Effect of a novel spatial-temporal computer-aided detection system on adenoma detection during colonoscopy: A multicenter, randomized controlled trial

Effect of a novel spatial-temporal computer-aided detection system on adenoma detection during colonoscopy: A multicenter, randomized controlled trial | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Effect of a novel spatial-temporal computer-aided detection system on adenoma detection during colonoscopy: A multicenter, randomized controlled trial Pengju Wang, Longsong Li, Long Rong, Peng Jin, Wenhui Zhang, Bo Zhang, and 10 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4389606/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Background Most computer-aided detection (CADe) systems depend on the spatial information from static images rendering them unreliable for real-time diagnosis. This research aims to assess the performance of a novel spatial-temporal CADe system. Methods This randomized study recruited patients 18 years or older scheduled for colonoscopy at four endoscopy centers from June 2023 to September 2023. Participants were randomly assigned to receive CADe colonoscopy or conventional colonoscopy. The primary outcome was ADR. Furthermore, the correlation between endoscopists’ acceptance rate of the CADe system and ADR was observed. Results Among 3317 patients, the ADR was 32.1% in the CADe group and 24.7% in the control group ( P < 0.001). The CADe group detected significantly more adenomas < 10 mm and flat-type adenomas [(23.3% vs. 18.4%, P = 0.001) and (15.5% vs. 9.9%, P = 0.001), respectively]. In addition, a significant correlation (r = 0.916, P < 0.001) was observed between the grit score and ADR with the CADe system. Conclusion The spatial-temporal CADe system significantly improved overall polyp and adenoma detection, especially for diminutive and flat-type lesions. Moreover, endoscopists with a greater propensity to embrace the CADe system tend to detect a higher proportion of adenomas during colonoscopy. artificial intelligence adenoma detection rate CADe colonoscopy Figures Figure 1 Figure 2 Figure 3 Figure 4 Introduction Intestinal adenomatous polyps are recognized as precancerous lesions that may progress to colorectal cancer (CRC) if timely intervention is not implemented [ 1 ] . Colonoscopy screening for polyps and adenomas has been demonstrated to effectively reduce the incidence of colorectal neoplasia [ 2 , 3 ] . A substantial cohort study highlighted the capacity of colonoscopy screening to reduce CRC mortality by 68% [ 4 ] . However, conventional examinations are subject to multiple variables, encompassing factors such as the procedural technique employed by the endoscopists, their level of experience, potential fatigue, and the quality of bowel preparation. 27% of adenomas are overlooked during conventional colonoscopy, with a potentially more pronounced omission rate for diminutive adenomas (≤ 5 mm), constituting a primary contributor to interval CRC [ 5 ] . Studies indicate that an increase in the ADR of 1.0% corresponds to a 3% reduction in the associated risk of interval CRC [ 6 ] . Recent studies have confirmed the efficacy of artificial intelligence (AI) based on conventional polyp detection algorithms. These studies have shown that AI has the potential to significantly improve both the ADR and the polyp detection rate (PDR) [ 7 , 8 ] . However, most polyp detection algorithms focus solely on the spatial dimension to capture the appearance and alterations of suspected polyps over time. Consequently, prevalent shortcomings include a notable incidence of false positives and negatives in extant algorithms, impacting the application of CADe systems in real-time diagnosis [ 9 ] . In addition, most studies have focused on the overall improvement in ADRs associated with the use of CADe systems. Nonetheless, the extent to which endoscopists accept the CADe systems differs. There was no reported link between the enhancement of ADR and endoscopists’ acceptance of the CADe systems. In response to the limitations inherent in extant algorithms, we introduced a pioneering CADe system, denominated DeFrame, distinguished by incorporating a sophisticated dual-flow fusion algorithm. Notably, this system assimilates spatial data and integrates temporal dimension insights to refine the accuracy of real-time polyp diagnosis within complex intestinal environments [ 10 ] . This study was designed to evaluate whether the CADe system could improve polyp and adenoma detection during colonoscopy. Moreover, the personality trait grit was assessed as an indicator of the endoscopists’ acceptance of the CADe system. The correlation between grit and the AI-assisted ADR was also assessed. Patients and methods The CADe system Colonoscopy signals consist of successive frames, both spatial and temporal. Most state-of-the-art algorithms concentrate solely on spatial data and excel in still images [ 11 ] . However, the efficiency of the CADe system decreases when the intestinal environment is intricate or undergoes rapid changes. Consequently, we designed a CADe system named Deframe to retrieve spatial and temporal data [ 10 ] . DeFrame, validated with a dataset of 20,660 images (13,347 typical and 7,313 atypical), achieved robust polyp detection performance, boasting a recall of 95.43% and a precision of 92.12%. The system excels in rapid polyp identification, as indicated by a bounding box on the endoscopy screen within 25 ± 9 ms upon detection (Fig. 1 ). Study population The research was conducted at four endoscopy centers in China: the First Medical Center of PLAGH, Peking University First Hospital, the Seventh Medical Center of PLAGH, and Daxing People's Hospital. Eligible participants aged 18 years and older undergoing screening, surveillance, or diagnostic colonoscopy at these centers were recruited and included between June 2023 and September 2023. The exclusion criteria included a history of inflammatory bowel disease (IBD), familial adenomatous polyposis, prior colorectal resection, or Peutz–Jeghers syndrome. Moreover, patients were excluded after randomization if the cecum could not be reached or if they had poor bowel preparation (Boston Bowel Preparation Scale (BBPS) score < 6). All included subjects provided informed consent before participating in the study. Study design We designed a single-blind, randomized parallel-group study, and this trial was registered at http://www.chictr.org.cn (ChiCTR2300071612). Subjects were stratified based on the clinical trial center and the clinical indication for colonoscopy and then allocated to either the CADe group (CADe colonoscopy) or the control group (conventional colonoscopy) at a 1:1 ratio. Endoscopists were conscious of the study arm to which each subject was assigned, while the subjects remained unaware. The trial involved 25 experienced endoscopists who were daily allocated to the endoscopy room, either with or without CADe. All procedures were performed with an EVIS LUCERA ELITE 290 (Olympus Co., Tokyo) system. The operation time, bowel preparation procedure, polyp characteristics (number, size, location), and withdrawal time were documented for each patient. In both the control and CADe groups, all polyps were removed or biopsied, except tiny, hyperplastic polyps in the rectum, which were typically left intact. All polyp specimens were distinctly marked and subjected to histological analysis. The Short Grit Scale (GRIT-S), an 8-item validated questionnaire, was used to measure grit levels, with participants rating it on a 5-point Likert scale as follows: “very much like me,” “mostly like me,” somewhat like me,” “not much like me,” and “not like me at all.” A total of four items underwent reverse coding. The individual scores were aggregated and subsequently divided by 8. The final scores ranged between 1 (not at all gritty) and 5 (extremely gritty). Throughout the research, grit served as a continuous variable. Histopathology Resected and biopsy specimens were fixed in distinct containers containing a 10% buffered formalin solution. Following fixation, standard histopathological procedures were applied for processing and staining. Expert pathologists, who were unbiased to the assigned examination mode, conducted the evaluation. Lesions were systematically categorized based on the Paris classification. Outcome measures The primary outcome focused on comparing the ADR between the two study arms. The ADR was defined as the proportion of patients exhibiting at least one histologically confirmed adenoma or carcinoma. The secondary outcomes included the PDR and the counts of adenomas and polyps detected per colonoscopy (APC and PPC). Additionally, the detection rates of polyps of varying sizes (diminutive [≤ 5 mm], small [6–9 mm], and large [≥ 10 mm]) and of varying sites (proximal colon [proximal to the splenic flexure] and distal colon [descending colon to rectum]) were assessed. Subgroup analyses were also conducted based on age, sex, and indication for colonoscopy. A correlation between each endoscopist's grit score and the AI-assisted ADR was observed. Statistical analysis Based on a relevant prior study, we estimated that the ADR for standard colonoscopy was 24% in routine practice. In comparison, the ADR for real-time computer-aided detection system colonoscopy is anticipated to be 30% [ 12 ] . Based on a two-sided test with a 5% significance level and 80% power, the total sample size required for the study was 1712 patients. Assuming that the dropout rate from the analysis was 10%, an estimated enrollment of approximately 2000 patients was planned. The sample size calculation was conducted using an online power calculator. Analysis was performed for the specified outcome measures. Baseline characteristics were assessed for between-group differences utilizing the χ² test for categorical variables and the Mann‒Whitney U test for continuous variables. The impact of the CADe system on the ADR and PDR was evaluated using logistic regression analysis, whereas the effect on the APC and PPC was assessed through the Mann‒Whitney U test. Covariate-adjusted logistic regression and negative binomial regression models were developed, incorporating group differences as covariates. These models were intended to address potential confounding factors, including the indication for colonoscopy, body mass index (BMI), age, BBPS score, and sex. A significance level of less than 0.05 according to two-sided tests was used to indicate statistical significance. All analyses were conducted using SPSS version 24. Results Patient characteristics A total of 3554 eligible subjects were randomly allocated to either the control group (n = 1780) or the AI-assisted group (CADe group, n = 1774). As depicted in Fig. 2 , within the control group, 114 subjects were excluded for reasons such as no cecal intubation (n = 9), inadequate BBPS scores (n = 96), or suspected inflammatory bowel disease (IBD) (n = 9). In the CADe group, 123 subjects were excluded; 15 had no cecal intubation, 90 had inadequate BBPS scores, and 18 were suspected of having IBD. Finally, the analysis included 1666 subjects in the control group and 1651 in the CADe group. As outlined in Table 1 , no statistically significant differences in sex, age, or BMI were evident between the two groups. Furthermore, there were no notable disparities in clinical indications between the control group and the CADe group: 34.6% for diagnostic, 47.1% for screening, and 18.3% for surveillance in the control group, compared with 35.8% for diagnostic, 47.9% for screening, and 16.3% for surveillance in the CADe group. Similarly, no significant differences were observed in terms of withdrawal time (425.15 ± 58.52 seconds vs. 422.31 ± 53.62 seconds) or BBPS score (7.53 ± 0.9 vs. 7.50 ± 0.9) between the two groups. Table 1 Baseline characteristics of the subjects enrolled Characteristics Control group (n = 1666) CADe group (n = 1651) P value Age, mean (SD), y 51.67(12.8) 51.71(12.6) 0.917 Sex, No. (%) Male 907(54.4) 900(54.5) 0.967 Female 759(45.6) 751(45.5) Indication for colonoscopy, No. (%) Diagnose 577(34.6) 591(35.8) 0.303 Screening 784(47.1) 791(47.9) Surveillance 305(18.3) 269(16.3) BMI, mean (SD) 23.3 (3.5) 23.2 (3.6) BBPS score, mean (SD) 7.53(0.9) 7.50(0.9) 0.465 Left colon bowel preparation 2.63(0.48) 2.61(0.48) 0.481 Transverse colon bowel preparation 2.55(0.49) 2.53(0.50) 0.252 Right colon bowel preparation 2.35(0.47) 2.36(0.48) 0.603 Withdrawal time, No. (%), sec 425.15(58.52) 422.31(53.62) 0.145 Per patient analysis As indicated in Table 2 , 528 out of 1651 subjects in the CADe group were diagnosed with at least one adenoma during colonoscopy, whereas 411 out of 1666 subjects in the control group were diagnosed, with an ADR of 32.1% or 24.7%, respectively. After adjustments for age, sex, and indication, the ADR was significantly greater in the CADe group than in the control group, a finding consistent with the PDR [51.3% (847/1651) vs. 44.1% (733/1666), P < 0.001]. Table 2 The detection rate of adenomas and polyps [n (%)] Control group (n = 1666) CADe group (n = 1651) Odds ratio (95% confidence interval) P value ADR 411(24.7) 528 (32.1) 1.439(1.236–1.675) < 0.001 Adenoma size category ≤ 5 mm 307(18.4) 384(23.3) 1.342(1.134–1.588) 0.001 6–9 mm 125(7.5) 196(11.9) 1.661(1.312–2.102) < 0.001 ≥ 10 mm 55(3.3) 76(4.6) 1.413(0.992–2.013) 0.054 Adenoma location Proximal colon 254(15.2) 329(19.9) 1.383(1.155–1.656) < 0.001 Distal colon 237(14.2) 305(18.5) 1.366(1.135–1.644) 0.001 Adenoma morphology a Ⅰp 22(1.3) 27(1.6) 1.242(0.705–2.190) 0.452 Ⅰsp 52(3.1) 59(3.6) 1.150(0.787–1.681) 0.469 Ⅰs 221(13.3) 288(17.4) 1.382(1.142–1.671) 0.001 Ⅱa 165(9.9) 256(15.5) 1.669(1.355–2.057) < 0.001 PDR 733(44.1) 847(51.3) 1.338(1.167–1.534) < 0.001 Poly size category ≤ 5 mm 629(37.8) 721(43.7) 1.278(1.112–1.468) 0.001 6–9 mm 186(11.2) 274(16.6) 1.583(1.296–1.934) < 0.001 ≥ 10 mm 72(4.3) 95(5.6) 1.306(0.952–1.792) 0.097 Polyp location Proximal colon 429(25.8) 505(30.6) 1.271(1.092–1.479) 0.002 Distal colon 501(30.1) 572(34.6) 1.233(1.066–1.426) 0.005 Polyp morphology a Ⅰp 31(1.9) 39(2.4) 1.276(0.792–2.055) 0.315 Ⅰsp 68(4.1) 90(5.5) 1.355(0.981–1.871) 0.064 Ⅰs 383(23.0) 455(27.6) 1.274(1.089–1.491) 0.002 Ⅱa 349(20.9) 458(27.7) 1.449(1.235-1.700) < 0.001 Regarding adenoma and polyp size, there were significant differences between the two groups for diminutive adenomas (≤ 5 mm) [23.3% vs. 18.4%, P = 0.001] and small adenomas (6–9 mm) [11.9% vs. 7.5%, P < 0.001]. This trend was also observed for diminutive polyps and small polyps. Lesions ≥ 10 mm in size, being larger, were more easily observable, resulting in no significant difference between the two groups. Concerning the location of the detected adenomas (Table 2 ), the proportion of patients with adenomas in the proximal and distal colon in the CADe group was significantly greater than that in the control group. Based on the lesion morphology, whether it was an adenoma or a polyp, significant differences were observed for types Is and Ⅱa between the CADe group and the control group. Per polyp analysis As illustrated in Table 3 , the APC was significantly greater in the CADe group than in the control group (0.52 vs. 0.39, P < 0.001). Similarly, PPC exhibited analogous findings, with a greater value in the CADe group than in the control group (0.99 vs. 0.83, P < 0.001). A noteworthy difference in the APC density was observed between the two groups for diminutive adenomas (0.32 vs. 0.25, P = 0.004) and small adenomas (0.15 vs. 0.09, P < 0.001). However, there was no significant difference in the percentage of patients with adenomas ≥ 10 mm. The APC density in both the proximal and distal colon was significantly greater in the CADe group than in the control group. Regarding the morphology of the adenomas, the APCs of type IIa adenomas in the CADe and control groups were 0.23 and 0.14, respectively ( P < 0.001). Similar trends were observed for polyp characteristics. Table 3 APC and PPC in the CADe group and control group [mean (SD)] Control group (n = 1666) CADe group (n = 1651) P value APC Mean ± SD 0.39 (1.01) 0.52 (0.85) < 0.001 M (Q1, Q3) 0 (0–0) 0(0–1) Adenoma size category ≤ 5mm Mean ± SD 0.25(0.62) 0.32(0.70) 0.004 M (Q1, Q3) 0 (0–0) 0 (0–0) 6-9mm Mean ± SD 0.09(0.37) 0.15(0.46) < 0.001 M (Q1, Q3) 0 (0–0) 0 (0–0) ≥ 10mm Mean ± SD 0.04(0.26) 0.05(0.26) 0.260 M (Q1, Q3) 0 (0–0) 0 (0–0) Adenoma location Proximal colon Mean ± SD 0.20(0.55) 0.28(0.67) < 0.001 M (Q1, Q3) 0 (0–0) 0 (0–0) Distal colon Mean ± SD 0.19(0.53) 0.25(0.60) 0.003 M (Q1, Q3) 0 (0–0) 0 (0–0) Adenoma morphology a Ip Mean ± SD 0.02(0.14) 0.02(0.15) 0.609 M (Q1, Q3) 0 (0–0) 0 (0–0) Isp Mean ± SD 0.04(0.22) 0.04(0.24) 0.467 M (Q1, Q3) 0 (0–0) 0 (0–0) Is Mean ± SD 0.20(0.59) 0.24(0.60) 0.059 M (Q1, Q3) 0 (0–0) 0 (0–0) IIa Mean ± SD 0.14(0.49) 0.23(0.64) < 0.001 M (Q1, Q3) 0 (0–0) 0 (0–0) PPC Mean ± SD 0.83(1.25) 0.99(1.36) < 0.001 M (Q1, Q3) 0 (0–1) 1(0–2) Polyp size category ≤ 5mm Mean ± SD 0.63(1.01) 0.71(1.04) 0.019 M (Q1, Q3) 0 (0–1) 0 (0–1) 6-9mm Mean ± SD 0.15(0.48) 0.22(0.55) < 0.001 M (Q1, Q3) 0 (0–0) 0 (0–0) ≥ 10mm Mean ± SD 0.06(0.29) 0.06(0.29) 0.340 M (Q1, Q3) 0 (0–0) 0 (0–0) Polyp location Proximal colon Mean ± SD 0.39(0.79) 0.48(0.88) 0.001 M (Q1, Q3) 0 (0–1) 0 (0–1) Distal colon Mean ± SD 0.44(0.81) 0.51(0.87) 0.014 M (Q1, Q3) 0 (0–1) 0 (0–1) Polyp morphology a Ip Mean ± SD 0.02(0.16) 0.03(0.19) 0.206 M (Q1, Q3) 0 (0–0) 0 (0–0) Isp Mean ± SD 0.05(0.26) 0.06(0.29) 0.086 M (Q1, Q3) 0 (0–0) 0 (0–0) Is Mean ± SD 0.41(0.92) 0.45(0.91) 0.301 M (Q1, Q3) 0 (0–0) 0 (0–1) IIa Mean ± SD 0.35(0.83) 0.45(0.90) 0.001 M (Q1, Q3) 0 (0–0) 0 (0–1) Subgroup analysis Figure 3 shows a notable increase in ADR for patients younger than 50 years in the CADe group compared with the control group (12.1% vs. 20.4%, P < 0.001), in contrast to 34.1% vs. 40.2%, P = 0.005 for those aged 50 years or older. A notable disparity in ADR was observed between male patients in the CADe group and the control group (27.6% vs. 36.4%, P < 0.001), in contrast to female patients (21.3% vs. 26.9%, P = 0.012), indicating a consistent, supportive effect of the AI across various age and sex groups. The disparities in ADRs between the two groups were further examined based on the subjects' indications as outlined in Fig. 3 . For screening and diagnostic examinations, a noteworthy distinction in ADR was observed between the CADe and control groups [(28.4% vs. 19.1%, P < 0.001), (31.4% vs. 24.4%, P < 0.001)]. However, for subjects undergoing surveillance, differences existed but did not reach statistical significance. The ADR analysis of each endoscopist For each endoscopist, AI-assisted colonoscopy (CADe) outperformed unassisted (control) colonoscopy in terms of ADR, demonstrating the widespread applicability of the CADe system; however, not all the differences were significant (Table 4 ). Table 4 The ADR analysis of each endoscopist Endoscopists control group CADe group P value Endoscopist 1 22.2% 30.00% 0.007 Endoscopist 2 15.2% 27.80% < 0.001 Endoscopist 3 24.4% 33.30% < 0.001 Endoscopist 4 17.4% 28.10% < 0.001 Endoscopist 5 29.4% 38.80% < 0.001 Endoscopist 6 26.3% 37.50% < 0.001 Endoscopist 7 22.7% 31.50% < 0.001 Endoscopist 8 23.9% 31.80% 0.012 Endoscopist 9 23.1% 29.60% 0.023 Endoscopist 10 30.8% 33.30% 0.216 Endoscopist 11 19.1% 30.60% < 0.001 Endoscopist 12 22.7% 32.50% < 0.001 Endoscopist 13 30.0% 39.80% < 0.001 Endoscopist 14 19.0% 25.00% 0.047 Endoscopist 15 18.5% 21.40% 0.203 Endoscopist 16 27.5% 30.50% 0.132 Endoscopist 17 23.6% 32.50% < 0.001 Endoscopist 18 18.8% 33.30% < 0.001 Endoscopist 19 34.1% 38.50% 0.093 Endoscopist 20 18.0% 27.30% < 0.001 Endoscopist 21 38.2% 38.80% 0.473 Endoscopist 22 30.0% 32.50% 0.351 Endoscopist 23 32.4% 33.80% 0.269 Endoscopist 24 23.7% 33.00% < 0.001 Endoscopist 25 29.8% 36.50% < 0.001 Correlation analysis of ADR and GRIT scores In our investigation, the average participant grit score was 3.39. Notably, we identified a substantial correlation (r = 0.916, P < 0.001) between grit score and AI-assisted ADR. Conversely, no correlation was observed between grit score and ADR without AI assistance ( Fig. 5) . Discussion In this multicenter, single-blind, parallel-designed, randomized controlled study, our findings indicated a significant enhancement in the ADR and PDR during colonoscopy with the application of the CADe system. This improvement was particularly pronounced for diminutive and small lesions, which pose challenges in identification without assistance. Notably, the system's effectiveness remained consistent across diverse subject populations. Furthermore, a robust correlation was observed between the grit score and AI-assisted ADR, suggesting a meaningful connection between the acceptance of AI assistance and the personality traits of the endoscopist. The auxiliary capabilities of the CADe system were realized through two primary mechanisms. First, the ability to identify intestinal lesions and furnish real-time feedback to endoscopists automatically was demonstrated. Many images featuring lesions sourced from medical record systems or public datasets and captured from easily observable angles were acquired to achieve this goal. These images were subsequently incorporated into the training regimen of the DeFrame system to simulate the progression of lesion appearance within the colonoscopic field of view. This functionality holds particular value in cases where polyps or adenomas are diminutive or manifest at the peripheries of the visual field, rendering them more challenging for endoscopists to discern accurately. Second, the DeFrame system exhibited specialized proficiency in detecting moving intestinal polyps, achieving an accuracy of 92.1%. This capability extended to instances where polyps made fleeting appearances within the visual field, lasting less than a second. An innovative edge computing technique was deployed to expedite information processing. Notably, we collected errors encountered by the DeFrame system during algorithm testing to facilitate iterative learning and minimize the impact of false positives, reducing potential interference for endoscopists [ 10 ] . The benefit of detecting and surgically removing diminutive and small polyps to prevent CRC has long been a topic of ongoing contention [ 13 ] . According to a retrospective analysis of the Dietary Polyp Prevention Trial, individuals with diminutive adenomas exhibit a 0.5% risk of occult cancer and a 7.7% risk of advanced occult adenoma; these findings cannot be ignored [ 14 ] . Consistent with many studies, our study showed that the CADe group demonstrated a markedly elevated detection rate of adenomas and polyps < 10 mm in size compared to the control group [ 15 , 16 ] . Furthermore, the CADe group exhibited significantly greater APC and PPC values than did the control group. This finding suggested that more patients at risk of future CRC were identified, potentially preventing progression to advanced adenoma [ 17 , 18 ] . Several scientific studies have shown that flat-type adenomas (Paris classification 0-Ⅱ) are more likely to develop into carcinomas [ 19 ] . These lesions, which are challenging to detect, are often found in the proximal colon, a region where thorough bowel cleaning is more complex. Studies have shown that the omission rate of flat-type adenomas reaches 35–60%, affecting the early treatment of patients and the prevention of colon cancer [ 20 ] . The CADe system can be used to thoroughly examine each frame of a colonoscopy video to identify suspicious lesions, outperforming the human eye in identifying less distinctive flat-type adenomas [ 21 ] . A greater proportion of flat neoplastic lesions was detected in our research and most other RCTs when CADe was employed than otherwise, potentially mitigating the risk of interval CRC in individuals undergoing the procedure [ 22 , 23 ] . In some previous randomized controlled studies with parallel designs focusing on CADe, higher ADRs and PDRs were consistently achieved with CADe assistance [ 24 , 25 ] . This finding suggested that CADe-related assistance has important implications for enhancing ADRs in the colonoscopy population and improving the overall quality of colonoscopy procedures [ 26 , 27 ] . However, these studies did not specifically analyze the impact of CADe on improving individual endoscopists' ADRs. Consequently, a conclusive determination regarding the effectiveness of CADe for each endoscopist could not be drawn from these investigations. In our study, we analyzed the increase in ADR for each endoscopist with the assistance of CADe, revealing that the CADe system provided varying degrees of assistive efficacy for different endoscopists. The acceptance of AI assistance by endoscopists constitutes an important diagnostic factor, a facet demonstrable through the lens of the personality trait known as grit [ 28 ] . Grit is delineated by characteristics such as perseverance and enduring passion for long-term objectives, encapsulating an individual's capacity to sustain protracted efforts and surmount obstacles in the pursuit of goals [ 29 ] . As a positive non-cognitive personality trait, grit manifests as the ability to persist in facing challenges coupled with a robust motivation to accomplish set goals [ 30 ] . Extensive research has identified grit as a superior predictor of success in fields characterized by high achievement. Notably, higher levels of grit correlate with enhanced medical school performance, while lower levels are associated with increased dropout rates in surgical residency training. Previous investigations have established that physicians typically exhibit an average grit score of 3.5 to 3.7 [ 31 ] . The participating endoscopists demonstrated an average grit score of 3.39 in the present study. Our research findings underscore the idea that endoscopists with elevated grit scores exhibit a greater propensity to embrace AI assistance, consequently increasing the ADR. Specifically, our study revealed a correlation between high grit, particularly concerning consistency of interest, and heightened ADRs. This correlation signifies a genuine commitment to achieving goals and sustaining robust motivation to overcome challenges. Importantly, these results imply the potential influence of specific personality traits of endoscopists on the acceptance of AI technology. This study is subject to several limitations. First, as indicated by some studies, the performance of AI in medical imaging may be correlated with demographic and ethnic factors [ 32 , 33 ] . Notably, although this research was conducted across multiple centers, its scope did not encompass individuals from diverse nations and ethnic backgrounds. Second, the trial involved a limited number of participating endoscopists. To ascertain the genuine assistive efficacy of AI systems, the inclusion of a more extensive and diverse pool of endoscopists with varying qualifications is essential. Third, given that this study exclusively employed the endoscopy system manufactured by Olympus Medical Systems, the generalizability of the results to endoscopy systems from other vendors remains uncertain. Finally, the assessment of the false-positive rate of the CADe system was omitted from this study. This omission arose from the impracticality of conducting a retrospective video review for false-positive rate analysis, as all the data utilized were prospectively collected. In summary, the CADe system significantly enhances the detection of polyps and adenomas during colonoscopy, reducing the risk of interval colorectal cancer among colonoscopy participants. Moreover, the effectiveness of the CADe system extends uniformly to each endoscopist. Additionally, the efficacy of AI-assisted endoscopists is associated with the individual personality traits of the endoscopist. Declarations Conflict of interest: The authors who participated in this study have no conflicts of interest to declare. Ethical approval: This study was approved by the Institutional Ethics Committees of all three participating hospitals. Animal research: Not applicable Consent to participate: Written informed consent was obtained from all the patients for their consent to participate in this study and for their data to be used for research purposes. Consent to publishing : Written informed consent was obtained from all the patients for their data to be used for research purposes. Plant reproducibility: Not applicable Provenance and peer review Not commissioned, externally peer-reviewed References Brenner H, Kloor M, Pox C P. Colorectal cancer[J]. Lancet (London, England), 2014, 383(9927): 1490-1502. Quintero E, Castells A, Bujanda L, et al. Colonoscopy versus fecal immunochemical testing in colorectal-cancer screening[J]. The New England Journal of Medicine, 2012, 366(8): 697-706. Shaukat A, Levin T R. Current and future colorectal cancer screening strategies[J]. Nature Reviews. Gastroenterology & Hepatology, 2022, 19(8): 521-531. Pan J, Xin L, Ma Y F, et al. Colonoscopy Reduces Colorectal Cancer Incidence and Mortality in Patients With Non-Malignant Findings: A Meta-Analysis[J]. The American Journal of Gastroenterology, 2016, 111(3): 355-365. Brenner H, Chen C. The colorectal cancer epidemic: challenges and opportunities for primary, secondary and tertiary prevention[J]. British Journal of Cancer, 2018, 119(7): 785-792. Corley D A, Jensen C D, Marks A R, et al. Adenoma detection rate and risk of colorectal cancer and death[J]. The New England Journal of Medicine, 2014, 370(14): 1298-1306. Hassan C, Spadaccini M, Iannone A, et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis[J]. Gastrointestinal Endoscopy, 2021, 93(1): 77-85.e6. Mori Y, Misawa M, Kudo S E. Challenges in artificial intelligence for polyp detection[J]. Digestive Endoscopy: Official Journal of the Japan Gastroenterological Endoscopy Society, 2022, 34(4): 870-871. Murakami D, Yamato M, Arai M, et al. Artificial intelligence in colonoscopy[J]. The Lancet. Gastroenterology & Hepatology, 2021, 6(12): 984-985. Chen S, Lu S, Tang Y, et al. A Machine Learning-Based System for Real-Time Polyp Detection (DeFrame): A Retrospective Study[J]. Frontiers in Medicine, 2022, 9: 852553. Cheng D C, Ting W C, Chen Y F, et al. AUTOMATIC DETECTION OF COLORECTAL POLYPS IN STATIC IMAGES[J]. Biomedical Engineering: Applications, Basis and Communications, 2011, 23(05): 357-367. Hassan C, Spadaccini M, Iannone A, et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis[J]. Gastrointestinal Endoscopy, 2021, 93(1): 77-85.e6. Vleugels J L A, Hazewinkel Y, Fockens P, et al. Natural history of diminutive and small colorectal polyps: a systematic literature review[J]. Gastrointestinal Endoscopy, 2017, 85(6): 1169-1176.e1. Pabby A, Schoen R E, Weissfeld J L, et al. Analysis of colorectal cancer occurrence during surveillance colonoscopy in the dietary Polyp Prevention Trial[J]. Gastrointestinal Endoscopy, 2005, 61(3): 385-391. Ishiyama M, Kudo S ei, Misawa M, et al. Impact of the clinical use of artificial intelligence–assisted neoplasia detection for colonoscopy: a large-scale prospective, propensity score–matched study (with video)[J]. Gastrointestinal Endoscopy, 2022, 95(1): 155-163. Mori Y, Kudo S E, Misawa M, et al. Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study[J]. Annals of Internal Medicine, 2018, 169(6): 357-366. Mori Y, East J E, Hassan C, et al. Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement[J]. Digestive Endoscopy: Official Journal of the Japan Gastroenterological Endoscopy Society, 2023, 35(4): 422-429. Hassan C, Balsamo G, Lorenzetti R, et al. Artificial Intelligence Allows Leaving-In-Situ Colorectal Polyps[J]. Clinical Gastroenterology and Hepatology: The Official Clinical Practice Journal of the American Gastroenterological Association, 2022, 20(11): 2505-2513.e4. Wallace M B, Sharma P, Bhandari P, et al. Impact of Artificial Intelligence on Miss Rate of Colorectal Neoplasia[J]. Gastroenterology, 2022, 163(1): 295-304.e5. Kim N H, Jung Y S, Jeong W S, et al. Miss rate of colorectal neoplastic polyps and risk factors for missed polyps in consecutive colonoscopies[J]. Intestinal Research, 2017, 15(3): 411-418. Yamada M, Saito Y, Yamada S, et al. Detection of flat colorectal neoplasia by artificial intelligence: A systematic review[J]. Best Practice & Research. Clinical Gastroenterology, 2021, 52-53: 101745. Repici A, Badalamenti M, Maselli R, et al. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial[J]. Gastroenterology, 2020, 159(2): 512-520.e7. Wang P, Berzin T M, Glissen Brown J R, et al. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study[J]. Gut, 2019, 68(10): 1813-1819. Gimeno-García A Z, Hernández Negrin D, Hernández A, et al. Usefulness of a novel computer-aided detection system for colorectal neoplasia: a randomized controlled trial[J]. Gastrointestinal Endoscopy, 2023, 97(3): 528-536.e1. Aniwan S, Mekritthikrai K, Kerr S J, et al. Computer-aided detection, mucosal exposure device, their combination, and standard colonoscopy for adenoma detection: a randomized controlled trial[J]. Gastrointestinal Endoscopy, 2023, 97(3): 507-516. Deliwala S S, Hamid K, Barbarawi M, et al. Artificial intelligence (AI) real-time detection vs. routine colonoscopy for colorectal neoplasia: a meta-analysis and trial sequential analysis[J]. International Journal of Colorectal Disease, 2021, 36(11): 2291-2303. Mori Y, Wang P, Løberg M, et al. Impact of Artificial Intelligence on Colonoscopy Surveillance After Polyp Removal: A Pooled Analysis of Randomized Trials[J]. Clinical Gastroenterology and Hepatology: The Official Clinical Practice Journal of the American Gastroenterological Association, 2023, 21(4): 949-959.e2. Jin E H, Lee D, Bae J H, et al. Improved Accuracy in Optical Diagnosis of Colorectal Polyps Using Convolutional Neural Networks with Visual Explanations[J]. Gastroenterology, 2020, 158(8): 2169-2179.e8. Clark K N, Malecki C K. Academic grit scale: psychometric properties and associations with achievement and life satisfaction[J]. Journal of School Psychology, 2019, 72: 49-66. Lee D H, Reasoner K, Lee D. Grit: what is it and why does it matter in medicine?[J]. Postgraduate Medical Journal, 2023, 99(1172): 535-541. Hewitt D B, Chung J W, Ellis R J, et al. National Evaluation of Surgical Resident Grit and the Association With Wellness Outcomes[J]. JAMA surgery, 2021, 156(9): 856-863. Martínez M E, Baron J A, Lieberman D A, et al. A pooled analysis of advanced colorectal neoplasia diagnoses after colonoscopic polypectomy[J]. Gastroenterology, 2009, 136(3): 832-841. Lieberman D, Sullivan B A, Hauser E R, et al. Baseline Colonoscopy Findings Associated With 10-Year Outcomes in a Screening Cohort Undergoing Colonoscopy Surveillance[J]. Gastroenterology, 2020, 158(4): 862-874.e8. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 30 Nov, 2025 Reviews received at journal 06 Nov, 2025 Reviewers agreed at journal 28 Oct, 2025 Reviewers agreed at journal 26 Jul, 2025 Reviewers agreed at journal 21 Jul, 2025 Reviewers agreed at journal 29 Oct, 2024 Reviewers invited by journal 01 Jun, 2024 Editor assigned by journal 01 Jun, 2024 Submission checks completed at journal 09 May, 2024 First submitted to journal 08 May, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4389606","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":300582735,"identity":"ad40e037-b291-408a-9a9c-154baf3ffefb","order_by":0,"name":"Pengju Wang","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Pengju","middleName":"","lastName":"Wang","suffix":""},{"id":300582740,"identity":"40878cb5-2cce-4f62-9785-5dec0315499e","order_by":1,"name":"Longsong Li","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Longsong","middleName":"","lastName":"Li","suffix":""},{"id":300582744,"identity":"6373d277-511b-4cc4-b4f5-0399389e6e58","order_by":2,"name":"Long Rong","email":"","orcid":"","institution":"Peking University First Hospital","correspondingAuthor":false,"prefix":"","firstName":"Long","middleName":"","lastName":"Rong","suffix":""},{"id":300582747,"identity":"b4c02bea-2f6e-4a47-b774-1ede0ec0eff9","order_by":3,"name":"Peng Jin","email":"","orcid":"","institution":"The Seventh Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Jin","suffix":""},{"id":300582750,"identity":"0df52d12-501d-4083-83cf-2d5b0df4b289","order_by":4,"name":"Wenhui Zhang","email":"","orcid":"","institution":"Beijing Daxing District People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Wenhui","middleName":"","lastName":"Zhang","suffix":""},{"id":300582753,"identity":"9868366a-230d-45a9-9ba0-c094e42725d3","order_by":5,"name":"Bo Zhang","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Zhang","suffix":""},{"id":300582755,"identity":"6dd9d8a6-3adc-49fb-b5e0-39a5440e482e","order_by":6,"name":"Yurong Tao","email":"","orcid":"","institution":"The Seventh Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yurong","middleName":"","lastName":"Tao","suffix":""},{"id":300582757,"identity":"1c12db74-17df-47bb-8a1d-305f024cad61","order_by":7,"name":"Li Ma","email":"","orcid":"","institution":"Beijing Daxing District People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Ma","suffix":""},{"id":300582759,"identity":"2945c2bb-7d9c-4482-8804-529dddc4b554","order_by":8,"name":"Chunyan Wang","email":"","orcid":"","institution":"Beijing Daxing District People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Chunyan","middleName":"","lastName":"Wang","suffix":""},{"id":300582761,"identity":"a8416249-1937-490a-84a5-feeca40c7d1d","order_by":9,"name":"Can Zhao","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Can","middleName":"","lastName":"Zhao","suffix":""},{"id":300582762,"identity":"f50b4320-8bd7-40c4-9fda-390adecc9990","order_by":10,"name":"Zihui Geng","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Zihui","middleName":"","lastName":"Geng","suffix":""},{"id":300582763,"identity":"c525b459-43ed-4d4b-a09e-82c1d0a37203","order_by":11,"name":"Yaxuan Cheng","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yaxuan","middleName":"","lastName":"Cheng","suffix":""},{"id":300582764,"identity":"8efa8ed9-7c42-426d-a46c-bcf3fd223f37","order_by":12,"name":"Fanqi Meng","email":"","orcid":"","institution":"Changsha High Wise Medical Technology ., LTD","correspondingAuthor":false,"prefix":"","firstName":"Fanqi","middleName":"","lastName":"Meng","suffix":""},{"id":300582766,"identity":"ab7516f8-b4dd-405b-a7a6-3933ca6c6370","order_by":13,"name":"Wen Xiao","email":"","orcid":"","institution":"Changsha High Wise Medical Technology ., LTD","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Xiao","suffix":""},{"id":300582768,"identity":"e9783bc4-ad75-426d-9ce0-48956e4f6bb7","order_by":14,"name":"Enqiang Linghu","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Enqiang","middleName":"","lastName":"Linghu","suffix":""},{"id":300582770,"identity":"4d5dfce2-5872-4f6d-a6d7-4fe225252c22","order_by":15,"name":"Ningli Chai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIie3PMWrDMBSA4WcEyvJSrTL0EC9TKYTkKjIZsnjwEQQGn8GhxwiEjDKCTjlAhwwOhc4OgUKhQySTjpU9BqJ/eNLwPoQAYrF7TAIYIIAnxgwoABRCjyScceXJc1qbYdLHAcmfc9IqLMRbebJFcVxUE/yWp72HJunOeeCR4zvZmr5WFZvuZHYAfGGapZvd/4SkIotkV5xNt5RVgK/auHuQrLsbwc+ekFFDJO9fWTiStKOI/MgLT9wan7XZQWJaN2XwL6Jeby/4a5dC2Lb52c/dpWy6c4D8lWk/Ey37ObzvWgKMX47FYrEH6wornUy0C1vw5QAAAABJRU5ErkJggg==","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":true,"prefix":"","firstName":"Ningli","middleName":"","lastName":"Chai","suffix":""}],"badges":[],"createdAt":"2024-05-08 13:23:53","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4389606/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4389606/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57287201,"identity":"1ff7e211-53f3-4ee0-ad58-c4ac6970afbf","added_by":"auto","created_at":"2024-05-28 16:43:02","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":345619,"visible":true,"origin":"","legend":"\u003cp\u003eAn image of when the lesion was detected with and without the CADe system.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003csup\u003ea\u003c/sup\u003e\u003cstrong\u003e \u003c/strong\u003eIdentification of adenomas by conventional colonoscopy. \u003cstrong\u003eb\u003c/strong\u003e Blue box marks adenomas detected by colonoscopy with CADe.\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-4389606/v1/b2a1773e11a06b24ea468042.png"},{"id":57287705,"identity":"a3098773-da3c-4d05-8d33-c44b561422ba","added_by":"auto","created_at":"2024-05-28 16:51:02","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":98020,"visible":true,"origin":"","legend":"\u003cp\u003eTrial profile.\u003c/p\u003e\n\u003cp\u003e50 participants were excluded before randomization; of those, 4 had familial polyposis, 24 were diagnosed with IBD, and 22 underwent colorectal resection. After randomization, 114 subjects were excluded from the control group; of those, 9 had no cecal intubation, 96 had inadequate BBPS scores, and 9 were suspected of having IBD. In the CADe group, 123 subjects were excluded; of those, 15 had no cecal intubation, 90 had inadequate BBPS scores, and 18 were suspected of having IBD. Finally, the analysis included 1666 subjects in the control group and 1651 in the CADe group.\u003c/p\u003e\n\u003cp\u003eIBD, inflammatory bowel disease. BBPS, Boston Bowel Preparation Scale; CADe, computer-aided detection.\u003c/p\u003e","description":"","filename":"figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-4389606/v1/6c1286a981f55e587986d737.png"},{"id":57287200,"identity":"2cdb6769-b297-45db-842c-bce276339cd9","added_by":"auto","created_at":"2024-05-28 16:43:02","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":74579,"visible":true,"origin":"","legend":"\u003cp\u003eADRs stratified by sex, age, and indication group.\u003c/p\u003e","description":"","filename":"figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-4389606/v1/01b43e42182796ec0fabe7f4.png"},{"id":57287202,"identity":"b5c6d696-52c5-446e-8a43-1c9f3dc084e8","added_by":"auto","created_at":"2024-05-28 16:43:02","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":21319,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation analysis of ADR and GRIT scores.\u003c/p\u003e\n\u003cp\u003eThe GRIT score indicates the extent to which each endoscopist's acceptance of the CADe system.\u003c/p\u003e","description":"","filename":"figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-4389606/v1/31e04eec37b644bd9cd25f38.png"},{"id":57287967,"identity":"953242f5-000d-4812-92db-f449ec655c81","added_by":"auto","created_at":"2024-05-28 16:59:03","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1633977,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4389606/v1/6e29d7db-5816-47c2-87b9-72d4df67819a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Effect of a novel spatial-temporal computer-aided detection system on adenoma detection during colonoscopy: A multicenter, randomized controlled trial","fulltext":[{"header":"Introduction","content":"\u003cp\u003eIntestinal adenomatous polyps are recognized as precancerous lesions that may progress to colorectal cancer (CRC) if timely intervention is not implemented\u003csup\u003e[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/sup\u003e. Colonoscopy screening for polyps and adenomas has been demonstrated to effectively reduce the incidence of colorectal neoplasia\u003csup\u003e[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]\u003c/sup\u003e. A substantial cohort study highlighted the capacity of colonoscopy screening to reduce CRC mortality by 68%\u003csup\u003e[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]\u003c/sup\u003e. However, conventional examinations are subject to multiple variables, encompassing factors such as the procedural technique employed by the endoscopists, their level of experience, potential fatigue, and the quality of bowel preparation. 27% of adenomas are overlooked during conventional colonoscopy, with a potentially more pronounced omission rate for diminutive adenomas (\u0026le;\u0026thinsp;5 mm), constituting a primary contributor to interval CRC\u003csup\u003e[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]\u003c/sup\u003e. Studies indicate that an increase in the ADR of 1.0% corresponds to a 3% reduction in the associated risk of interval CRC\u003csup\u003e[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eRecent studies have confirmed the efficacy of artificial intelligence (AI) based on conventional polyp detection algorithms. These studies have shown that AI has the potential to significantly improve both the ADR and the polyp detection rate (PDR) \u003csup\u003e[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]\u003c/sup\u003e. However, most polyp detection algorithms focus solely on the spatial dimension to capture the appearance and alterations of suspected polyps over time. Consequently, prevalent shortcomings include a notable incidence of false positives and negatives in extant algorithms, impacting the application of CADe systems in real-time diagnosis\u003csup\u003e[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]\u003c/sup\u003e. In addition, most studies have focused on the overall improvement in ADRs associated with the use of CADe systems. Nonetheless, the extent to which endoscopists accept the CADe systems differs. There was no reported link between the enhancement of ADR and endoscopists\u0026rsquo; acceptance of the CADe systems.\u003c/p\u003e \u003cp\u003eIn response to the limitations inherent in extant algorithms, we introduced a pioneering CADe system, denominated DeFrame, distinguished by incorporating a sophisticated dual-flow fusion algorithm. Notably, this system assimilates spatial data and integrates temporal dimension insights to refine the accuracy of real-time polyp diagnosis within complex intestinal environments\u003csup\u003e[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/sup\u003e. This study was designed to evaluate whether the CADe system could improve polyp and adenoma detection during colonoscopy. Moreover, the personality trait grit was assessed as an indicator of the endoscopists\u0026rsquo; acceptance of the CADe system. The correlation between grit and the AI-assisted ADR was also assessed.\u003c/p\u003e"},{"header":"Patients and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eThe CADe system\u003c/h2\u003e \u003cp\u003eColonoscopy signals consist of successive frames, both spatial and temporal. Most state-of-the-art algorithms concentrate solely on spatial data and excel in still images\u003csup\u003e[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]\u003c/sup\u003e. However, the efficiency of the CADe system decreases when the intestinal environment is intricate or undergoes rapid changes. Consequently, we designed a CADe system named Deframe to retrieve spatial and temporal data\u003csup\u003e[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/sup\u003e. DeFrame, validated with a dataset of 20,660 images (13,347 typical and 7,313 atypical), achieved robust polyp detection performance, boasting a recall of 95.43% and a precision of 92.12%. The system excels in rapid polyp identification, as indicated by a bounding box on the endoscopy screen within 25\u0026thinsp;\u0026plusmn;\u0026thinsp;9 ms upon detection (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eStudy population\u003c/h3\u003e\n\u003cp\u003eThe research was conducted at four endoscopy centers in China: the First Medical Center of PLAGH, Peking University First Hospital, the Seventh Medical Center of PLAGH, and Daxing People's Hospital. Eligible participants aged 18 years and older undergoing screening, surveillance, or diagnostic colonoscopy at these centers were recruited and included between June 2023 and September 2023. The exclusion criteria included a history of inflammatory bowel disease (IBD), familial adenomatous polyposis, prior colorectal resection, or Peutz\u0026ndash;Jeghers syndrome. Moreover, patients were excluded after randomization if the cecum could not be reached or if they had poor bowel preparation (Boston Bowel Preparation Scale (BBPS) score\u0026thinsp;\u0026lt;\u0026thinsp;6). All included subjects provided informed consent before participating in the study.\u003c/p\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eStudy design\u003c/h2\u003e \u003cp\u003eWe designed a single-blind, randomized parallel-group study, and this trial was registered at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://www.chictr.org.cn\u003c/span\u003e\u003cspan address=\"http://www.chictr.org.cn\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (ChiCTR2300071612). Subjects were stratified based on the clinical trial center and the clinical indication for colonoscopy and then allocated to either the CADe group (CADe colonoscopy) or the control group (conventional colonoscopy) at a 1:1 ratio. Endoscopists were conscious of the study arm to which each subject was assigned, while the subjects remained unaware.\u003c/p\u003e \u003cp\u003eThe trial involved 25 experienced endoscopists who were daily allocated to the endoscopy room, either with or without CADe. All procedures were performed with an EVIS LUCERA ELITE 290 (Olympus Co., Tokyo) system. The operation time, bowel preparation procedure, polyp characteristics (number, size, location), and withdrawal time were documented for each patient. In both the control and CADe groups, all polyps were removed or biopsied, except tiny, hyperplastic polyps in the rectum, which were typically left intact. All polyp specimens were distinctly marked and subjected to histological analysis.\u003c/p\u003e \u003cp\u003e The Short Grit Scale (GRIT-S), an 8-item validated questionnaire, was used to measure grit levels, with participants rating it on a 5-point Likert scale as follows: \u0026ldquo;very much like me,\u0026rdquo; \u0026ldquo;mostly like me,\u0026rdquo; somewhat like me,\u0026rdquo; \u0026ldquo;not much like me,\u0026rdquo; and \u0026ldquo;not like me at all.\u0026rdquo; A total of four items underwent reverse coding. The individual scores were aggregated and subsequently divided by 8. The final scores ranged between 1 (not at all gritty) and 5 (extremely gritty). Throughout the research, grit served as a continuous variable.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eHistopathology\u003c/h2\u003e \u003cp\u003eResected and biopsy specimens were fixed in distinct containers containing a 10% buffered formalin solution. Following fixation, standard histopathological procedures were applied for processing and staining. Expert pathologists, who were unbiased to the assigned examination mode, conducted the evaluation. Lesions were systematically categorized based on the Paris classification.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eOutcome measures\u003c/h2\u003e \u003cp\u003eThe primary outcome focused on comparing the ADR between the two study arms. The ADR was defined as the proportion of patients exhibiting at least one histologically confirmed adenoma or carcinoma. The secondary outcomes included the PDR and the counts of adenomas and polyps detected per colonoscopy (APC and PPC). Additionally, the detection rates of polyps of varying sizes (diminutive [\u0026le;\u0026thinsp;5 mm], small [6\u0026ndash;9 mm], and large [\u0026ge;\u0026thinsp;10 mm]) and of varying sites (proximal colon [proximal to the splenic flexure] and distal colon [descending colon to rectum]) were assessed. Subgroup analyses were also conducted based on age, sex, and indication for colonoscopy. A correlation between each endoscopist's grit score and the AI-assisted ADR was observed.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eBased on a relevant prior study, we estimated that the ADR for standard colonoscopy was 24% in routine practice. In comparison, the ADR for real-time computer-aided detection system colonoscopy is anticipated to be 30%\u003csup\u003e[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]\u003c/sup\u003e. Based on a two-sided test with a 5% significance level and 80% power, the total sample size required for the study was 1712 patients. Assuming that the dropout rate from the analysis was 10%, an estimated enrollment of approximately 2000 patients was planned. The sample size calculation was conducted using an online power calculator.\u003c/p\u003e \u003cp\u003eAnalysis was performed for the specified outcome measures. Baseline characteristics were assessed for between-group differences utilizing the χ\u0026sup2; test for categorical variables and the Mann‒Whitney U test for continuous variables. The impact of the CADe system on the ADR and PDR was evaluated using logistic regression analysis, whereas the effect on the APC and PPC was assessed through the Mann‒Whitney U test. Covariate-adjusted logistic regression and negative binomial regression models were developed, incorporating group differences as covariates. These models were intended to address potential confounding factors, including the indication for colonoscopy, body mass index (BMI), age, BBPS score, and sex. A significance level of less than 0.05 according to two-sided tests was used to indicate statistical significance. All analyses were conducted using SPSS version 24.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003ePatient characteristics\u003c/h2\u003e \u003cp\u003eA total of 3554 eligible subjects were randomly allocated to either the control group (n\u0026thinsp;=\u0026thinsp;1780) or the AI-assisted group (CADe group, n\u0026thinsp;=\u0026thinsp;1774). As depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, within the control group, 114 subjects were excluded for reasons such as no cecal intubation (n\u0026thinsp;=\u0026thinsp;9), inadequate BBPS scores (n\u0026thinsp;=\u0026thinsp;96), or suspected inflammatory bowel disease (IBD) (n\u0026thinsp;=\u0026thinsp;9). In the CADe group, 123 subjects were excluded; 15 had no cecal intubation, 90 had inadequate BBPS scores, and 18 were suspected of having IBD. Finally, the analysis included 1666 subjects in the control group and 1651 in the CADe group.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eAs outlined in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, no statistically significant differences in sex, age, or BMI were evident between the two groups. Furthermore, there were no notable disparities in clinical indications between the control group and the CADe group: 34.6% for diagnostic, 47.1% for screening, and 18.3% for surveillance in the control group, compared with 35.8% for diagnostic, 47.9% for screening, and 16.3% for surveillance in the CADe group. Similarly, no significant differences were observed in terms of withdrawal time (425.15\u0026thinsp;\u0026plusmn;\u0026thinsp;58.52 seconds vs. 422.31\u0026thinsp;\u0026plusmn;\u0026thinsp;53.62 seconds) or BBPS score (7.53\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9 vs. 7.50\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9) between the two groups.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eBaseline characteristics of the subjects enrolled\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCharacteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eControl group\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1666)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCADe group\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1651)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, mean (SD), y\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e51.67(12.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e51.71(12.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.917\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eSex, No. (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e907(54.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e900(54.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.967\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e759(45.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e751(45.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eIndication for colonoscopy, No. (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiagnose\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e577(34.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e591(35.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.303\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eScreening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e784(47.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e791(47.9)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSurveillance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e305(18.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e269(16.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBMI, mean (SD)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23.3 (3.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e23.2 (3.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBBPS score, mean (SD)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e7.53(0.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.50(0.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.465\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLeft colon bowel preparation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.63(0.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.61(0.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.481\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTransverse colon bowel preparation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.55(0.49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.53(0.50)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.252\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRight colon bowel preparation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.35(0.47)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.36(0.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.603\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWithdrawal time, No. (%), sec\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e425.15(58.52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e422.31(53.62)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.145\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003ePer patient analysis\u003c/h2\u003e \u003cp\u003eAs indicated in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, 528 out of 1651 subjects in the CADe group were diagnosed with at least one adenoma during colonoscopy, whereas 411 out of 1666 subjects in the control group were diagnosed, with an ADR of 32.1% or 24.7%, respectively. After adjustments for age, sex, and indication, the ADR was significantly greater in the CADe group than in the control group, a finding consistent with the PDR [51.3% (847/1651) vs. 44.1% (733/1666), \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001].\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe detection rate of adenomas and polyps [n (%)]\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eControl group\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1666)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCADe group\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1651)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eOdds ratio (95% confidence interval)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eADR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e411(24.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e528 (32.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.439(1.236\u0026ndash;1.675)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e \u003cp\u003eAdenoma size category\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026le;\u0026thinsp;5 mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e307(18.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e384(23.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.342(1.134\u0026ndash;1.588)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u0026ndash;9 mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e125(7.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e196(11.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.661(1.312\u0026ndash;2.102)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;10 mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e55(3.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e76(4.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.413(0.992\u0026ndash;2.013)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.054\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e \u003cp\u003eAdenoma location\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProximal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e254(15.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e329(19.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.383(1.155\u0026ndash;1.656)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDistal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e237(14.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e305(18.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.366(1.135\u0026ndash;1.644)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e \u003cp\u003eAdenoma morphology \u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22(1.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e27(1.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.242(0.705\u0026ndash;2.190)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.452\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠsp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e52(3.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e59(3.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.150(0.787\u0026ndash;1.681)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.469\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e221(13.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e288(17.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.382(1.142\u0026ndash;1.671)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅡa\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e165(9.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e256(15.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.669(1.355\u0026ndash;2.057)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePDR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e733(44.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e847(51.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.338(1.167\u0026ndash;1.534)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e \u003cp\u003ePoly size category\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026le;\u0026thinsp;5 mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e629(37.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e721(43.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.278(1.112\u0026ndash;1.468)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u0026ndash;9 mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e186(11.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e274(16.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.583(1.296\u0026ndash;1.934)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;10 mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e72(4.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95(5.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.306(0.952\u0026ndash;1.792)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.097\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e \u003cp\u003ePolyp location\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProximal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e429(25.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e505(30.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.271(1.092\u0026ndash;1.479)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDistal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e501(30.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e572(34.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.233(1.066\u0026ndash;1.426)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.005\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e \u003cp\u003ePolyp morphology \u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e31(1.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e39(2.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.276(0.792\u0026ndash;2.055)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.315\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠsp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e68(4.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e90(5.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.355(0.981\u0026ndash;1.871)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.064\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e383(23.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e455(27.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.274(1.089\u0026ndash;1.491)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅡa\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e349(20.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e458(27.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.449(1.235-1.700)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eRegarding adenoma and polyp size, there were significant differences between the two groups for diminutive adenomas (\u0026le;\u0026thinsp;5 mm) [23.3% vs. 18.4%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.001] and small adenomas (6\u0026ndash;9 mm) [11.9% vs. 7.5%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001]. This trend was also observed for diminutive polyps and small polyps. Lesions\u0026thinsp;\u0026ge;\u0026thinsp;10 mm in size, being larger, were more easily observable, resulting in no significant difference between the two groups. Concerning the location of the detected adenomas (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e), the proportion of patients with adenomas in the proximal and distal colon in the CADe group was significantly greater than that in the control group. Based on the lesion morphology, whether it was an adenoma or a polyp, significant differences were observed for types Is and Ⅱa between the CADe group and the control group.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003ePer polyp analysis\u003c/h2\u003e \u003cp\u003eAs illustrated in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, the APC was significantly greater in the CADe group than in the control group (0.52 vs. 0.39, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Similarly, PPC exhibited analogous findings, with a greater value in the CADe group than in the control group (0.99 vs. 0.83, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). A noteworthy difference in the APC density was observed between the two groups for diminutive adenomas (0.32 vs. 0.25, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.004) and small adenomas (0.15 vs. 0.09, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). However, there was no significant difference in the percentage of patients with adenomas\u0026thinsp;\u0026ge;\u0026thinsp;10 mm. The APC density in both the proximal and distal colon was significantly greater in the CADe group than in the control group. Regarding the morphology of the adenomas, the APCs of type IIa adenomas in the CADe and control groups were 0.23 and 0.14, respectively (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Similar trends were observed for polyp characteristics.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eAPC and PPC in the CADe group and control group [mean (SD)]\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eControl group\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1666)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCADe group\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1651)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eAPC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.39 (1.01)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.52 (0.85)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0(0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eAdenoma size category\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u0026le;\u0026thinsp;5mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.25(0.62)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.32(0.70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e6-9mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.09(0.37)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.15(0.46)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;10mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.04(0.26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.05(0.26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e0.260\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eAdenoma location\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eProximal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.20(0.55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.28(0.67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eDistal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.19(0.53)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.25(0.60)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eAdenoma morphology \u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.02(0.14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.02(0.15)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e0.609\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIsp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.04(0.22)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.04(0.24)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e0.467\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.20(0.59)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.24(0.60)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e0.059\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIIa\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.14(0.49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.23(0.64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c7\" namest=\"c6\" rowspan=\"2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003ePPC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.83(1.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.99(1.36)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1(0\u0026ndash;2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003ePolyp size category\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u0026le;\u0026thinsp;5mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.63(1.01)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.71(1.04)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e6-9mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.15(0.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.22(0.55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;10mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.06(0.29)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.06(0.29)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.340\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003ePolyp location\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eProximal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.39(0.79)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.48(0.88)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eDistal colon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.44(0.81)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.51(0.87)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.014\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003ePolyp morphology \u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.02(0.16)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.03(0.19)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.206\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIsp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.05(0.26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.06(0.29)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.086\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.41(0.92)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.45(0.91)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.301\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eIIa\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.35(0.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.45(0.90)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eM (Q1, Q3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c7\" namest=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eSubgroup analysis\u003c/h2\u003e \u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows a notable increase in ADR for patients younger than 50 years in the CADe group compared with the control group (12.1% vs. 20.4%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), in contrast to 34.1% vs. 40.2%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.005 for those aged 50 years or older. A notable disparity in ADR was observed between male patients in the CADe group and the control group (27.6% vs. 36.4%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), in contrast to female patients (21.3% vs. 26.9%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.012), indicating a consistent, supportive effect of the AI across various age and sex groups.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe disparities in ADRs between the two groups were further examined based on the subjects' indications as outlined in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. For screening and diagnostic examinations, a noteworthy distinction in ADR was observed between the CADe and control groups [(28.4% vs. 19.1%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), (31.4% vs. 24.4%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001)]. However, for subjects undergoing surveillance, differences existed but did not reach statistical significance.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003eThe ADR analysis of each endoscopist\u003c/h2\u003e \u003cp\u003eFor each endoscopist, AI-assisted colonoscopy (CADe) outperformed unassisted (control) colonoscopy in terms of ADR, demonstrating the widespread applicability of the CADe system; however, not all the differences were significant (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe ADR analysis of each endoscopist\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopists\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003econtrol group\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCADe group\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30.00%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.007\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e15.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e27.80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e24.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33.30%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e17.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e28.10%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e29.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38.80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26.3%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22.7%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e31.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e31.80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.012\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23.1%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e29.60%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.023\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33.30%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.216\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19.1%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30.60%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22.7%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e39.80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e25.00%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.047\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e21.40%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.203\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.132\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23.6%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33.30%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e34.1%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.093\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e27.30%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e38.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38.80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.473\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.351\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e32.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33.80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.269\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23.7%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33.00%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndoscopist 25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e29.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36.50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003eCorrelation analysis of ADR and GRIT scores\u003c/h2\u003e \u003cp\u003e In our investigation, the average participant grit score was 3.39. Notably, we identified a substantial correlation (r\u0026thinsp;=\u0026thinsp;0.916, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) between grit score and AI-assisted ADR. Conversely, no correlation was observed between grit score and ADR without AI assistance (\u003cb\u003eFig.\u0026nbsp;5)\u003c/b\u003e.\u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this multicenter, single-blind, parallel-designed, randomized controlled study, our findings indicated a significant enhancement in the ADR and PDR during colonoscopy with the application of the CADe system. This improvement was particularly pronounced for diminutive and small lesions, which pose challenges in identification without assistance. Notably, the system's effectiveness remained consistent across diverse subject populations. Furthermore, a robust correlation was observed between the grit score and AI-assisted ADR, suggesting a meaningful connection between the acceptance of AI assistance and the personality traits of the endoscopist.\u003c/p\u003e \u003cp\u003eThe auxiliary capabilities of the CADe system were realized through two primary mechanisms. First, the ability to identify intestinal lesions and furnish real-time feedback to endoscopists automatically was demonstrated. Many images featuring lesions sourced from medical record systems or public datasets and captured from easily observable angles were acquired to achieve this goal. These images were subsequently incorporated into the training regimen of the DeFrame system to simulate the progression of lesion appearance within the colonoscopic field of view. This functionality holds particular value in cases where polyps or adenomas are diminutive or manifest at the peripheries of the visual field, rendering them more challenging for endoscopists to discern accurately. Second, the DeFrame system exhibited specialized proficiency in detecting moving intestinal polyps, achieving an accuracy of 92.1%. This capability extended to instances where polyps made fleeting appearances within the visual field, lasting less than a second. An innovative edge computing technique was deployed to expedite information processing. Notably, we collected errors encountered by the DeFrame system during algorithm testing to facilitate iterative learning and minimize the impact of false positives, reducing potential interference for endoscopists\u003csup\u003e[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe benefit of detecting and surgically removing diminutive and small polyps to prevent CRC has long been a topic of ongoing contention\u003csup\u003e[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]\u003c/sup\u003e. According to a retrospective analysis of the Dietary Polyp Prevention Trial, individuals with diminutive adenomas exhibit a 0.5% risk of occult cancer and a 7.7% risk of advanced occult adenoma; these findings cannot be ignored\u003csup\u003e[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/sup\u003e. Consistent with many studies, our study showed that the CADe group demonstrated a markedly elevated detection rate of adenomas and polyps\u0026thinsp;\u0026lt;\u0026thinsp;10 mm in size compared to the control group\u003csup\u003e[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]\u003c/sup\u003e. Furthermore, the CADe group exhibited significantly greater APC and PPC values than did the control group. This finding suggested that more patients at risk of future CRC were identified, potentially preventing progression to advanced adenoma\u003csup\u003e[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eSeveral scientific studies have shown that flat-type adenomas (Paris classification 0-Ⅱ) are more likely to develop into carcinomas\u003csup\u003e[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/sup\u003e. These lesions, which are challenging to detect, are often found in the proximal colon, a region where thorough bowel cleaning is more complex. Studies have shown that the omission rate of flat-type adenomas reaches 35\u0026ndash;60%, affecting the early treatment of patients and the prevention of colon cancer\u003csup\u003e[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/sup\u003e. The CADe system can be used to thoroughly examine each frame of a colonoscopy video to identify suspicious lesions, outperforming the human eye in identifying less distinctive flat-type adenomas\u003csup\u003e[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]\u003c/sup\u003e. A greater proportion of flat neoplastic lesions was detected in our research and most other RCTs when CADe was employed than otherwise, potentially mitigating the risk of interval CRC in individuals undergoing the procedure\u003csup\u003e[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn some previous randomized controlled studies with parallel designs focusing on CADe, higher ADRs and PDRs were consistently achieved with CADe assistance\u003csup\u003e[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]\u003c/sup\u003e. This finding suggested that CADe-related assistance has important implications for enhancing ADRs in the colonoscopy population and improving the overall quality of colonoscopy procedures\u003csup\u003e[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]\u003c/sup\u003e. However, these studies did not specifically analyze the impact of CADe on improving individual endoscopists' ADRs. Consequently, a conclusive determination regarding the effectiveness of CADe for each endoscopist could not be drawn from these investigations. In our study, we analyzed the increase in ADR for each endoscopist with the assistance of CADe, revealing that the CADe system provided varying degrees of assistive efficacy for different endoscopists.\u003c/p\u003e \u003cp\u003eThe acceptance of AI assistance by endoscopists constitutes an important diagnostic factor, a facet demonstrable through the lens of the personality trait known as grit\u003csup\u003e[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]\u003c/sup\u003e. Grit is delineated by characteristics such as perseverance and enduring passion for long-term objectives, encapsulating an individual's capacity to sustain protracted efforts and surmount obstacles in the pursuit of goals\u003csup\u003e[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]\u003c/sup\u003e. As a positive non-cognitive personality trait, grit manifests as the ability to persist in facing challenges coupled with a robust motivation to accomplish set goals \u003csup\u003e[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]\u003c/sup\u003e. Extensive research has identified grit as a superior predictor of success in fields characterized by high achievement. Notably, higher levels of grit correlate with enhanced medical school performance, while lower levels are associated with increased dropout rates in surgical residency training. Previous investigations have established that physicians typically exhibit an average grit score of 3.5 to 3.7\u003csup\u003e[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/sup\u003e. The participating endoscopists demonstrated an average grit score of 3.39 in the present study. Our research findings underscore the idea that endoscopists with elevated grit scores exhibit a greater propensity to embrace AI assistance, consequently increasing the ADR. Specifically, our study revealed a correlation between high grit, particularly concerning consistency of interest, and heightened ADRs. This correlation signifies a genuine commitment to achieving goals and sustaining robust motivation to overcome challenges. Importantly, these results imply the potential influence of specific personality traits of endoscopists on the acceptance of AI technology.\u003c/p\u003e \u003cp\u003eThis study is subject to several limitations. First, as indicated by some studies, the performance of AI in medical imaging may be correlated with demographic and ethnic factors\u003csup\u003e[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/sup\u003e. Notably, although this research was conducted across multiple centers, its scope did not encompass individuals from diverse nations and ethnic backgrounds. Second, the trial involved a limited number of participating endoscopists. To ascertain the genuine assistive efficacy of AI systems, the inclusion of a more extensive and diverse pool of endoscopists with varying qualifications is essential. Third, given that this study exclusively employed the endoscopy system manufactured by Olympus Medical Systems, the generalizability of the results to endoscopy systems from other vendors remains uncertain. Finally, the assessment of the false-positive rate of the CADe system was omitted from this study. This omission arose from the impracticality of conducting a retrospective video review for false-positive rate analysis, as all the data utilized were prospectively collected.\u003c/p\u003e \u003cp\u003eIn summary, the CADe system significantly enhances the detection of polyps and adenomas during colonoscopy, reducing the risk of interval colorectal cancer among colonoscopy participants. Moreover, the effectiveness of the CADe system extends uniformly to each endoscopist. Additionally, the efficacy of AI-assisted endoscopists is associated with the individual personality traits of the endoscopist.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eConflict of interest:\u003c/strong\u003e The authors who participated in this study have no conflicts of interest to declare.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval:\u0026nbsp;\u003c/strong\u003eThis study was approved by the Institutional Ethics Committees of all three participating hospitals.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAnimal research:\u0026nbsp;\u003c/strong\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to participate:\u003c/strong\u003e Written informed consent was obtained from all the patients for their consent to participate in this study and for their data to be used for research purposes.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to publishing\u003c/strong\u003e: Written informed consent was obtained from all the patients for their data to be used for research purposes.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePlant reproducibility:\u003c/strong\u003e Not applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eProvenance and peer review\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eNot commissioned, externally peer-reviewed\u003c/strong\u003e\u003cstrong\u003e\u003cbr\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eBrenner H, Kloor M, Pox C P. Colorectal cancer[J]. Lancet (London, England), 2014, 383(9927): 1490-1502.\u003c/li\u003e\n\u003cli\u003eQuintero E, Castells A, Bujanda L, et al. Colonoscopy versus fecal immunochemical testing in colorectal-cancer screening[J]. The New England Journal of Medicine, 2012, 366(8): 697-706.\u003c/li\u003e\n\u003cli\u003eShaukat A, Levin T R. Current and future colorectal cancer screening strategies[J]. Nature Reviews. Gastroenterology \u0026amp; Hepatology, 2022, 19(8): 521-531.\u003c/li\u003e\n\u003cli\u003ePan J, Xin L, Ma Y F, et al. Colonoscopy Reduces Colorectal Cancer Incidence and Mortality in Patients With Non-Malignant Findings: A Meta-Analysis[J]. The American Journal of Gastroenterology, 2016, 111(3): 355-365.\u003c/li\u003e\n\u003cli\u003eBrenner H, Chen C. The colorectal cancer epidemic: challenges and opportunities for primary, secondary and tertiary prevention[J]. British Journal of Cancer, 2018, 119(7): 785-792.\u003c/li\u003e\n\u003cli\u003eCorley D A, Jensen C D, Marks A R, et al. Adenoma detection rate and risk of colorectal cancer and death[J]. The New England Journal of Medicine, 2014, 370(14): 1298-1306.\u003c/li\u003e\n\u003cli\u003eHassan C, Spadaccini M, Iannone A, et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis[J]. Gastrointestinal Endoscopy, 2021, 93(1): 77-85.e6.\u003c/li\u003e\n\u003cli\u003eMori Y, Misawa M, Kudo S E. Challenges in artificial intelligence for polyp detection[J]. Digestive Endoscopy: Official Journal of the Japan Gastroenterological Endoscopy Society, 2022, 34(4): 870-871.\u003c/li\u003e\n\u003cli\u003eMurakami D, Yamato M, Arai M, et al. Artificial intelligence in colonoscopy[J]. The Lancet. Gastroenterology \u0026amp; Hepatology, 2021, 6(12): 984-985.\u003c/li\u003e\n\u003cli\u003eChen S, Lu S, Tang Y, et al. A Machine Learning-Based System for Real-Time Polyp Detection (DeFrame): A Retrospective Study[J]. Frontiers in Medicine, 2022, 9: 852553.\u003c/li\u003e\n\u003cli\u003eCheng D C, Ting W C, Chen Y F, et al. AUTOMATIC DETECTION OF COLORECTAL POLYPS IN STATIC IMAGES[J]. Biomedical Engineering: Applications, Basis and Communications, 2011, 23(05): 357-367.\u003c/li\u003e\n\u003cli\u003eHassan C, Spadaccini M, Iannone A, et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis[J]. Gastrointestinal Endoscopy, 2021, 93(1): 77-85.e6.\u003c/li\u003e\n\u003cli\u003eVleugels J L A, Hazewinkel Y, Fockens P, et al. Natural history of diminutive and small colorectal polyps: a systematic literature review[J]. Gastrointestinal Endoscopy, 2017, 85(6): 1169-1176.e1.\u003c/li\u003e\n\u003cli\u003ePabby A, Schoen R E, Weissfeld J L, et al. Analysis of colorectal cancer occurrence during surveillance colonoscopy in the dietary Polyp Prevention Trial[J]. Gastrointestinal Endoscopy, 2005, 61(3): 385-391.\u003c/li\u003e\n\u003cli\u003eIshiyama M, Kudo S ei, Misawa M, et al. Impact of the clinical use of artificial intelligence\u0026ndash;assisted neoplasia detection for colonoscopy: a large-scale prospective, propensity score\u0026ndash;matched study (with video)[J]. Gastrointestinal Endoscopy, 2022, 95(1): 155-163.\u003c/li\u003e\n\u003cli\u003eMori Y, Kudo S E, Misawa M, et al. Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study[J]. Annals of Internal Medicine, 2018, 169(6): 357-366.\u003c/li\u003e\n\u003cli\u003eMori Y, East J E, Hassan C, et al. Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement[J]. Digestive Endoscopy: Official Journal of the Japan Gastroenterological Endoscopy Society, 2023, 35(4): 422-429.\u003c/li\u003e\n\u003cli\u003eHassan C, Balsamo G, Lorenzetti R, et al. Artificial Intelligence Allows Leaving-In-Situ Colorectal Polyps[J]. Clinical Gastroenterology and Hepatology: The Official Clinical Practice Journal of the American Gastroenterological Association, 2022, 20(11): 2505-2513.e4.\u003c/li\u003e\n\u003cli\u003eWallace M B, Sharma P, Bhandari P, et al. Impact of Artificial Intelligence on Miss Rate of Colorectal Neoplasia[J]. Gastroenterology, 2022, 163(1): 295-304.e5.\u003c/li\u003e\n\u003cli\u003eKim N H, Jung Y S, Jeong W S, et al. Miss rate of colorectal neoplastic polyps and risk factors for missed polyps in consecutive colonoscopies[J]. Intestinal Research, 2017, 15(3): 411-418.\u003c/li\u003e\n\u003cli\u003eYamada M, Saito Y, Yamada S, et al. Detection of flat colorectal neoplasia by artificial intelligence: A systematic review[J]. Best Practice \u0026amp; Research. Clinical Gastroenterology, 2021, 52-53: 101745.\u003c/li\u003e\n\u003cli\u003eRepici A, Badalamenti M, Maselli R, et al. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial[J]. Gastroenterology, 2020, 159(2): 512-520.e7.\u003c/li\u003e\n\u003cli\u003eWang P, Berzin T M, Glissen Brown J R, et al. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study[J]. Gut, 2019, 68(10): 1813-1819.\u003c/li\u003e\n\u003cli\u003eGimeno-Garc\u0026iacute;a A Z, Hern\u0026aacute;ndez Negrin D, Hern\u0026aacute;ndez A, et al. Usefulness of a novel computer-aided detection system for colorectal neoplasia: a randomized controlled trial[J]. Gastrointestinal Endoscopy, 2023, 97(3): 528-536.e1.\u003c/li\u003e\n\u003cli\u003eAniwan S, Mekritthikrai K, Kerr S J, et al. Computer-aided detection, mucosal exposure device, their combination, and standard colonoscopy for adenoma detection: a randomized controlled trial[J]. Gastrointestinal Endoscopy, 2023, 97(3): 507-516.\u003c/li\u003e\n\u003cli\u003eDeliwala S S, Hamid K, Barbarawi M, et al. Artificial intelligence (AI) real-time detection vs. routine colonoscopy for colorectal neoplasia: a meta-analysis and trial sequential analysis[J]. International Journal of Colorectal Disease, 2021, 36(11): 2291-2303.\u003c/li\u003e\n\u003cli\u003eMori Y, Wang P, L\u0026oslash;berg M, et al. Impact of Artificial Intelligence on Colonoscopy Surveillance After Polyp Removal: A Pooled Analysis of Randomized Trials[J]. Clinical Gastroenterology and Hepatology: The Official Clinical Practice Journal of the American Gastroenterological Association, 2023, 21(4): 949-959.e2.\u003c/li\u003e\n\u003cli\u003eJin E H, Lee D, Bae J H, et al. Improved Accuracy in Optical Diagnosis of Colorectal Polyps Using Convolutional Neural Networks with Visual Explanations[J]. Gastroenterology, 2020, 158(8): 2169-2179.e8.\u003c/li\u003e\n\u003cli\u003eClark K N, Malecki C K. Academic grit scale: psychometric properties and associations with achievement and life satisfaction[J]. Journal of School Psychology, 2019, 72: 49-66.\u003c/li\u003e\n\u003cli\u003eLee D H, Reasoner K, Lee D. Grit: what is it and why does it matter in medicine?[J]. Postgraduate Medical Journal, 2023, 99(1172): 535-541.\u003c/li\u003e\n\u003cli\u003eHewitt D B, Chung J W, Ellis R J, et al. National Evaluation of Surgical Resident Grit and the Association With Wellness Outcomes[J]. JAMA surgery, 2021, 156(9): 856-863.\u003c/li\u003e\n\u003cli\u003eMart\u0026iacute;nez M E, Baron J A, Lieberman D A, et al. A pooled analysis of advanced colorectal neoplasia diagnoses after colonoscopic polypectomy[J]. Gastroenterology, 2009, 136(3): 832-841.\u003c/li\u003e\n\u003cli\u003eLieberman D, Sullivan B A, Hauser E R, et al. Baseline Colonoscopy Findings Associated With 10-Year Outcomes in a Screening Cohort Undergoing Colonoscopy Surveillance[J]. Gastroenterology, 2020, 158(4): 862-874.e8.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-big-data","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bigd","sideBox":"Learn more about [Journal of Big Data](http://journalofbigdata.springeropen.com)","snPcode":"40537","submissionUrl":"https://submission.nature.com/new-submission/40537/3","title":"Journal of Big Data","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"artificial intelligence, adenoma detection rate, CADe, colonoscopy","lastPublishedDoi":"10.21203/rs.3.rs-4389606/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4389606/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eMost computer-aided detection (CADe) systems depend on the spatial information from static images rendering them unreliable for real-time diagnosis. This research aims to assess the performance of a novel spatial-temporal CADe system.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis randomized study recruited patients 18 years or older scheduled for colonoscopy at four endoscopy centers from June 2023 to September 2023. Participants were randomly assigned to receive CADe colonoscopy or conventional colonoscopy. The primary outcome was ADR. Furthermore, the correlation between endoscopists\u0026rsquo; acceptance rate of the CADe system and ADR was observed.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eAmong 3317 patients, the ADR was 32.1% in the CADe group and 24.7% in the control group (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). The CADe group detected significantly more adenomas\u0026thinsp;\u0026lt;\u0026thinsp;10 mm and flat-type adenomas [(23.3% vs. 18.4%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.001) and (15.5% vs. 9.9%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.001), respectively]. In addition, a significant correlation (r\u0026thinsp;=\u0026thinsp;0.916, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) was observed between the grit score and ADR with the CADe system.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe spatial-temporal CADe system significantly improved overall polyp and adenoma detection, especially for diminutive and flat-type lesions. Moreover, endoscopists with a greater propensity to embrace the CADe system tend to detect a higher proportion of adenomas during colonoscopy.\u003c/p\u003e","manuscriptTitle":"Effect of a novel spatial-temporal computer-aided detection system on adenoma detection during colonoscopy: A multicenter, randomized controlled trial","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-28 16:42:58","doi":"10.21203/rs.3.rs-4389606/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-30T16:56:57+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-06T13:00:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"742552924605771269089211284013425459","date":"2025-10-28T12:25:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"289516361636582761542022571966307768833","date":"2025-07-26T23:09:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"57889436042645378545941088137928574676","date":"2025-07-21T14:05:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"33015500314226577656984332171517020729","date":"2024-10-29T08:34:51+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-06-01T16:50:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-06-01T13:30:29+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-09T10:39:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Big Data","date":"2024-05-08T13:12:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-big-data","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bigd","sideBox":"Learn more about [Journal of Big Data](http://journalofbigdata.springeropen.com)","snPcode":"40537","submissionUrl":"https://submission.nature.com/new-submission/40537/3","title":"Journal of Big Data","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9fc45b1b-172e-4b55-ae80-5208b036590d","owner":[],"postedDate":"May 28th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-26T13:23:46+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-28 16:42:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4389606","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4389606","identity":"rs-4389606","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}