Introduction

The high diagnostic accuracy of colon capsule endoscopy (CCE) for colorectal polyps makes it a valid alternative in colorectal screening compared to conventional colonoscopy [1, 2]. To achieve an acceptable adenoma detection rate (ADR) by colonoscopy the scope withdrawal time should be > 6 minutes (min) [3]. No guideline currently exists for the optimal colon transit time (CTT) in CCE. We aimed to investigate the impact of CCT on polyp detection rate (PDR) to establish a minimum CCT for an acceptable PDR.

Aims & Methods

Between August 2020 and December 2022, the trial CareForColon2015 was conducted in Denmark [4,5]. Complete CCE investigation was defined a study with visualization of the hemorrhoidal plexus or excreted capsule within battery lifetime and bowel preparation rated fair or better on the Leighton-Rex scale for all colonic segments. PDR was defined as number of CCEs in which at least one polyp was detected, divided by the total number of CCEs. Additionally, we calculated two PDRs limited to polyps > 5 and > 9 millimeter (mm), respectively. Statistical analyses were performed in Stata/BE 17.0 (StataCorp, Texas, USA). Logistic regression models adjusted for age, sex and bowel preparation were used to estimate odds ratios (OR) for polyp detection based on CTT as a categorical variable.

Results

Two thousand and thirty had CCE; 616 were excluded due to incomplete investigation (30.3%). For the complete CCEs, the total PDR was 79.4%. PDR was 68.8% for polyps > 5 mm and 46.5% for polyps > 9 mm. CTT > 60 min (n = 1,009) was set as reference in the analyses of PDR stratified by CTT ≤ 15 min (n = 74), CTT 16-30 min (n = 126) and CTT 31-60 min (n = 205). The OR of polyp detection was significantly lower for CTT ≤ 15 min (OR 0.334, p < 0.001) and CTT 31-60 min (OR 0.663, p = 0.013) (Table 1). Regarding PDR for polyps > 5 mm, the OR was significantly lower for investigations ≤ 15 min (OR 0.466, p = 0.003) and 31-60 min (OR 0.695, p = 0.027) (Table 1). No significant differences for PDR concerning polyps > 9 mm and CTT were observed (Table 1).

Table 1 Calculated odds ratio (OR), 95 % confidence interval, p value and forest plot for PDR overall, PDR > 5 mm and PDR > 9 mm stratified for colonic transit time (CTT). For all calculations, CTT > 60 minutes was set as baseline and OR are adjusted for sex and age.

Conclusion

Until now, expert opinion is used in evaluation of CCE investigation validity; Rex et al. suggests CTT < 40 min combined with poor preparation as a technically inadequate investigation for polyps [6]. Also, Pickhardt et al. have demonstrated the malignant potential of polyps > 9 mm to be significantly higher than of diminutive polyps [7], suggesting the impact of missed polyps ≤ 9 mm to be low. Thus, our results suggests CTT to have minor clinical impact on patient pathway in colorectal screening CCE although a CTT ≤ 60 min is significantly correlated with lower PDR compared to CTT > 60 min.

References

1. Kjølhede T, Ølholm AM, Kaalby L, et al. Diagnostic accuracy of capsule endoscopy compared with colonoscopy for polyp detection: systematic review and meta-analyses. Endoscopy. 2021;53(07):713-21.
2. Sulbaran M, Bustamante-Lopez L, Bernardo W, et al. Systematic review and meta-analysis of colon capsule endoscopy accuracy for colorectal cancer screening. An alternative during the Covid-19 pandemic? J Med Screen. 2022;29(3):148-55.
3. Barclay RL, Vicari JJ, Doughty AS, et al. Colonoscopic Withdrawal Times and Adenoma Detection during Screening Colonoscopy. New England Journal of Medicine. 2006;355(24):2533-41.
4. Kaalby L, Deding U, Kobaek-Larsen M, et al. Colon capsule endoscopy in colorectal cancer screening: a randomised controlled trial. BMJ Open Gastroenterol. 2020;7(1).
5. Deding U, Bjorsum-Meyer T, Kaalby L, et al. Colon capsule endoscopy in colorectal cancer screening: Interim analyses of randomized controlled trial CareForColon2015. Endosc Int Open. 2021;9(11):E1712-E9.
6. Rex DK, Adler SN, Aisenberg J, et al. Accuracy of Capsule Colonoscopy in Detecting Colorectal Polyps in a Screening Population. Gastroenterology. 2015;148(5):948-57.e2.
7. Pickhardt, P. J., Hassan, C., Laghi, et al. Small and diminutive polyps detected at screening CT colonography: a decision analysis for referral to colonoscopy. AJR. American journal of roentgenology. 2008; 190(1), 136–144.

Disclosure

A.K.: Co-founder and shareholder of A.J.M. Medicaps; co-director and shareholder of iCERV Ltd.; consultancy fees (Jinshan Ltd.); travel support (Jinshan, Aquilant, and Dr Falk Pharma); research support (grant) from ESGE/Given Imaging Ltd. And (material) IntroMedic/SynMed; honoraria (Dr Falk Pharma UK, Ferring, Jinshan, Medtronic). Member of Advisory board meetings (Dr Falk Pharma UK, Tillots, ANKON).

Introduction

Colon Capsule Endoscopy (CCE) offers a non-invasive alternative to colonoscopy for lower gastrointestinal (GI) investigations. However, its adoption is limited by lengthy reading times, reader fatigue, and variable diagnostic accuracy. These factors are often influenced by bowel preparation quality and completion rates. Artificial intelligence (AI) has shown the potential to improve diagnostic accuracy of polyp detection and reduce reading times in capsule endoscopy.

Aims & Methods

Objective(s): The primary aim is to assess the diagnostic accuracy of Computer-Aided Detection (CADe) system (AiSPEED™) assisted CCE reading using full-video analysis in a real-world clinical setting. Secondary outcome was to assess a) non-inferiority compared to standard clinician reading in detecting polypoid lesions and b) mean reading time.
Methods: CESCAIL study is a multi-centre study of 14 UK centres recruited 720 participants between November 2021 and September 2024. Participants (prospectively and retrospectively enrolled ) included those ≥18 years referred for CCE under the urgent cancer pathway or for post-polypectomy surveillance. CCEs were performed using PillCam™ COLON 2 and analysed using AiSPEED™. CCE videos were evaluated by separate clinicians who provided standard readings, while AI-assisted reading included an AI-assisted pre-reader review and subsequent clinician validation.

Results

720 patients were enrolled, with 673 included in the final analysis. The capsule excretion rate before battery depletion was 77.1%, with adequate bowel preparation achieved at 78.1% (with standard) and 74.0% (with AI-assisted reading) (McNemar p=0.108). In the per-patient analysis, the diagnostic yield for detecting polyps was 63.6% (428/673) for standard reading and 70.6% (475/673) for AI-assisted reading, using the expert panel as the reference standard. These findings confirmed both non-inferiority (p<0.001) and superiority (p<0.001) of the AI-assisted reading. The diagnostic accuracy for detecting polyps requiring follow-up procedure (flexible sigmoidoscopy/colonoscopy) was 0.96 (95% CI: 0.95–0.98) for AI-assisted reading, compared to 0.91 (95% CI: 0.89–0.93) for standard reading (p<0.0001) (see Table 1). The mean reading time per video was 8.7 minutes for AI-assisted reading compared to 47.3 minutes for standard reading, representing a 5.4-fold reduction.

Conclusion

AI-assisted reading with AiSPEED™ offers the potential for greater accuracy in polyp detection and significantly reduced clinician reading times during CCE examination compared to standard reading methods.

References

1. Moen S, Vuik FER, Kuipers EJ, Spaander MCW. Artificial Intelligence in Colon Capsule Endoscopy-A Systematic Review. Diagnostics (Basel). 2022;12(8).
2. Mota J, Joao Almeida M, Mendes F, Martins M, Ribeiro T, Afonso J, et al. A Comprehensive Review of Artificial Intelligence and Colon Capsule Endoscopy: Opportunities and Challenges. Diagnostics (Basel). 2024;14(18).
3. Spada C, Piccirelli S, Hassan C, Ferrari C, Toth E, Gonzalez-Suarez B, et al. AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study. Lancet Digit Health. 2024;6(5):e345-e53.
4. Spada C, Hassan C, Galmiche JP, Neuhaus H, Dumonceau JM, Adler S, et al. Colon capsule endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Guideline. Endoscopy. 2012;44(5):527-36.
5. PillCam COLON 2 for investigation of the colon through direct visualisation [Internet]. NATIONAL INSTITUTE FOR HEALTH AND CARE EXCELLENCE. August 2024. Available from: https://www.nice.org.uk/guidance/gid-dg10083/documents/final-scope-2.

Disclosure

Hagen Wenzek serves as the CEO, and Elizabeth White is the Project Manager at Corporate Health International which owns the ​intellectual property of AiSPEED^TM

Introduction

Artificial Intelligence (AI) assisted reading in Small Bowel Capsule Endoscopy (SBCE) has recently been shown to achieve comparable and potentially superior accuracy compared to standard clinician reading. In Colon Capsule Endoscopy (CCE), AI algorithms have also demonstrated promising results. However, the extent of AI-assisted reading's advantage remains unclear, particularly regarding its performance across different polyp sizes, morphologies, locations, and other factors. A deeper understanding of these variables is crucial for optimising AI performance and facilitating its clinical integration.

Aims & Methods

This CESCAIL sub-analysis evaluates the per-polyp diagnostic accuracy of AI-assisted versus standard clinician assessment (readings) and identifies key factors influencing AI-assisted accuracy using AiSPEED^TM, the Computer-Aided Detection (CADe) system.
The CESCAIL study evaluated the diagnostic accuracy of AI-assisted CCE readings using AiSPEED™ compared to the standard readings. Standard readings were manually performed by clinicians, while AI-assisted readings incorporated an AI pre-review followed by clinician validation. A total of 1,803 polyps from 673 patients were analysed at the per-polyp level, focusing on sensitivity and positive predictive value. Factors influencing the improved accuracy of AI-assisted readings over standard clinician readings were also assessed, including polyp size, morphology, location, patient demographics (age and sex), bowel preparation quality, capsule excretion rates, comorbidities, medications, reading time, and video duration.

Results

AI-assisted reading demonstrated significantly higher sensitivity with clear superiority for smaller polyps (<10 mm) compared to larger ones (≥10 mm) (OR 2.27 vs 0.88, p<0.001) (see Table 1). While there was no observed difference in diagnostic accuracy between AI-assisted and standard clinician assessment for polyps ≥10 mm, non-inferiority was established. AI accuracy remained consistent between 6–9 mm and ≤5 mm polyps (p=0.64). The most notable improvement was observed with hyperplastic polyps (HPs) (OR 5.4, p<0.001). No significant differences were identified for pedunculated, sub-pedunculated, Lateral Spreading Tumours, or Sessile Serrated Lesions. Furthermore, AI-assisted readings were significantly more accurate for left-sided polyps than right-sided ones (OR 2.36 vs 1.66, p<0.0001), although AI-assisted reads outperformed standard reads in both locations.

Conclusion

This study highlights the performance and consistency of AI-assisted reading, particularly for detecting smaller adenomas and HPs, with notably improved accuracy in the left colon. Next-generation AI should focus on distinguishing significant from diminutive polyps and enhancing polyp characterisation, especially for right-sided lesions.

References

1. Spada C, Piccirelli S, Hassan C, Ferrari C, Toth E, Gonzalez-Suarez B, et al. AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study. Lancet Digit Health. 2024;6(5):e345-e53.

Disclosure

Hagen Wenzek serves as the CEO, Elizabeth White is the Project Manager, and Pablo Laiz is the AI software engineer at Corporate Health International, which owns the intellectual properties of AiSPEED^TM.

Introduction

Colon capsule endoscopy (CCE) may be recommended as a screening test for individuals under the age of 50 with low familial risk, diagnosed with irritable bowel syndrome (IBS) but lacking alarming symptoms and showing no fecal immunochemical test (FIT) positivity.

Aims & Methods

In the present study, our aim was to assess the efficacy, feasibility and acceptance of CCE in IBS patients with low risk of CRC, and our secondary aim was to assess polyp detection rates, transit times, cleanliness level and patient satisfaction. From April 2022 to April 2024, we conducted a prospective study at our institution involving 196 patients with IBS under the age of 50 (130 (66%) males, 66 (44%) females). We applied first in the literature, the recently developed colon capsule endoscopy technology of the Anx Robotics (USA) Navicam dual-camera CCE for this comprehensive assessment. The new first generation Navicam CCE measures 31mm in length and 11.6mm in diameter, weighing approximately 3 grams. The two cameras operate at adaptive frame rate of 0.5 to 16 pic/sec, with adaptive focus of 0-30 mm, providing an image resolution of 480x480 pixels. The minimum battery time is 12h, and this is a fully functional panenteric capsule. Colonoscopy under anaesthesia was offered to all patients, and after detailed information and signing the consent form, they chose CCE as the first examination method. We identified and addressed the incomplete cases, recorded capsule transit times, and calculated the polyp detection rates. If polyps were detected, patients underwent subsequent colonoscopy with Propofol sedation for polyp removal and histological analysis.

Results

Out of the total cases, 8.7% (n=17) were incomplete. The average colon and total transit time was 201.95 and 360.55 mins, respectively. Our study revealed a remarkable 14.8% (n=29) polyp detection rate (PDR) among the participants. PDR varied across age groups (18-30yo: 12.5%, 31-40yo: 14.04%, 41-50yo: 17.39%). Polyp sizes were categorized as <5mm (n=20), 5-7mm (n=6), and >7mm (n=3). The majority of polyps were located in the sigmoid colon (n=12), followed by the unspecified left colon (n=10) and the right colon (n=7). Subsequent colonoscopy due to positive CCE performed in all patients and detected an additional 6 small polyps (<3mm). In 4 cases, colonoscopy yielded negative results. However, upon conducting a back-to-back colonoscopy all of the previously undetected polyps were eventually found. Histology results revealed one high-grade dysplastic polyp. The average cleanliness level of the colon was assessed using the CCE Cleansing Score (CC-CLEAR). For the coecum, the right and left colon, the average scores were 5.5-7-8, respectively. Impressively, 95% of participants reported high tolerance, and 91% of respondents expressed a preference for CCCE as the next screening procedure too and colonoscopy only after a positive CCE result.

Conclusion

Navicam colon capsule endoscopy emerges as a useful and feasible screening tool, demonstrating unparalleled promise in detecting polyps among asymptomatic individuals. Its polyp detection rate, cost-effectiveness, patient-friendly nature, and agreement with colonoscopy findings position it as a potent complementary method for advancing colorectal screening in low CRC risk individuals.

Introduction

Despite the rising global incidence of colorectal cancer (CRC) and increasing pressure on endoscopy services, colon capsule endoscopy (CCE) has seen limited clinical uptake, primarily due to a lack of trust in its diagnostic accuracy. Although multiple systematic reviews and meta-analyses have reported reasonable polyp detection rates, scepticism persists. This meta-review and meta-meta-analysis aim to synthesise evidence on CCE’s diagnostic accuracy in polyp and CRC detection, using CT colonography or colonoscopy as the reference standard.

Aims & Methods

We conducted a systematic search of EMBASE, MEDLINE, and PubMed for systematic reviews, with or without meta-analyses, evaluating the diagnostic accuracy of CCE in detecting polyps and CRC. A qualitative thematic review and meta-meta-analysis were conducted following PRISMA guidelines. A bivariate generalised linear mixed model (GLMM) with random effects was used for pooled diagnostic accuracy estimates, and meta-regression was performed using restricted maximum likelihood (REML) estimation.

Results

Nine systematic reviews (8 with meta-analyses) were included, comprising 3472 participants in 28 unique primary studies after removing duplicates. A total of 82 studies were included across nine systematic reviews, but only 28 were unique primary studies. The corrected covered area (CCA) was 100%, indicating a high overlap among the systematic reviews. A subsequent meta-analysis of all 28 unique primary studies showed a pooled per-patient diagnostic accuracy for detecting polyps of any size with a sensitivity of 0.79 (95% CI: 0.69–0.86), specificity: 0.77 (95% CI: 0.71–0.82) and AUC: 0.81 (95% CI: 0.47–0.96). For polyps ≥6mm, the sensitivity, specificity, and AUC were 0.80, 0.87, and 0.81, respectively. Detection of polyps ≥10mm showed a sensitivity of 0.88, specificity of 0.95, and AUC of 0.95. The second-generation CCE (CCE2) demonstrated improved accuracy in any size polyps: Sensitivity 0.90 (95% CI: 0.79–0.96), Specificity: 0.81 (95% CI: 0.70–0.89) and AUC: 0.82 (95% CI: 0.46–0.96). For polyps ≥6mm, CCE2 achieved AUC 0.92, and for polyps ≥10mm, AUC 0.94. CCE2 subgroup analysis demonstrated a high sensitivity of 0.90 (95% CI: 0.79-0.96) for any polyp size and 0.87 (95% CI:0.82-0.91) for polyps ≥6mm, with both results exhibiting low heterogeneity (P >0.05, I² <25%). The pooled CRC detection sensitivity was 0.96 (95% CI: 0.73–1.00) after excluding missed cancers due to capsule battery exhaustion before excretion.

Conclusion

This analysis confirms CCE2's high diagnostic accuracy for polyp and colorectal cancer detection. While technical challenges persist, CCE2 shows promise as a complementary diagnostic tool to help address increasing endoscopy service demands.

References

Rokkas T, et al. A meta-analysis evaluating the accuracy of colon capsule endoscopy in detecting colon polyps. Gastrointest Endosc. 2010;71(4):792-8.
Spada C, et al. Meta-analysis shows colon capsule endoscopy is effective in detecting colorectal polyps. Clin Gastroenterol Hepatol. 2010;8(6):516-22.
Spada C, et al. Accuracy of First- and Second-Generation Colon Capsules in Endoscopic Detection of Colorectal Polyps: A Systematic Review and Meta-analysis. Clin Gastroenterol Hepatol. 2016;14(11):1533-43 e8.
Vuik FER, et al. Colon capsule endoscopy in colorectal cancer screening: a systematic review. Endoscopy. 2021;53(8):815-24.
Alihosseini S, et al. Second-generation colon capsule endoscopy for detection of colorectal polyps: A meta-analysis. Med J Islam Repub Iran. 2020;34:81.
Kjolhede T, et al. Diagnostic accuracy of capsule endoscopy compared with colonoscopy for polyp detection: systematic review and meta-analyses. Endoscopy. 2021;53(7):713-21.
Ali H, et al. Diagnostic Accuracy for Per-Patient Polyp Detection of Second-Generation Capsule Endoscopy Compared to Colonoscopy: A Meta-Analysis of Multicenter Studies. Cureus. 2021;13(8):e17560.
Mollers T, et al. Second-generation colon capsule endoscopy for detection of colorectal polyps: Systematic review and meta-analysis of clinical trials. Endosc Int Open. 2021;9(4):E562-E71.
Sulbaran M, et al. Systematic review and meta-analysis of colon capsule endoscopy accuracy for colorectal cancer screening. An alternative during the Covid-19 pandemic? J Med Screen. 2022;29(3):148-55.

Disclosure

No conflict of interest

Introduction

Colon capsule endoscopy (CCE) has been demonstrated to be comparable to colonoscopy and better than CT colonography (CTC) for the detection of colonic pathology. Challenges include poor completion rates and high re-investigation rates.

Aims & Methods

The aim of this study was to assess the role of CCE with faecal immunochemical testing (FIT) as a non-invasive, diagnostic tool in symptomatic and screening populations attending Connolly Hospital.
Prospective participants were identified from both the central endoscopy waiting list at Connolly Hospital and from our national colorectal screening programme, Bowel Screen. All participants were due to attend Connolly Hospital for a symptomatic or surveillance colonoscopy during the time period of the study. Consenting participants underwent CCE the day prior to their scheduled colonoscopy. CCEs were read by two expert readers. Participants were sent FIT kits to complete prior to CCE. Primary outcomes were CCE polyp detection rates (PDR). The potential benefit of using FIT as a triage tool to identify low-risk individuals appropriate for CCE over colonoscopy was explored.

Results

80 back-to-back procedures were completed January 2023-February 2024 (M: F 50:30, mean age 59.6, range 35-78) in a single centre. The most common indications for colonoscopy were surveillance 41.5%, PR bleeding 21% and diarrhoea/ IBD assessment 15%.
CCE detected a total of 108 polyps in 45/80 (56%) participants versus 93 polyps in 39/80 (48%) participants at colonoscopy (p= 0.34). When only complete CCE are included, the polyp detection rate increased to 31/45 (68%), p< 0.05. 79% supplied FITs prior to CCE. CCE PDR for all polyps when FIT < 50 ng/ml was 19/33 (57%) versus (20/27) 74% with FIT > 50 ng/ml (p=0.18). There is trend towards significance. A lower FIT cut-off, closer to limit of detection, not available to this study, may have more significant results.
Only one participant had a cancer diagnosed at colonoscopy. It was located on the ileocaecal valve. The cancer was not detected by CCE despite the capsule passing through this region. This, to our knowledge, is only the second missed cancer by CCE documented.
ESGE 2012 guidelines recommend follow up colonoscopy for one polyp measuring 6mm or more, or if three polyps of any size are detected. 50/80 (62.5%) CCE examinations would have required follow up if they were not part of a study and scheduled for next day colonoscopy. Even when looking at only those CCE examinations that were complete, 17/45 (38%) required further investigation. Reasons for re-investigation included incomplete examination 32/49 (65%), for polypectomy 16/49 (33%) and for biopsy in 1/49 (2%).
False negative CCE rates for polyps greater than 6mm range from 2-15.5% in the literature. In keeping with this, the false negative CCE for all polyps in this study was 8.75%, and 6.25% for polyps greater than 6mm.
There were no adverse events reported. There were technical issues reported in 16% of CCE. These included the capsule not turning on until it was beyond the caecum, participants removing the belt intermittently and one interference which was believed to be secondary to a topical glucose monitor.

Conclusion

The increasing demand on colonoscopy waiting lists raises concerns regarding the ability of health services to deliver traditional endoscopy in a timely fashion. Alternative modalities are necessary and CCE is a viable diagnostic alternative. There is likely a role for FIT testing as a triage tool prior to CCE to reduce re-investigation rates.