Introduction

Adenoma detection rate (ADR) and serrated polyp detection rate (SDR) are internationally recognised quality indicators of colonoscopy. However, determining ADR and SDR requires the matching of endoscopy and histology reports, which can be challenging in the presence of separate electronic medical record systems. The use of coding analytics may expedite this process, enabling rapid and efficient data collection and extraction from reports. This study aimed to validate an innovative coding analytic in measuring ADR and SDR.

Aims & Methods

A coding analytic algorithm was developed to semi-automatically extract patients’ names, polyp type, caecal intubation rate, and bowel preparation quality, from colonoscopy and histology reports. These reports were then manually reviewed to verify the concordance of patient names, ADR and SDR between the two methods. This process was applied in the initial phase, repeated following coding analytic change, and again with a validation cohort.

Results

The initial phase, which included 5911 colonoscopies performed by 53 endoscopists from January 2021 to June 2022, revealed that the coding analytic program extracted all patient names with 99.9% concordance and had a 98.9% accuracy in ADR and SDR. The discrepancies were mainly limited by spelling variation, different histology report dates, missing histology reports from the hospital’s pathology database, and overlapping terms such as tubular adenoma and tubulovillous adenoma, or villous changes that were not specific to polyps. Coding analytic search terms were subsequently modified to take into consideration these limitations. Following modification, using data from the same cohort, accuracy of the coding analytics improved to 100%, excluding 4 colonoscopies that had missing histology reports.
A total of 2022 colonoscopies performed by 40 endoscopists at the same hospital network, over July to December 2022, were included in a validation cohort. The updated coding analytic program accurately extracted all patient names with 100% concordance, and a 99.9% accuracy in ADR and SDR. The sensitivities of ADR and SDR were 99.9% and 99.6% respectively, with specificities of 100% for both ADR and SDR (Table 1). The discrepancies in the validation phase arose from 2 histology mismatches, that were a result of missing histology reports from the hospital’s histology database program. Excluding this software error renders the coding analytic program to be 100% accurate.

Table 1: Performance of coding analytics before and after modification of coding search terms

Conclusion

This study demonstrated and validated an automated extraction coding algorithm to have an accuracy of almost 100% in determining ADR and SDR for endoscopists in a large tertiary healthcare colonoscopy service. Wider adoption of these coding analytics may enable significant improvements in auditing of colonoscopy quality that is more time-efficient.

Introduction

Colonoscopy plays a key role in colorectal cancer (CRC) screening. It is effective in reducing morbidity and mortality from CRC. To optimize quality of colonoscopy, performance measures (PM) have been identified and published by major international societies. While adenoma detection rate (ADR) is an imperative quality measure the sessile serrated lesion detection rate (SSLDR) is not currently a quality indicator for screening colonoscopy.
This study aimed to determine the trend of polyp detection rate (PDR), ADR, and SSLDR in participants in different age groups.

Aims & Methods

We performed a retrospective observational study of patients who underwent colonoscopy at Olymed, Kyiv, Ukraine from April 2021 through December 2023. All data were extracted and collected anonymously from the colonoscopy database and pathology reports and further analyzed. We divided patients by the different age groups and calculated PDR, ADR, and SSLDR for each group. PDR, ADR, and SSLDR were defined as the number of colonoscopies with at least one polyp, adenoma, and sessile serrated lesion detected respectively, divided by the total number of complete colonoscopies performed.

Results

This study was performed initially on 2676 patients who underwent colonoscopy from April 2021 through December 2023. Colonoscopies were mainly performed with colonoscopes with magnification and artificial intelligence assistance. After the exclusion of colonoscopies where examinations weren`t extended to the cecum or Boston Bowel Preparation Scale < 6 the final study dataset consisted of 2402 colonoscopies. The patients were divided into 6 main groups and considering the discussion about lowering the screening age for CRC 2 additional groups were added. Results of PDR, ADR, and SSLDR for each group are shown in Table 1.

Conclusion

This study reveals a notable trend of the PDR, ADR, and SSLDR in different age groups during colonoscopy. While ADR and PDR show an increase with patient age, a similar pattern is not observed with SSLDR. This finding underscores the importance of recognizing SSLs, particularly in younger adults, as they appear to be more common than previously assumed. Further investigation into the role of SSLs in the development of CRC, particularly among younger adults, is warranted. Additionally, there is a need to establish the ideal SSDR metric and define a target for endoscopists to meet.
By advancing our understanding of SSLs and their implications for CRC risk, we can improve screening and prevention strategies to reduce the burden of colorectal cancer in the population.

Introduction

Adenomas per Colonoscopy (APC) might serve as an adjuvant quality metric to the Adenoma Detection Rate (ADR). This indicator is calculated by dividing the total number of detected adenomas by the number of colonoscopies performed. It motivates the operator to maximize adenoma identification and removal during screening procedures and allows a more comprehensive assessment of the colonoscopy's quality.

Aims & Methods

The aims of this study were to assess the association between the ADR and the APC metrics in colorectal cancer screening and to explore factors influenciating each of these indicators. This retrospective, single-center study analyzed total screening colonoscopies conducted on 50 years old or more patients, over a period of 18 months (from April 2022 to September 2023) and their corresponding histological reports. Colonoscopies with at least one colonic segment with less than 2 points on the Boston Bowel Preparation Scale (BBPs) were excluded. Statistical analysis was performed using SPSS v29.0.

Results

502 total colonoscopies were included. ADR was 41.7% and APC was 76.5%. The number of adenomas per colonoscopy ranged from 0 to 11 adenomas. There was a positive statistically significant association between the ADR and the APC (β=0.6, p<0.001). No statistically significant difference was found in the average age between patients with and without adenomas (p>0.05), nor a correlation between age and the number of APC (p>0.05). Men were 2.1 times more likely to have at least one adenoma (p<0.05) and the average number of adenomas per colonoscopy was statistically significant higher in men (p<0.05). The BBPS score was not associated with the detection of at least one adenoma or to the total number of adenomas per colonoscopy (p>0.05). The average withdrawal time was higher in patients with adenomas (p<0.05), and there was a positive, statistically significant, moderate correlation between withdrawal time and the number of APC (r=0.5; p<0.001). No association was found between the colonoscopy schedule, endoscopist fatigue or experience and the presence of at least one adenoma (p>0.05). The average number of adenomas per colonoscopy was also not statistically significantly different among the previously mentioned groups (p>0.05).

Conclusion

Our study confirmed a significant association between the ADR and the APC, encouraging the use of APC as a complementary metric in colorectal cancer screening. Influencing factors were similar between the two indicators. While gender and withdrawal time significantly influenced adenoma detection and the number of adenomas detected per colonoscopy, with men and longer procedures showing higher ADR and APC rates, other factors such as age, bowel preparation quality, and procedural variables showed no significant impact.

Introduction

AI (artificial intelligence)-driven computer-aided detection (CADe) systems are typically trained using high-quality, standardized colonoscopy images/videos, assuming its use under optimal bowel preparation. However, it remains uncertain how varying levels of bowel cleanliness affect CADe performance.

Aims & Methods

To measure the impact of bowel preparation quality on the adenoma detection capability of CADe systems.
This is a cumulative post-hoc analysis of individual data from three randomized controlled studies with similar design comparing CADe-assisted with standard colonoscopy (SC). Only patients with adequate bowel preparation (Boston Bowel Preparation Scale [BBPS] >2 in each colonic segment) were included. The primary outcome measure was the difference in adenoma detection rate (ADR) and adenoma per colonoscopy (APC) between the CADe-assisted and SC groups, according to the quality level of bowel preparation, classified as good (BBPS 6–7) or excellent (BBPS 8–9).

Results

A total of 2103 patients (1047 CADe, 1056 SC; mean age 61.5 ± 9.2 years; 50.4% male) were included. Bowel preparation was rated as good in 906 patients (43.1%) and excellent in 1197 patients (56.9%). CADe increased ADR and APC compared to SC in both good (52.2% vs. 43.8%; 1.21 vs. 0.93) and excellent (54.5% vs. 43.9%; 1.09 vs. 0.89) bowel preparation groups. The absolute increase in ADR with CADe was +8.4% (95% CI: 1.9–14.9) and +10.6% (95% CI: 5.0–16.2) in good and excellent preparation groups, respectively, with no significant interaction between preparation quality and CADe effect (Δ = +2.2%, 95% CI: -6.4–10.8; interaction p = 0.612). Similarly, APC increases were +0.28 (95% CI: 0.06–0.50) and +0.20 (95% CI: 0.03–0.36) for the good and excellent preparation groups, respectively, without significant interaction observed (Δ = -0.08, 95% CI: –0.22 to +0.06, interaction p = 0.261). Similar trends were observed when the analysis was restricted to the right colon or to diminutive adenomas.

Conclusion

In patients with adequate bowel preparation, CADe improves adenoma detection regardless of cleansing quality grades.

References

1. Repici, A, Badalament M, Maselli R et al. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology 2020; 159: 512–520
2. Repici A, Spadaccini M, Antonelli G, et al. Artificial intelligence and colonoscopy experience: lessons from two randomised trials. Gut 2022; 71: 757-765.
3. Rondonotti E, Di Paolo D, Rizzotto ER, et al. Efficacy of a computer-aided detection system in a fecal immunochemical test-based organized colorectal cancer screening program: a randomized controlled trial (AIFIT study). Endoscopy. 2022; 54: 1171-1179.

Introduction

One-fourth of colorectal neoplasia is missed at screening colonoscopy, representing the leading cause of interval colorectal cancer (I-CRC). Colonoscopy assisted by artificial intelligence (AI) with computer-aided polyp detection (CADe) showed higher adenoma detection rate (ADR) and higher adenoma per colonoscopy compared to white light (WL) colonoscopy in randomized clinical trials (RCTs). Despite ADR is a reliable quality indicator and has been associated to the risk of I-CRC and death, an adequate ADR does not eliminate the risk of lesion miss rate since the relationship between ADR and adenoma miss rate (AMR) is only indirect.

Aims & Methods

The aim of this meta-analysis is to summarise the performance of CADe systems on miss rate of colonic lesions. PubMed/Medline, Embase and Cochrane Library were systematically searched through October 2022 by two independent reviewers (M.M. and A.F.) for tandem-design RCTs comparing miss rate of colonic lesions in CAD-first colonoscopy followed by WL colonoscopy (experimental arm) vs WL-first colonoscopy followed by CAD colonoscopy (control arm).
The primary outcomes were pooled AMR and polyp miss rate (PMR). Secondary outcomes were advanced adenoma miss rate (aAMR) and sessile serrated lesion miss rate (SMR). Lesion miss rate was defined as the number of lesions detected at second colonoscopy divided by the total number of same lesions detected at first and second colonoscopy. A random-effect model was applied for pooling results. Heterogeneity was expressed as I².

Results

Overall, 4 RCTs (1166 patients), were included in the analysis. Pooled AMR was significantly lower in the CAD-first compared to WL-first arm (131/842, 15.5% vs 300/857, 35.0%; RR, 0.45; 95% CI, 0.35-0.58; P<0.001; I²=49%). PMR was also lower in the CAD-first compared to WL-first arm (192/1198, 16.0% vs 474/1244, 38.1%; RR, 0.43; 95% CI, 0.30-0.61; P<0.001; I²=82%).
No significant difference in aAMR (2/23, 8.7% vs 5/32, 15.6%; RR, 1.28; 95% CI, 0.34-4.83; P=0.71; I²=0%) and in SMR (5/43, 11.6% vs 27/67, 40.3%; RR, 0.44; 95% CI, 0.15-1.28; P=0.13; I²=46%) were observed.

Table 1. Characteristics of the studies included in the meta-analysis.

Conclusion

According to available evidence, the use of colonoscopy assisted by AI with CADe results in a significant lower AMR and PMR, with a potential implication in reducing the incidence of I-CRC. No significant difference in aAMR and SMR has been observed, even if these results should be further confirmed in studies with larger sample sizes.