment of growth hormone secretion in young adult patients with childhood-onset growth hormone deficiency.

OBJECTIVE: Patients with childhood-onset GH deficiency (coGHD) need retesting in late adolescence or young adulthood to verify whether they need to continue GH treatment. For this purpose the Growth Hormone Research Society (GRS) recommends the insulin tolerance test (ITT), or as an alternative the arginine + growth hormone releasing hormone test (ARG + GHRH test) as a diagnostic tool in adolescents and adults. However, there are no standardized cut-off levels based on normal GH secretion for determining GHD vs. GH sufficiency in young adults for the ITT, the ARG + GHRH test or the pyridostigmine + GHRH (PD + GHRH) test, a further new GH stimulation test. PATIENTS AND MEASUREMENTS: We studied 43 patients (28 with organic coGHD, 15 with idiopathic coGHD; 30 males, 13 females; aged 20.4 years, range 16.2-25.4; body mass index 23.5, range 16.3-35.8) using the ARG [0.5 g/kg intravenously (i.v.)] + GHRH (1 micro g/kg i.v.) test, the PD (120 mg orally) + GHRH (1 micro g/kg i.v.) test and the ITT (0.1 IU/kg i.v.) and compared these data with the results of 40 healthy age- and weight-matched volunteers. RESULTS: The GH response in patients was significantly lower than in healthy controls: ARG + GHRH test, 0.8 micro g/l (interquartile range 0.3-2.6) vs. 51.8 micro g/l (32.6-71.2) in controls (P < 0.0001); PD + GHRH test, 0.9 micro g/l (0.3-1.9) vs. 40.4 micro g/l (27.1-54.4) in controls (P < 0.0001); ITT, 0.1 micro g/l (0.0-0.8) vs. 20.3 micro g/l (14.7-31.7) in controls (P < 0.0001). In the ARG + GHRH test we found a diagnostic sensitivity of 100% and a specificity of 97.5% for a cut-off range from 15.1 to 20.3 micro g/l, in the PD + GHRH test a sensitivity of 100% and a specificity of 97% (cut-off range 9.1-13.1 micro g/l) and in the ITT a sensitivity and specificity of 100% each within a cut-off range from 2.7 to 8.8 micro g/l. CONCLUSION: There were no marked differences in sensitivity and specificity in young adults among ARG + GHRH test, PD + GHRH test and the ITT in assessing GH secretion. Because of the lack of side-effects, the ARG + GHRH test is the recommended method for re-evaluation of coGHD in young adults when pituitary GHD is suspected. Furthermore, in adult patient groups where organic pituitary coGHD is common, the ITT may be completely replaced by the ARG + GHRH test. Because of the predominance of hypothalamic GHD in childhood, the ITT is commonly performed for the re-evaluation of patients with childhood-onset GHD because of its mechanism of GH stimulation. The present results confirm the high discriminatory capability of the ITT in young adults.