Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence (AI)-assisted optical ...diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs).
Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations PIVI-1 threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines.
Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %-93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %-98.9 %) and 92.6 % (95 %CI 90.0 %-95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %-87.3 %) than for experts (91.9 %, 95 %CI 88.5 %-94.5 %); however, nonexperts quickly approached the performance levels of experts over time.
AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopists' high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.
Linked color imaging (LCI) is a newly developed image-enhancing endoscopy technology that provides bright endoscopic images and increases color contrast. We investigated whether LCI improves the ...detection of neoplastic lesions in the right colon when compared with high definition white-light imaging (WLI).
Consecutive patients undergoing colonoscopy were randomized (1:1) after cecal intubation into right colon inspection at first pass by LCI or by WLI. At the hepatic flexure, the scope was reintroduced to the cecum under LCI and a second right colon inspection was performed under WLI in previously LCI-scoped patients (LCI-WLI group) and vice versa (WLI-LCI group). Lesions detected on first- and second-pass examinations were used to calculate detection and miss rates, respectively. The primary outcome was the right colon adenoma miss rate.
Of the 600 patients enrolled, 142 had at least one adenoma in the right colon, with similar right colon adenoma detection rates (r-ADR) in the two groups (22.7 % in LCI-WLI and 24.7 % in WLI-LCI). At per-polyp analysis, double inspection of the right colon in the LCI-WLI and WLI-LCI groups resulted in an 11.8 % and 30.6 % adenoma miss rate, respectively (
< 0.001). No significant difference in miss rate was found for advanced adenomas or sessile serrated lesions. At per-patient analysis, at least one adenoma was identified in the second pass only (incremental ADR) in 2 of 300 patients (0.7 %) in the LCI - WLI group and in 13 of 300 patients (4.3 %) in the WLI - LCI group (
= 0.01).
LCI could reduce the miss rate of neoplastic lesions in the right colon.
Single-center studies, which were retrospective and/or involved unblinded colonoscopists, have suggested that water exchange, but not water immersion, compared with air insufflation significantly ...increases the adenoma detection rate (ADR), particularly in the proximal and right colon. Head-to-head comparison of the three techniques with ADR as primary outcome and blinded colonoscopists has not been reported to date. In a randomized controlled trial with blinded colonoscopists, we aimed to evaluate the impact of the three insertion techniques on ADR.
A total of 1224 patients aged 50 - 70 years (672 males) and undergoing screening colonoscopy were randomized 1:1:1 to water exchange, water immersion, or air insufflation. Split-dose bowel preparation was adopted to optimize colon cleansing. After the cecum had been reached, a second colonoscopist who was blinded to the insertion technique performed the withdrawal. The primary outcome was overall ADR according to the three insertion techniques (water exchange, water immersion, and air insufflation). Secondary outcomes were other pertinent overall and right colon procedure-related measures.
Baseline characteristics of the three groups were comparable. Compared with air insufflation, water exchange achieved a significantly higher overall ADR (49.3 %, 95 % confidence interval CI 44.3 % - 54.2 % vs. 40.4 % 95 %CI 35.6 % - 45.3 %;
= 0.03); water exchange showed comparable overall ADR vs. water immersion (43.4 %, 95 %CI 38.5 % - 48.3 %;
= 0.28). In the right colon, water exchange achieved a higher ADR than air insufflation (24.0 %, 95 %CI 20.0 % - 28.5 % vs. 16.9 %, 95 %CI 13.4 % - 20.9 %;
= 0.04) and a higher advanced ADR (6.1 %, 95 %CI 4.0 % - 9.0 % vs. 2.5 %, 95 %CI 1.2 % - 4.6 %;
= 0.03). Compared with air insufflation, the mean number of adenomas per procedure was significantly higher with water exchange (
= 0.04). Water exchange achieved the highest cleanliness scores (overall and in the right colon). These variables were comparable between water immersion and air insufflation.
The design with blinded observers strengthens the validity of the observation that water exchange, but not water immersion, can achieve significantly higher adenoma detection than air insufflation. Based on this evidence, the use of water exchange should be encouraged.Trial registered at ClinicalTrials.gov (NCT02041507).
Blue-light imaging (BLI) is a chromoendoscopy technique that uses direct (not filtered) emission of blue light with short wavelength (410 nm) to increase visibility of microvascular pattern and ...superficial mucosa. A BLI-based classification system for colorectal polyps (also called BLI Adenomas Serrated International Classification, BASIC) has been created and was validated using still images or short videos. We aimed to validate BASIC in a clinical practice setting, using thresholds recommended by the American Society for Gastrointestinal Endoscopy for the resect and discard strategy as the reference standard.
We studied 333 patients (mean age, 62.7±8.1 y; 176 men) who underwent screening colonoscopy from January through July 2019. Six endoscopists trained in BASIC participated in the study. All detected diminutive polyps were characterized by real-time BLI and categorized as adenoma or non-adenoma according to BASIC. All polyps were removed and evaluated by histopathology. The BLI-directed surveillance intervals (based on high-confidence characterization of polyps 5 mm or smaller and pathology feature for others) were compared with histology-directed surveillance intervals, according to United States Multi-society Task Force and European Society of Gastrointestinal Endoscopy recommendations. We calculated negative-predictive values of optical real-time analysis of diminutive rectosigmoid adenomas.
When we applied BASIC, 748 polyps smaller than 5 mm were categorized with 89% accuracy (95% CI, 85.9%-90.6%). BLI-directed surveillance was correct for 90% of patients according to the United States Multi-society task force criteria (95% CI, 86%-93%) and for 96% of patients according to European Society of Gastrointestinal Endoscopy criteria (95% CI, 93%-97%). The negative-predictive value for 302 polyps smaller than 5 mm, located in the rectosigmoid colon and evaluated with high confidence, based on histologic features of adenomatous polyps, was 91% (95% CI, 85%-95%).
Our analysis of data from 333 patients undergoing screen colonoscopies supports the validity of BASIC discriminating diminutive colorectal polyps with histologic features of adenomas from non-adenomas. This allows for the implementation of the resect and discard strategy based on BLI in clinical practice. ClinicalTrials.gov no: NCT03746171.
Water-aided colonoscopy: a systematic review Leung, Felix W., MD; Amato, Arnaldo, MD; Ell, Christian, MD, PhD ...
Gastrointestinal endoscopy,
09/2012, Letnik:
76, Številka:
3
Journal Article
Recenzirano
Background Water-aided methods for colonoscopy are distinguished by the timing of removal of infused water, predominantly during withdrawal (water immersion) or during insertion (water exchange). ...Objective To discuss the impact of these approaches on colonoscopy pain and adenoma detection rate (ADR). Design Systematic review. Setting Randomized, controlled trial (RCT) that compared water-aided methods and air insufflation during colonoscope insertion. Patients Patients undergoing colonoscopy. Intervention Medline, PubMed, and Google searches (January 2008-December 2011) and personal communications of manuscripts in press were considered to identify appropriate RCTs. Main Outcome Measurements Pain during colonoscopy and ADR. RCTs were grouped according to whether water immersion or water exchange was used. Reported pain scores and ADR were tabulated based on group assignment. Results Pain during colonoscopy is significantly reduced by both water immersion and water exchange compared with traditional air insufflation. The reduction in pain scores was qualitatively greater with water exchange as compared with water immersion. A mixed pattern of increases and decreases in ADR was observed with water immersion. A higher ADR, especially proximal to the splenic flexure, was obtained when water exchange was implemented. Limitations Differences in the reports limit application of meta-analysis. The inability to blind the colonoscopists exposed the observations to uncertain bias. Conclusion Compared with air insufflation, both water immersion and water exchange significantly reduce colonoscopy pain. Water exchange may be superior to water immersion in minimizing colonoscopy discomfort and in increasing ADR. A head-to-head comparison of these 3 approaches is required.
Linked-color imaging (LCI), a new image-enhancing technology emphasizing contrast in mucosal color, has been demonstrated to substantially reduce polyp miss rate as compared with standard white-light ...imaging (WLI) in tandem colonoscopy studies. Whether LCI increases adenoma detection rate (ADR) remains unclear.
Consecutive subjects undergoing screening colonoscopy after fecal immunochemical test (FIT) positivity were 1:1 randomized to undergo colonoscopy with LCI or WLI, both in high-definition systems. Insertion and withdrawal phases of each colonoscopy were carried out using the same assigned light. Experienced endoscopists from 7 Italian centers participated in the study. Randomization was stratified by gender, age, and screening round. The primary outcome measure was represented by ADR.
Of 704 eligible subjects, 649 were included (48.9% men, mean age ± standard deviation, 60.8 ± 7.3 years) and randomized to LCI (n = 326) or WLI (n = 323) colonoscopy. The ADR was higher in the LCI group (51.8%) than in the WLI group (43.7%) (relative risk, 1.19; 95% confidence interval, 1.01-1.40). The proportions of patients with advanced adenomas and sessile serrated lesions were, respectively, 21.2% and 8.6% in the LCI arm and 18.9% and 5.9% in the WLI arm (not significant for both comparisons). At multivariate analysis, LCI was independently associated with ADR, along with male gender, increasing age, and adequate (Boston Bowel Preparation Scale score ≥6) bowel preparation. At per-polyp analysis, the mean ± standard deviation number of adenomas per colonoscopy was comparable in the LCI and WLI arms, whereas the corresponding figures for proximal adenomas was significantly higher in the LCI group (.72 ± 1.2 vs .55 ± 1.07, P = .05)
In FIT-positive patients undergoing screening colonoscopy, the routine use of LCI significantly increased the ADR. (Clinical trial registration number: NCT03690297.)
Background Uncontrolled data suggest that warm water infusion (WWI) instead of air insufflation (AI) during the insertion phase of unsedated colonoscopy improves patient tolerance and satisfaction. ...Objective We tested the hypothesis that water could increase the proportion of patients able to complete unsedated colonoscopy and improve patient tolerance compared with the conventional procedure. Design Randomized, controlled trial. Setting Single center, community hospital. Patients Consecutive outpatients agreeing to start colonoscopy without premedication. Methods Patients were randomly assigned to either WWI or AI insertion phase of colonoscopy. Sedation and/or analgesia were administered on patient request if significant pain or discomfort occurred. Main Outcome Measurements Percentage of patients requiring sedation/analgesia. Pain and tolerance scores were assessed at discharge by using a 100-mm visual analog scale. Results A total of 230 subjects (116 in the WWI group and 114 in the AI group) were enrolled. Intention-to-treat analysis showed that the proportion of patients requesting sedation/analgesia during the procedure (main outcome measurement) was 12.9% in the WWI group and 21.9% in AI group ( P = .07). Cecal intubation rates were 94% in the WWI group and 95.6% in the AI group ( P = .57). Median (interquartile range) scores for pain were 28 (12-44) and 39 (14-54) in WWI and AI groups, respectively ( P = .05); corresponding figures for tolerance were 10 (3-18) and 14 (5-42), respectively ( P = .01). The adenoma detection rates were 25% and 40.1% for the WWI and AI groups, respectively ( P = .013). Limitations Single-center study, endoscopists not blinded to randomization. Conclusions WWI instead of AI is not associated with a statistically significant decrease in the number of patients requiring on-demand sedation, although it significantly improves the overall patient tolerance of colonoscopy. The finding of a lower adenoma detection rate in the WWI group calls for further evaluations. (Clinical trial registration number: NCT00905554 ).
It has been proposed that the use of narrow-band imaging (NBI) for real-time histological assessment to determine postpolypectomy surveillance intervals is a cost-effective approach to the management ...of diminutive polyps. However, significant discrepancies in NBI performance have been observed among endoscopists; hence, professional societies recommend training, monitoring, and auditing. The aim of the present study was to evaluate the performance of real-time optical diagnosis for diminutive polyps after the inclusion of this approach in an internal quality assurance program, in order to assess its applicability in clinical practice Patients and methods: Four endoscopists attended periodic training sessions on NBI assessment of polyp histology before and during the study. Performance was audited and periodic feedback was provided. The accuracy of high-confidence NBI evaluation for polyps ≤ 5 mm in predicting surveillance intervals according to the European and US guidelines, and the negative predictive value (NPV) for adenoma in the rectosigmoid were calculated and compared with recommended thresholds (90 % agreement and 90 % NPV, respectively).
Overall, 284 outpatients (mean age 61.3 ± 18.2 years; 63 % males) were enrolled. A total of 656 polyps were detected, 465 of which (70.9 %) were diminutive (70.5 % adenomas). Sensitivity, specificity, positive and negative predictive values, and accuracy of high-confidence NBI predictions for adenoma in diminutive lesions were 95.3 %, 83.5 %, 93.5 %, 87.6 %, and 91.9 %, respectively. High-confidence characterization of diminutive polyps predicted the correct surveillance interval in 95.8 % and 93.3 % of cases according to European and American guidelines, respectively. NPV for adenoma in the rectosigmoid was 91.3 %
For community settings in which endoscopists are adequately trained and performance is periodically audited, real-time optical diagnosis for diminutive polyps is sufficiently accurate to avoid postpolypectomy histological examination of resected lesions, or to leave rectosigmoid hyperplastic polyps in place. Trial registered at ClinicalTrials.gov (NCT02196402).
Background
Underwater endoscopic mucosal resection without submucosal injection has been described for removing large flat colorectal lesions.
Objective
We aim to evaluate the reproducibility of this ...technique in terms of ease of implementation, safety and efficacy.
Methods
A prospective observational study of consecutive underwater endoscopic mucosal resection in a community hospital was performed.
Results
From September 2014 to April 2015, 25 flat or sessile colorectal lesions (median size 22.8 mm, range 10–50 mm; 18 placed in the right colon) were removed in 25 patients. Two of the lesions were adenomatous recurrences on scar of prior resection and one was a recurrence on a surgical anastomosis. The resection was performed en bloc in 76% of the cases. At the pathological examination, 14 lesions (56%) had advanced histology and seven (28%) were sessile serrated adenomas (two with high-grade dysplasia). Complete resection was observed in all the lesions removed en bloc. Intra-procedural bleeding was observed in two cases; both were managed endoscopically and were uneventful. No major adverse events occurred.
Conclusion
Underwater endoscopic mucosal resection appears to be an easy, safe and effective technique in a community setting. Further studies evaluating the efficacy of the technique (early and late recurrence), as well as comparing it with traditional mucosal resection, are warranted.
Objectives
To generate a prognostic model based on a nomogram for adverse event (AE) prediction after lumen‐apposing metal stents (LAMS) placement in patients with pancreatic fluid collections (PFC).
...Methods
Data from a large multicenter series of PFCs treated with LAMS placement were retrieved. AE (overall and excluding mild events) prediction was calculated through a logistic regression model and a nomogram was created and internally validated after bootstrapping. Results were expressed in terms of odds ratio (OR) and 95% confidence interval (CI). Discrimination was assessed by c‐statistics and calibrated by comparing deciles of predicted and observed ORs.
Results
Overall, 516 patients were included (males 68%, mean age 61.6 ± 15.2 years). PFCs were predominantly walled‐off necrosis (52.1%). Independent predictors of AE occurrence were injury of main pancreatic duct (OR in the case of leak 2.51, 95% CI 1.06–5.97, P = 0.03; OR in the case of complete disruption 2.61, 1.53–4.45, P = 0.01), abnormal vessels (OR in the case of perigastric varices 2.90, 1.31–6.42, P = 0.008; OR in the case of pseudoaneurysm 2.99, 1.75–11.93, P = 0.002), using a multigate technique (OR 3.00, 1.28–5.24; P = 0.05), and need of percutaneous drainage (OR 2.81, 1.03–7.65, P = 0.04). By nomogram, a score beyond 200 points corresponded to a 50% probability of AE occurrence. The model was confirmed even when excluding mild AEs and it showed optimal discrimination (c‐index 76.8%, 95% CI 74–79), confirmed after internal validation.
Conclusion
Patients with preprocedural evidence of pancreatic duct leak/disruption, vessel alteration, requiring percutaneous drainage or a multigate technique are at higher risk for AE.
PDF
