Serrated Lesion Detection Rate Research Articles

Linked color imaging improves colorectal lesion detection especially for low performance endoscopists: An international trial in Asia.

Linked color imaging (LCI) is an image-enhanced endoscopy technique that accentuates the color difference between red and white, potentially improving the adenoma detection rate (ADR). However, it remains unclear whether LCI performance in detecting colorectal lesions differs based on endoscopists' experience levels. We aimed to evaluate the differences in LCI efficacy based on the experience levels of endoscopists by conducting an exploratory analysis. In this post hoc analysis of an international randomized controlled trial comparing the detection of adenoma and other lesions using colonoscopy with LCI and high-definition white light imaging (WLI), we included patients from 11 institutions across four countries/regions: Japan, Thailand, Taiwan, and Singapore. We retrospectively reviewed differences in the lesion detection of LCI according to endoscopists' colonoscopy history or ADR. We included 1692 and 1138 patients who underwent colonoscopies performed by 54 experts (experience of ≥5000 colonoscopies) and by 43 non-experts (experience of <5000 colonoscopies), respectively. Both expert and non-expert groups showed a significant improvement in ADR with LCI compared to WLI (expert, 61.7% vs 46.4%; P<0.001; non-expert, 56.6% vs 46.4%; P<0.001). LCI had no effect on sessile serrated lesion detection rate in non-experts (3.1% vs 2.5%; P=0.518). LCI significantly improved detection rates in endoscopists with relatively low detection performance, defined as an ADR<50%. This exploratory study analyzed data from a previous trial and revealed that LCI is useful for both experts and non-experts and is even more beneficial for endoscopists with relatively low detection performance using WLI.

A128 OPTIMIZED COMPUTER ASSISTED TECHNIQUE FOR INCREASING ADENOMA DETECTION DURING COLONOSCOPY: A RANDOMIZED CONTROLLED TRIAL

Abstract Background Efforts to improve colonoscopy have recently focused on improving adenoma detection interventions such as artificial intelligence (CADe) that have demonstrated improvements in Adenoma Detection Rates (ADR). Although studies have focused on implementation of one intervention at a time. Aims We evaluated an optimized computer assisted technique (CADopt) versus standard colonoscopy to improve ADR during colonosocopy. Methods A prospective randomized controlled trial was conducted enrolling adults (45–80 years) undergoing elective colonoscopy. Participants were randomized (1:1) to the intervention group (CADopt, and control group. In the CADopt group, endoscopists used a computer aided polyp detection combined with linked colour imaging, water exchange colonoscopy, and cecal retroflexion. In the control group, standard colonoscopy was performed. Primary outcome was Adenoma Detection Rate (ADR) in the intervention and control groups. Secondary outcomes included advanced ADR (AADR) and sessile serrated lesion detection rates (SDR). Results A total of 467 patients were recruited and randomized (CADopt group 229 patients, 50.2% female vs 238 patients, 48.3% female in the control group). ADR was 49.3% (95%CI 42.7-56.0) for the CADopt group vs 38.2% (95%CI 32.0-44.7) for the control group (p=0.016). AADR and SDR were 13.1% (95%CI 9.0-18.2) and 6.6% (95%CI 3.7-10.6) for the CADopt group versus 8.0% (95%CI 4.9-12.2), and 7.1% (95%CI 4.2-11.1) for the control group, respectively. Conclusions Using an optimized computer assisted technique led to significant improvements in ADR and a trend towards AADR improvements. Funding Agencies Fujifilm

Use of a Novel Artificial Intelligence System Leads to the Detection of Significantly Higher Number of Adenomas During Screening and Surveillance Colonoscopy: Results From a Large, Prospective, US Multicenter, Randomized Clinical Trial.

Adenoma per colonoscopy (APC) has recently been proposed as a quality measure for colonoscopy. We evaluated the impact of a novel artificial intelligence (AI) system, compared with standard high-definition colonoscopy, for APC measurement. This was a US-based, multicenter, prospective randomized trial examining a novel AI detection system (EW10-EC02) that enables a real-time colorectal polyp detection enabled with the colonoscope (CAD-EYE). Eligible average-risk subjects (45 years or older) undergoing screening or surveillance colonoscopy were randomized to undergo either CAD-EYE-assisted colonoscopy (CAC) or conventional colonoscopy (CC). Modified intention-to-treat analysis was performed for all patients who completed colonoscopy with the primary outcome of APC. Secondary outcomes included positive predictive value (total number of adenomas divided by total polyps removed) and adenoma detection rate. In modified intention-to-treat analysis, of 1,031 subjects (age: 59.1 ± 9.8 years; 49.9% male), 510 underwent CAC vs 523 underwent CC with no significant differences in age, gender, ethnicity, or colonoscopy indication between the 2 groups. CAC led to a significantly higher APC compared with CC: 0.99 ± 1.6 vs 0.85 ± 1.5, P = 0.02, incidence rate ratio 1.17 (1.03-1.33, P = 0.02) with no significant difference in the withdrawal time: 11.28 ± 4.59 minutes vs 10.8 ± 4.81 minutes; P = 0.11 between the 2 groups. Difference in positive predictive value of a polyp being an adenoma among CAC and CC was less than 10% threshold established: 48.6% vs 54%, 95% CI -9.56% to -1.48%. There were no significant differences in adenoma detection rate (46.9% vs 42.8%), advanced adenoma (6.5% vs 6.3%), sessile serrated lesion detection rate (12.9% vs 10.1%), and polyp detection rate (63.9% vs 59.3%) between the 2 groups. There was a higher polyp per colonoscopy with CAC compared with CC: 1.68 ± 2.1 vs 1.33 ± 1.8 (incidence rate ratio 1.27; 1.15-1.4; P < 0.01). Use of a novel AI detection system showed to a significantly higher number of adenomas per colonoscopy compared with conventional high-definition colonoscopy without any increase in colonoscopy withdrawal time, thus supporting the use of AI-assisted colonoscopy to improve colonoscopy quality ( ClinicalTrials.gov NCT04979962).

Artificial intelligence fails to improve colonoscopy quality: A single centre retrospective cohort study

BACKGROUND Limited data currently exists on the clinical utility of Artificial Intelligence Assisted Colonoscopy (AIAC) outside of clinical trials. AIM To evaluate the impact of AIAC on key markers of colonoscopy quality compared to conventional colonoscopy (CC). METHODS This single-centre retrospective observational cohort study included all patients undergoing colonoscopy at a secondary centre in Brisbane, Australia. CC outcomes between October 2021 and October 2022 were compared with AIAC outcomes after the introduction of the Olympus Endo-AID module from October 2022 to January 2023. Endoscopists who conducted over 50 procedures before and after AIAC introduction were included. Procedures for surveillance of inflammatory bowel disease were excluded. Patient demographics, proceduralist specialisation, indication for colonoscopy, and colonoscopy quality metrics were collected. Adenoma detection rate (ADR) and sessile serrated lesion detection rate (SSLDR) were calculated for both AIAC and CC. RESULTS The study included 746 AIAC procedures and 2162 CC procedures performed by seven endoscopists. Baseline patient demographics were similar, with median age of 60 years with a slight female predominance (52.1%). Procedure indications, bowel preparation quality, and caecal intubation rates were comparable between groups. AIAC had a slightly longer withdrawal time compared to CC, but the difference was not statistically significant. The introduction of AIAC did not significantly change ADR (52.1% for AIAC vs 52.6% for CC, P = 0.91) or SSLDR (17.4% for AIAC vs 18.1% for CC, P = 0.44). CONCLUSION The implementation of AIAC failed to improve key markers of colonoscopy quality, including ADR, SSLDR and withdrawal time. Further research is required to assess the utility and cost-efficiency of AIAC for high performing endoscopists.

S419 Bi-Institutional Colonoscopy Quality Report Card Improves Adenoma and Sessile Serrated Lesion Detection Rates

S419 Bi-Institutional Colonoscopy Quality Report Card Improves Adenoma and Sessile Serrated Lesion Detection Rates

S319 Sessile Serrated Lesion Detection Rate in Individuals with Positive Fecal Immunohistochemical Test Undergoing Colonoscopy: Results from a Large Nationwide Veterans Affairs Database

S319 Sessile Serrated Lesion Detection Rate in Individuals with Positive Fecal Immunohistochemical Test Undergoing Colonoscopy: Results from a Large Nationwide Veterans Affairs Database

S322 Sessile Serrated Lesion Detection Rate in Individuals with Positive Fecal Immunohistochemical Test Undergoing Colonoscopy: A Systematic Review and Meta-Analysis

S322 Sessile Serrated Lesion Detection Rate in Individuals with Positive Fecal Immunohistochemical Test Undergoing Colonoscopy: A Systematic Review and Meta-Analysis

S728 Impact of a Polyp Detection Poster on Sessile Serrated Lesion Detection Rate

S728 Impact of a Polyp Detection Poster on Sessile Serrated Lesion Detection Rate

The Time Has Come to Adopt the Sessile Serrated Lesion Detection Rate as a Quality Metric.

The Time Has Come to Adopt the Sessile Serrated Lesion Detection Rate as a Quality Metric.

Cap-assisted colonoscopy can increase the rate of sessile serrated lesion detection at the left lateral decubitus position: A retrospective case-control study.

We investigated the effectiveness of cap-assisted colonoscopy conducted with the patient in the left lateral decubitus position at both the colonoscope's insertion and withdrawal timepoints compared to the effectiveness of colonoscopy without a cap conducted in the supine position at withdrawal. This was a case-control study, based on historical comparisons of patients over 2 time periods. The first group of patients underwent colonoscopies with a transparent cap and the patient was in the left lateral decubitus position at both the insertion and withdrawal timepoints from April to June 2019. The subsequent group underwent colonoscopies without a cap and with the patient in the supine position at withdrawal from July to September 2019. The rates of successful intubation, cecal intubation time, and number, size, shape, and location of the detected adenomas and sessile serrated lesions were compared between the 2 groups. Data from 644 colonoscopies (cap-assisted colonoscopy + left lateral decubitus position, n=320; other colonoscopies, n=324) were analyzed. The demographic characteristics and technical performances were similar. The SSL detection rate was significantly higher with cap-assisted colonoscopy and the left lateral decubitus position than with other colonoscopies (3.4% vs 0.93%, P=.029). The adenoma detection rates in the 2 groups were similar (31% and 28%, respectively, P=.43).Cap-assisted colonoscopy in the left lateral decubitus position may increase the detection rate of sessile serrated lesions compared to colonoscopy without a cap and supine position at withdrawal.

Neoplasia Diagnosis After Multi-target Stool DNA Is Enhanced Among Lowest Baseline Detectors.

Variation in colorectal neoplasia detection limits the effectiveness of screening colonoscopy. By evaluating neoplasia detection rates of individual colonoscopists, we aimed to quantify the effects of pre-procedural knowledge of a positive (+) multi-target stool DNA (mt-sDNA) on colonoscopy quality metrics. We retrospectively identified physicians who performed a high volume of + mt-sDNA colonoscopies; colorectal neoplasia at post-mt-sDNA colonoscopy was recorded. These colonoscopists were stratified into quartiles based on baseline adenoma detection rates. Baseline colonoscopy adenoma detection rates and sessile serrated lesion detection rates were compared to post-mt-sDNA colonoscopy neoplasia diagnosis rates among each quartile. Withdrawal times were measured from negative exams. During the study period (2014-17) the highest quartile of physicians by volume of post-mt-sDNA colonoscopies were evaluated. Among thirty-five gastroenterologists, their median screening colonoscopy adenoma detection rate was 32% (IQR, 28-39%) and serrated lesion detection rate was 13% (8-15%). After + mt-sDNA, adenoma diagnosis increased to 47% (36-56%) and serrated lesion diagnosis increased to 31% (17-42%) (both p < 0.0001). Median withdrawal time increased from 10 (7-13) to 12 (10-17) minutes (p < 0.0001) and was proportionate across quartiles. After + mt-sDNA, lower baseline detectors had disproportionately higher rates of adenoma diagnosis in female versus male patients (p = 0.048) and higher serrated neoplasia diagnosis rates among all patients (p = 0.0092). Knowledge of + mt-sDNA enriches neoplasia diagnosis compared to average risk screening exams. Adenomatous and serrated lesion diagnosis was magnified among those with lower adenoma detection rates. Awareness of the mt-sDNA result may increase physician attention during colonoscopy. Pre-procedure knowledge of a positive mt-sDNA test improves neoplasia diagnosis rates among colonoscopists with lower baseline adenoma detection rates, independent of withdrawal time.

Determining efficacy of dynamic multimedia bowel preparation instructions versus standard instructions on adenoma detection and patient reported measures (DIGICLEAN trial): a study protocol for a multicentre, colonoscopist-blinded, randomised controlled trial

IntroductionColonoscopy plays important roles in bowel cancer screening and treatment. Poor bowel preparation occurs in 20–25% of colonoscopies. This negatively impacts adenoma and sessile serrated lesion detection rates, procedural time,...

Revisiting bowel preparation: The quest for the optimal low‐residue diet duration

Revisiting bowel preparation: The quest for the optimal <scp>low‐residue</scp> diet duration

A111 CLINICAL AND PATHOLOGICAL OUTCOMES BETWEEN WATER EXCHANGE AND AIR INSUFFLATION USING NON-SEDATED EXTENDED FLEXIBLE SIGMOIDOSCOPY FOR AVERAGE RISK COLORECTAL CANCER SCREENING: PRELIMINARY FINDINGS FROM A RANDOMIZED CONTROL TRIAL

Abstract Background Colorectal cancer (CRC) is Canada's third most common cancer type and represents approximately 11% of all cancer deaths. While sedated colonoscopy or flexible sigmoidoscopy (FS) continues to be considered for CRC screening, these modalities have limitations and risks. Another unevaluated screening modality, known as an extended FS (EFS), attempts to capitalize on the benefits of a FS while minimizing the risks involved with a sedated colonoscopy. EFS provides a scope-based examination up to the splenic flexure and then attempts to examine beyond, often to the point of the caecum. Providing the option for EFS may produce improvements in the patient experience and performance, which may improve the feasibility of using scope-based screening more broadly in screening programs. Purpose To determine the extent non-sedated EFS using the water exchange method (WE) is associated with a complete colon examination compared to the traditional air insufflation (AI) method using CO2 in an average-risk screening population. Method This randomized control trial included 90 non-sedated participants, screened by trained general surgery and gastroenterology clinicians at Kelowna General Hospital, British Columbia, Canada, using two different scope insufflation techniques, WE and AI. The primary outcome of interest was the cecal intubation rates (CIR), while secondary outcomes included the adenoma detection rate (ADR) and reported pain scores. Other metrics, such as patient satisfaction rates, sessile serrated adenoma detection rates (SSADR), and serrated lesion detection rates (SLDR) were also recorded. Result(s) The demographic characteristics between the WE and AI groups were statistically similar, with the mean age of participants being 58 and 57, respectively. During the study period, four endoscopists performed the EFS. There were higher initial satisfaction rates in the WE group vs the AI (95% vs 77%, satisfaction of ≥ 9/10 p = 0.028). CIR and ADR were similar between the WE and AI group (CIR = 93% vs 91%, p = 0.710), (ADR = 40% vs 34%, p = 0.660). The SSADR and SLDR were also similar between the WE and AI group (SSADR = 21% vs 14%, p = 0.408), (SLDR = 42% vs 36%, p = 0.528). Conclusion(s) EFS without sedation using either technique exceeds quality benchmarks recommended for sedated screening colonoscopy while maintaining adequate patient safety and comfort. The WE method optimizes a patient's overall experience making a strategy of average risk colorectal cancer screening with non-sedated WE EFS feasible. Please acknowledge all funding agencies by checking the applicable boxes below CAG, Other Please indicate your source of funding; Kelowna General Hospital, Interior Health Disclosure of Interest None Declared

Sessile serrated lesion detection rates continue to increase: 2008-2020.

Background and study aims We assessed sessile serrated lesion detection rate (SSLDR) at a large academic medical center from 2008 to 2020 and modeled a local, aspirational target SSLDR. We also assessed SSLDRs among all gastroenterology fellows to better understand the relationship between SSLDRs and total colonoscopies performed. Patients and methods SSL-positive pathology results were flagged from a dataset composed of all screening colonoscopies for average-risk patients from 2008 to 2020. Unadjusted SSLDRs were calculated for individual endoscopists by year. A mixed effects logistic regression was used to estimate the log odds of SSL detection, with one model estimating division-wide predictors of SSL detection and a second model focused exclusively on colonoscopies performed by fellows. Model-adjusted SSLDRs were estimated for all 13 years and across both categories of all endoscopists and fellows only. Results Adjusted SSLDRs showed a consistent improvement in SSLDR from a low of 0.37 % (95 % confidence interval [CI]: 0.10-0.63) in 2008 to a high of 7.94 % (95 % CI: 6.34-9.54) in 2020. Among fellows only, the odds of SSL detection were significantly lower during their first year compared to their second year (OR: 0.80, 95 % CI: 0.66-0.98) but not significantly higher in their third year compared to their second year (OR: 1.09, 95 % CI: 0.85-1.4). Conclusions SSLDR increased steadily and significantly throughout our study period but variance among endoscopists persists. The peak SSLDR from 2020 of 7.94 % should serve as the local aspirational target for this division's attendings and fellows but should be continuously reevaluated.

Effect of add-on devices with projections on screening colonoscopy: a systematic review and meta-analysis.

Add-on devices with projections, e.g., Endocuff, Endocuff Vision, EndoRings, and Wingcap, placed on the distal tip of the colonoscope promise to improve the detection of precancerous lesions. We performed a meta-analysis to evaluate the performance of these devices exclusively among individuals undergoing colonoscopy for screening purpose. A computerized literature search was performed across MEDLINE and Cochrane Library databases for randomized controlled trials that compared standard colonoscopy (SC) to procedures using add-on devices. The primary outcome was adenoma detection rate (ADR), while secondary outcomes included polyp detection rate (PDR), advanced ADR (AADR), and sessile serrated lesion detection rate (SSLDR). The effect size on study outcomes was calculated using a random-effects model and presented as the risk ratio (RR) and 95% confidence interval (CI). Seven studies enrolling a total of 5785 patients were included. The use of add-on-devices with projections was associated with a higher ADR compared to SC: 45.9% vs. 41.1%; RR 1.18, 95%CI 1.02-1.37; P=0.03; I2=79%. Although PDR was higher in screening colonoscopies assisted by add-on devices as compared to SC, the difference failed to reach significance: 55.1% vs. 50.8%; RR 1.10, 95%CI 0.96-1.26; P=0.17; I2=75%. No difference was found between procedures assisted by add-on devices with projections and SC colonoscopies in terms of AADR (18.5% vs. 17.6%; RR 1.00, 95%CI 0.79-1.27; P=0.98; I2=56%) or SSLDR (6.8% vs. 5.8%; RR 1.17, 95%CI 0.95-1.44; P=0.15; I2=0%). Colonoscopy assisted by add-on devices with projections achieves a better ADR compared to SC among individuals undergoing screening for bowel cancer.

Quality of colonoscopy performed by medical or surgical specialists and trainees in five Australian hospitals.

Ensuring colonoscopy procedure quality is vital to the success of screening and surveillance programmes for bowel cancer in Australia. However, the data on the performance of quality metrics, through adequate adenoma detection, bowel preparation, and procedure completion rates, in the Australian public sector is limited. Understanding these can inform quality improvement to further strengthen our capacity for prevention and early detection of colorectal cancer. To determine the quality of colonoscopy in Australian teaching hospitals and their association with proceduralist specialty, trainee involvement, and location. We retrospectively evaluated 2443 consecutive colonoscopy procedure reports from 1 January to 1 April, 2018 from five public teaching tertiary hospitals in Australia (median 60 years old, 49% male). Data for bowel preparation quality, procedure completion rates, and detection rates of clinically significant adenomas, conventional adenomas, and serrated lesions was collected and compared to national criteria for quality in colonoscopy. Participating hospital, proceduralist specialty, and trainee involvement indicators were used for stratification. Data was analysed using Chi-squared tests of independence, Mann-Whitney U, One-way ANOVA, and multivariate binary logistic regression. Fifty-two point two percent (n = 1276) and 43.3% (n = 1057) were performed by medical and surgical proceduralists respectively, whilst 29.8% (n = 728) involved a trainee. Inadequate bowel preparation affected 7.3% of all procedures. The procedure completion rate was 95.1%, which increased to 97.5% after adjustment for bowel preparation quality. The pooled cancer, adenoma, and serrated lesion detection rates for all five hospitals were 3.5%, 40%, and 5.9% respectively. Assessed hospitals varied significantly by patient age (P < 0.001), work-force composition (P < 0.001), adequacy of bowel preparation (P < 0.001), and adenoma detection rate (P < 0.001). Two hospitals (40%) did not meet all national criteria for quality, due to a procedure completion rate of 94.5% or serrated lesion detection rate of 2.6%. Although lower than the other hospitals, the difference was not significant. Compared with surgical specialists, procedures performed by medical specialists involved older patients [65 years (inter-quartile range, IQR 58-73) vs 64 years (IQR 56-71); P = 0.04] and were associated with a higher adenoma detection rate [odds ratio (OR) 1.53; confidence interval: 1.21-1.94; P < 0.001]. Procedures involving trainee proceduralists were not associated with differences in the detection of cancer, adenoma, or serrated lesions, compared with specialists, or according to their medical or surgical background. On multivariate analysis, cancer detection was positively associated with patient age (OR 1.04; P < 0.001) and negatively associated with medical compared to surgical proceduralists (OR 0.54; P = 0.04). Conventional adenoma detection rates were independently associated with increasing patient age (OR 1.04; P < 0.001), positively associated with medical compared to surgical proceduralists (OR 1.41; P = 0.002) and negatively associated with male gender (OR 0.53; P < 0.001). Significant differences in the quality of colonoscopy in Australia exist, even when national benchmarks are achieved. The role of possible contributing factors, like procedural specialty and patient gender need further evaluation.

Adenoma detection rate is enough to assess endoscopist performance: a population-based observational study of FIT-positive colonoscopies.

Background and study aims Neoplasia-related indicators, such as adenoma detection rate (ADR), are a priority in the quality improvement process for colonoscopy. Our aim was to assess and compare different detection and characterization indicators in fecal immunochemical test (FIT)-positive colonoscopies, to determine associated factors, and to propose benchmarks. Patients and methods Retrospective analysis of prospectively collected data from all colonoscopies performed between 2015 and 2019 after a positive quantitative FIT in the population-based colorectal cancer screening program conducted in Alsace, part of the French national program. Detection indicators included ADR, mean number of adenomas per colonoscopy, and proximal serrated lesion (SL) detection rate. Characterization indicators included rate of non-neoplastic polyp (NNP) detection. Results Overall, 13,067 FIT-positive colonoscopies were evaluated, performed by 80 community gastroenterologists. The overall ADR was 57.6 %, and a 10 µg/g increase in fecal hemoglobin concentration was significantly associated with higher ADR (odds ratio [95 % confidence interval] = 1.02 [1.02–1.03]). Endoscopists whose ADR was ≥ 55 % were high detectors for all neoplasia, including proximal SLs and number of adenomas. The rate of detection of NNPs was 39.5 % in highest detectors (ADR > 70 %), significantly higher than in lower detectors (21.4 %) ( P < 0.001). There was a strong correlation between detection and characterization indicators, e. g. between rates of detection of proximal SLs and NNPs (Pearson = 0.73; P < 0.01). Conclusions A single indicator, ADR, is enough to assess endoscopist performance for both detection and characterization in routine practice provided the minimum target standard is raised and a maximum standard is added: 55 % and 70 % for FIT-positive colonoscopies, respectively.

Adenoma and Sessile Serrated Lesion Detection Rates at Screening Colonoscopy for Ages 45–49 Years vs Older Ages Since the Introduction of New Colorectal Cancer Screening Guidelines

All major U.S. guidelines now endorse average-risk colorectal cancer (CRC) screening at 45-49 years of age. Concerns exist that endoscopic capacity may be strained, that low-risk persons may self-select for screening, and that calculations of the adenoma detection rate may be diluted. We analyzed age-specific screening colonoscopy volumes and lesion detection rates before vs after the endorsement of CRC screening at 45-49 years of age. We compared colonoscopy volumes and lesion detection rates in our healthcare system during period 1 (October 2017 to December 2018), before the first change in guidelines, vs period 2 (January 2019 to August 2021), the era of new guidelines. The proportion of first-time screening colonoscopies performed in 45- to 49-year-olds increased from 3.5% to 11.6% (relative risk, 3.36; 95% CI, 2.45-4.61). The period 2 detection rates for adenoma, advanced adenoma, sessile serrated lesion, advanced sessile serrated lesion, adenomas per colonoscopy, and lesions per colonoscopy were very similar for 45- to 49-year-olds (34.3%, 6.3%, 8.6%, 2.9%, 0.58, and 0.69, respectively) and 50- to 54-year-olds (38.2%, 5.8%, 9.4%, 3.0%, 0.63, and 0.76, respectively) at first-time screening, and for 60- to 64-year-olds at rescreening (33.4%, 6.1%, 7.2%, 2.3%, 0.61, and 0.70, respectively). All detection rates, adenomas per colonoscopy, and lesions per colonoscopy increased from period 1 to period 2 (eg, overall adenoma detection rate 35.1% vs 42.6%; P < .0001), without any decreases among 45- to 49-year-olds. In our healthcare system, a lower CRC screening initiation age has modestly affected colonoscopy volume by age without compromising screening yield. Lesion detection rates, including for advanced adenomas, in average-risk 45- to 49-year-olds approximate those in 50- to 54-year-olds at first-time screening and 60- to 64-year-olds at rescreening. National monitoring is needed to assess fully the impact of lowering the CRC screening initiation age.

Natural Language Processing for Assessing Quality Indicators in Free-Text Colonoscopy and Pathology Reports: Development and Usability Study.

BackgroundManual data extraction of colonoscopy quality indicators is time and labor intensive. Natural language processing (NLP), a computer-based linguistics technique, can automate the extraction of important clinical information, such as adverse events, from unstructured free-text reports. NLP information extraction can facilitate the optimization of clinical work by helping to improve quality control and patient management.ObjectiveWe developed an NLP pipeline to analyze free-text colonoscopy and pathology reports and evaluated its ability to automatically assess adenoma detection rate (ADR), sessile serrated lesion detection rate (SDR), and postcolonoscopy surveillance intervals.MethodsThe NLP tool for extracting colonoscopy quality indicators was developed using a data set of 2000 screening colonoscopy reports from a single health care system, with an associated 1425 pathology reports. The NLP system was then tested on a data set of 1000 colonoscopy reports and its performance was compared with that of 5 human annotators. Additionally, data from 54,562 colonoscopies performed between 2010 and 2019 were analyzed using the NLP pipeline.ResultsThe NLP pipeline achieved an overall accuracy of 0.99-1.00 for identifying polyp subtypes, 0.99-1.00 for identifying the anatomical location of polyps, and 0.98 for counting the number of neoplastic polyps. The NLP pipeline achieved performance similar to clinical experts for assessing ADR, SDR, and surveillance intervals. NLP analysis of a 10-year colonoscopy data set identified great individual variance in colonoscopy quality indicators among 25 endoscopists.ConclusionsThe NLP pipeline could accurately extract information from colonoscopy and pathology reports and demonstrated clinical efficacy for assessing ADR, SDR, and surveillance intervals in these reports. Implementation of the system enabled automated analysis and feedback on quality indicators, which could motivate endoscopists to improve the quality of their performance and improve clinical decision-making in colorectal cancer screening programs.