Visceral adipose tissue reduction measured by deep neural network architecture improved reflux esophagitis endoscopic grade.

BACKGROUND AND AIMS: Visceral obesity is a risk factor for reflux esophagitis (RE). We investigated the risk of RE according to visceral adipose tissue (VAT) measured by deep neural network architecture using computed tomography and evaluated the longitudinal association between abdominal adipose tissue changes and the disease course of RE. METHODS: Individuals receiving health checkups who underwent esophagogastroduodenoscopy (EGD) and abdominal computed tomography (CT) at Seoul National University Healthcare System Gangnam Center between 2015 and 2016 were included. Visceral and subcutaneous adipose tissue areas and volumes were measured using a deep neural network architecture and CT. The association between the abdominal adipose tissue area and volume and the risk of RE was evaluated. Participants who underwent follow-up EGD and abdominal CT were selected; the effects of changes in abdominal adipose tissue area and volume on RE endoscopic grade were investigated using Cox proportional hazards regression. RESULTS: We enrolled 6570 patients who underwent EGD and abdomen CT on the same day. RE was associated with male sex, hypertension, diabetes, excessive alcohol intake, current smoking status, and levels of physical activity. The VAT area and volume increased the risk of RE dose-dependently. A decreasing VAT volume was significantly associated with improvement in RE endoscopic grade (HR:3.22, 95%CI:1.82-5.71). Changes in subcutaneous adipose tissue volume and the disease course of RE were not significantly correlated. CONCLUSIONS: Visceral obesity is strongly associated with RE. VAT volume reduction was prospectively associated with improvement in RE endoscopic grade dose-dependently. Visceral obesity is a potential target for RE treatment.

Impact of Smoking and Alcohol Consumption on Early-Onset Gastric Cancer Development in Young Koreans: A Population-Based Study.

PURPOSE: Although smoking and alcohol consumption are known risk factors for gastric cancer (GC), studies assessing their effects on early-onset GC are limited. In this nationwide, population-based, prospective cohort study, we assessed the effects of smoking and alcohol consumption on early-onset GC in patients aged <50 years. MATERIALS AND METHODS: We analyzed data of patients aged 20-39 years who underwent cancer and general health screening in the Korean National Health Screening Program between 2009 and 2012. We calculated the adjusted hazard ratios (aHR) and 95% confidence intervals (CI) for GC incidence until December 2020. RESULTS: We enrolled 6,793,699 individuals (men:women=4,077,292:2,716,407) in this cohort. The mean duration of follow-up was 9.4 years. During follow-up, 9,893 cases of GC (men:women=6,304:3,589) were reported. Compared with the aHRs (95% CI) of never-smokers, those of former and current-smokers were 1.121 (1.044-1.205) and 1.282 (1.212-1.355), respectively. Compared with the aHRs (95% CI) of non-consumers, those of low-moderate- and high-risk alcohol consumers were 1.095 (1.046-1.146) and 1.212 (1.113-1.321), respectively. GC risk was the highest in current-smokers and high-risk alcohol consumers (1.447 [1.297-1.615]). Interestingly, alcohol consumption and smoking additively increased the GC risk in men but not in women (Pinteraction=0.002). CONCLUSION: Smoking and alcohol consumption are significant risk factors for early-onset GC in young Koreans. Further studies are needed to investigate sex-based impact of alcohol consumption and smoking on GC incidence in young individuals.

Boston bowel preparation scale score 6 has more missed lesions compared with 7-9.

Adequate bowel preparation is an important factor in high-quality colonoscopy. It is generally accepted that a Boston Bowel Preparation Scale (BBPS) score ≥ 6 is adequate, but some reports suggest ≥ 7. Subjects who underwent colonoscopy at least twice within 3 years from August 2015 to December 2019 were included. Polyp detection rates (PDRs), adenoma detection rates (ADRs), and number of polyps including adenomas were compared stratified by baseline colonoscopy (C1) BBPS score. Among 2352 subjects, 529 had BBPS 6 (group 1) and 1823 had BBPS 7-9 (group 2) at C1. There was no significant difference in PDR or ADR at C1 and follow-up colonoscopy (C2) between the two groups. However, the numbers of polyps (1.84 vs. 1.56, P = 0.001) and adenomas (1.02 vs. 0.88, P = 0.034) at C2 were significantly higher in group 1 than group 2, respectively. Segmental BBPS score 2 in group 1 compared to group 2, especially, showed higher PDR (P = 0.001) and ADR (P = 0.007) at C2. BBPS 6 is associated with a higher number of polyps and adenomas in short-term follow-up colonoscopy than BBPS 7-9. To reduce the risk of missed polyps, a thorough examination is necessary for BBPS 6.

Enhancing artificial intelligence-doctor collaboration for computer-aided diagnosis in colonoscopy through improved digital literacy.

Establishing appropriate trust and maintaining a balanced reliance on digital resources are vital for accurate optical diagnoses and effective integration of computer-aided diagnosis (CADx) in colonoscopy. Active learning using diverse polyp image datasets can help in developing precise CADx systems. Enhancing doctors' digital literacy and interpreting their results is crucial. Explainable artificial intelligence (AI) addresses opacity, and textual descriptions, along with AI-generated content, deepen the interpretability of AI-based findings by doctors. AI conveying uncertainties and decision confidence aids doctors' acceptance of results. Optimal AI-doctor collaboration requires improving algorithm performance, transparency, addressing uncertainties, and enhancing doctors' optical diagnostic skills.

The Persistence of Hypertriglyceridemia and the Risk of Early Onset Colorectal Cancer According to Tumor Subsites: A Nationwide Population-based Study.

Purpose: The incidence of early-onset colorectal cancer (EoCRC) is increasing worldwide. The association between hypertriglyceridemia (HTG) and EoCRC risk remains unclear. Materials and Methods: We conducted a nationwide cohort study of 3,340,635 individuals aged 20-49 years who underwent health checkups between 2009 and 2011 under the Korean National Health Insurance Service. HTG was defined as serum triglyceride (TG) level ≥ 150 mg/dL. According to the change in TG status, participants were categorized into persistent normotriglyceridemia (NTG, group 1), NTG to HTG (group 2), HTG to NTG (group 3), and persistent HTG (group 4) groups. The EoCRC incidence was followed up until 2019. Results: In total, 7492 EoCRC cases developed after a mean of 6.05 years of follow-up. Group 4 had the highest risk of EoCRC (adjusted hazard ratio [aHR]: 1.097, 95% confidence interval [CI]: 1.025-1.174). While the risk of rectal cancer was significantly increased in groups 3 and 4 (aHR [95% CI]: 1.236[1.076-1.419] and 1.175[1.042-1.325], respectively), no significant risk differences were observed in right colon cancer. In group 4, male sex and diabetes were associated with a further increased risk of EoCRC (aHR [95% CI]:1.149[1.082-1.221] and 1.409[1.169-1.699], respectively). In addition, there was a dose-response relationship between serum TG levels and the risk of EoCRC (p for trends < 0.0001). Conclusion: Persistent HTG increased the risk of EoCRC, which was significantly higher only for rectal cancer and marginally higher for other colonic subsites.

Alteration of Metabolic Syndrome Is Associated with the Decreased Risk of Colorectal Cancer.

Metabolic syndrome (MetS) can be resolved through active control. We aimed to examine the effect of changes in MetS status on colorectal cancer (CRC) risk. A total of 5,704,611 Korean national insurance beneficiaries that received two consecutive biennial mandatory health exams (2009-2011) were followed-up until 2017. MetS was determined as the presence of at least three of five components. Participants were categorized into four groups according to the change in MetS status; MetS-never, -resolved, -developed, or -persistent. A Cox proportional hazards model adjusted for age, sex, smoking, alcohol drinking, and physical exercise was used. Participants who recovered from MetS had a higher risk of CRC than those free of MetS but had a lower risk than those with persistent MetS (HR: 0.91, 95% CI: 0.86-0.95 vs. HR: 0.75, 95% CI: 0.73-0.78; reference: persistence group). Among the five MetS components, resolving high blood pressure, abdominal obesity, and blood sugar had a preventive effect on CRC prevention, while normalization of lipid profile did not reduce CRC risk independently. Resolving MetS could reduce CRC risk compared to having persistent MetS, indicating the necessity of considering control of MetS as a CRC prevention policy.

Association of changes in obesity and abdominal obesity status with early-onset colorectal cancer risk: a nationwide population-based cohort study.

Background and aims: The incidence of early-onset colorectal cancer (EO-CRC, diagnosed before 50 years of age) has increased in recent decades. The aim of this study was to investigate the association between changes in obesity status and EO-CRC risk. Methods: From a nationwide population-based cohort, individuals <50 years old who participated in the national health checkup program in both 2009 and 2011 were included. Obesity was defined as a body mass index ≥25 kg/m2. Abdominal obesity was defined as a waist circumference ≥ 90 cm in men and ≥ 85 cm in women. Participants were classified into 4 groups according to the change in obesity (normal/normal, normal/obese, obese/normal, persistent obese) and abdominal obesity (normal/normal, normal/abdominal obesity, abdominal obesity/normal, persistent abdominal obesity) status. Participants were followed up until 2019 and censored when they became 50 years old. Results: Among 3,340,635 participants, 7,492 patients were diagnosed with EO-CRC during 7.1 years of follow-up. The risk of EO-CRC was higher in the persistent obesity and persistent abdominal obesity groups than in the normal/normal groups (hazard ratio (HR) [95% confidence interval (CI)] = 1.09 [1.03-1.16] and 1.18 [1.09-1.29], respectively). Participants with both persistent obesity and abdominal obesity had a higher EO-CRC risk than those in the normal/normal groups for both [HR (95% CI) = 1.19 (1.09-1.30)]. Conclusion: Persistent obesity and persistent abdominal obesity before the age of 50 are associated with a slightly increased risk of EO-CRC. Addressing obesity and abdominal obesity in young individuals might be beneficial in reducing the risk of EO-CRC.

The risk of colorectal cancer according to obesity status at four-year intervals: a nationwide population-based cohort study.

Obesity is a risk factor for colorectal cancer. However, the effect of body weight change on colorectal cancer is uncertain. This study aimed to investigate the relationship between difference in body mass index and the risk of colorectal cancer. In this nationwide population-based cohort study, participants of the national cancer screening program in 2005 and 2009 were enrolled. Difference of body mass index was calculated from screening data from 2005 and 2009. Participants were divided into four groups according to direction of obesity status: non-obese/non-obese, non-obese/obese, obese/non-obese, and obese/obese. The effect of differences in body mass index on colorectal cancer was analyzed. Among 3,858,228 participants, 47,894 (1.24%) participants were newly diagnosed with colorectal cancer during the 9.2 years of follow-up. The incidence of colorectal cancer was higher in the obese/obese group than the non-obese/non-obese group (hazard ratio = 1.08 [1.06-1.11], P trend < 0.001). The men in the obese/obese group had a higher risk of colon cancer than women (hazard ratio = 1.13 [1.10-1.17] in men, and hazard ratio = 1.04 [1.01-1.18] in women, P = 0.001). Persistent obesity was associated with a higher risk of incidence of colorectal cancer.

Sex and Tumor-Site Differences in the Association of Alcohol Intake With the Risk of Early-Onset Colorectal Cancer.

PURPOSE: Given the increasing incidence of early-onset colorectal cancer (CRC; diagnosed before age 50 years) worldwide, it is important to identify modifiable risk factors. We investigated whether alcohol consumption in the young population correlated with an increased early-onset CRC risk that differed by tumor location and sex. PATIENTS AND METHODS: We investigated the association between average daily alcohol consumption and the risk of early-onset CRC among 5,666,576 individuals age 20-49 years using data from the Korean National Health Insurance Service (2009-2019). Alcohol consumption levels of nondrinker, light (reference), moderate, and heavy drinker were defined as 0, <10, 10 to <30, and ≥30 g/d for men and 0, <10, 10 to <20, and ≥20 g/d for women, respectively. Multivariate Cox proportional hazards models were used to estimate adjusted hazard ratios (aHRs) with 95% CIs. RESULTS: We identified 8,314 incident early-onset CRC cases during the follow-up period. Moderate and heavy drinkers showed an increased risk of early-onset CRC compared with light drinkers (aHR, 1.09 [95% CI, 1.02 to 1.16] and aHR, 1.20 [95% CI, 1.11 to 1.29], respectively). Subgroup analysis by tumor location showed positive dose-response significance for early-onset distal colon and rectal cancers, but not for proximal colon cancer. The dose-response association between drinking frequency and risk of early-onset CRC was significant, with a 7%, 14%, and 27% increased risk for 1-2, 3-4, and ≥5 d/wk compared with nondrinkers, respectively. CONCLUSION: Excessive alcohol consumption increases the risk of CRC onset before age 50 years. Thus, effective interventions are required to discourage alcohol consumption among young people and to tailor CRC screening approaches for high-risk individuals.

Allergic Diseases and Risk of Malignancy of Gastrointestinal Cancers.

The aim of this study was to investigate the effect of allergic diseases, including allergic rhinitis, asthma, and atopic dermatitis, on the development of gastrointestinal (GI) cancers. We analyzed 9,892,633 Korean adults who underwent a medical check-up in the year 2009, and they were followed up until the year 2017. Allergic diseases and cancers were defined using the International Classification of Disease Codes. A Cox proportional hazards model was adapted to calculate the hazard ratios (HRs) and 95% confidence intervals (CIs). During a 7.3-year follow-up period, 48,045 patients were diagnosed with cancer. For all-combined allergic diseases, significant inverse associations were observed for cancers of the esophagus, stomach, colorectum, and liver (adjusted hazard ratios (aHRs [95% confidence interval, CI] 0.86 [0.82-0.91], 0.93 [0.91-0.94], 0.95 [0.93-0.96], and 0.90 [0.88-0.92], respectively). The sex-stratified analysis showed that the preventive effect of allergic diseases was persistent in gastric, colorectal, and liver cancers regardless of sex, while the inverse associations with esophageal and pancreatic cancers were observed only in men (aHR [95% CI] 0.84 [0.80-0.89] and 0.96 [0.93-0.99]). Allergic diseases, particularly allergic rhinitis, in adults were significantly associated with a decreased risk of most GI cancers, except for gallbladder and biliary tract cancers.

Impact of 3-second rule for high confidence assignment on the performance of endoscopists for the real-time optical diagnosis of colorectal polyps.

BACKGROUND: Confusion between high and low confidence decisions in optical diagnosis hinders the implementation of real-time optical diagnosis in clinical practice. We evaluated the effect of a 3-second rule (decision time limited to 3 seconds for a high confidence assignment) in expert and nonexpert endoscopists. METHODS: This single-center prospective study included eight board-certified gastroenterologists. A 2-month baseline phase used standard real-time optical diagnosis for colorectal polyps < 10 mm and was followed by a 6-month intervention phase using optical diagnosis with the 3-second rule. Performance, including high confidence accuracy, and Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) and Simple Optical Diagnosis Accuracy (SODA) thresholds, was measured. RESULTS: Real-time optical diagnosis was performed on 1793 patients with 3694 polyps. There was significant improvement in high confidence accuracy between baseline and intervention phases in the nonexpert group (79.2 % vs. 86.3 %; P = 0.01) but not in the expert group (85.3 % vs. 87.5 %; P = 0.53). Using the 3-second rule improved the overall performance of PIVI and SODA in both groups. CONCLUSIONS: The 3-second rule was effective in improving real-time optical diagnosis performance, especially in nonexperts.

Risk of cancer in patients with insomnia: Nationwide retrospective cohort study (2009-2018).

PURPOSE: To investigate the association between insomnia and the risk of various cancers using the Korean National Health Insurance Service database. MATERIALS AND METHODS: Patients who underwent a national health examination in 2009 were followed-up until 2018. Newly-diagnosed cancers were collected one year after the baseline. Insomnia was defined as having a diagnosis of F510 or G470 within one year prior to enrollment. The incidence of various cancers was compared between patients with and without insomnia. RESULTS: In the overall study population (N = 3,982,012), the risk for any type of cancer was not different between controls and insomnia patients (adjusted hazard ratio [aHR]: 0.990). However, it was different by age; insomnia increased the risk of any cancer in younger age groups (20-39y and 40-59y, aHR:1.310 and 1.139, respectively) but it significantly decreased the risk in the 60-79y age group (aHR: 0.939). In cancer type, colorectal cancer risk was lower (aHR: 0.872, P < 0.0001), whereas leukemia risk was higher (aHR: 1.402, P < 0.0001) in patients with insomnia than in those without it, regardless of sex. In men, the risk of stomach cancer was lower (aHR: 0.882, P = 0.0003), and the risks of lung (aHR:1.114, P = 0.0005), kidney (aHR 1.226, P = 0.0107), and prostate (aHR:1.101, P = 0.0028) cancers were higher in insomnia patients than in control patients. In women, insomnia patients compared to control patients showed a lower risk of ovarian cancer (aHR:0.856, P = 0.0344, respectively), while they had a higher risk of oral (aHR:1.616, P = 0.002), thyroid (aHR:1.072, P = 0.0192), and nerve (aHR: 1.251, P = 0.016) cancers. CONCLUSION: Insomnia is associated with an increased or decreased risk of some cancers, depending on age, cancer type and sex.

Endoscopists performance in optical diagnosis of colorectal polyps in artificial intelligence studies.

Widespread adoption of optical diagnosis of colorectal neoplasia is prevented by suboptimal endoscopist performance and lack of standardized training and competence evaluation. We aimed to assess diagnostic accuracy of endoscopists in optical diagnosis of colorectal neoplasia in the framework of artificial intelligence (AI) validation studies. Literature searches of databases (PubMed/MEDLINE, EMBASE, Scopus) up to April 2022 were performed to identify articles evaluating accuracy of individual endoscopists in performing optical diagnosis of colorectal neoplasia within studies validating AI against a histologically verified ground-truth. The main outcomes were endoscopists' pooled sensitivity, specificity, positive and negative predictive value (PPV/NPV), positive and negative likelihood ratio (LR) and area under the curve (AUC for sROC) for predicting adenomas versus non-adenomas. Six studies with 67 endoscopists and 2085 (IQR: 115-243,5) patients were evaluated. Pooled sensitivity and specificity for adenomatous histology was respectively 84.5% (95% CI 80.3%-88%) and 83% (95% CI 79.6%-85.9%), corresponding to a PPV, NPV, LR+, LR- of 89.5% (95% CI 87.1%-91.5%), 75.7% (95% CI 70.1%-80.7%), 5 (95% CI 3.9%-6.2%) and 0.19 (95% CI 0.14%-0.25%). The AUC was 0.82 (CI 0.76-0.90). Expert endoscopists showed a higher sensitivity than non-experts (90.5%, [95% CI 87.6%-92.7%] vs. 75.5%, [95% CI 66.5%-82.7%], p < 0.001), and Eastern endoscopists showed a higher sensitivity than Western (85%, [95% CI 80.5%-88.6%] vs. 75.8%, [95% CI 70.2%-80.6%]). Quality was graded high for 3 studies and low for 3 studies. We show that human accuracy for diagnosis of colorectal neoplasia in the setting of AI studies is suboptimal. Educational interventions could benefit by AI validation settings which seem a feasible framework for competence assessment.

Association Between Metabolic Syndrome and the Risk of Colorectal Cancer Diagnosed Before Age 50 Years According to Tumor Location.

BACKGROUND & AIMS: The increasing prevalence of obesity at younger ages is concurrent with an increased earlier-onset colorectal cancer (CRC) (before age 50 years) incidence, particularly left-sided colon cancer. We investigated whether obesity and metabolic syndrome (MetS) are associated with increased earlier-onset CRC risk according to tumor location. METHODS: Our nationwide population-based cohort study enrolled 9,774,081 individuals who underwent health checkups under the Korean National Health Insurance Service from 2009 to 2010, with follow-up until 2019. We collected data on age, sex, lifestyle factors, body mass index (BMI), waist circumference (WC), blood pressure, and laboratory findings. A multivariate Cox proportional hazards regression analysis was performed. RESULTS: A total of 8320 earlier-onset and 57,257 later-onset CRC cases developed during follow-up. MetS was associated with increased earlier-onset CRC (adjusted hazard ratio, 1.20; 95% CI, 1.14-1.27), similar to later-onset CRC (adjusted hazard ratio, 1.19; 95% CI, 1.17-1.21). The adjusted hazard ratios for earlier-onset CRC with 1, 2, 3, 4, and 5 MetS components were 1.07 (95% CI, 1.01-1.13), 1.13 (95% CI, 1.06-1.21), 1.25 (95% CI, 1.16-1.35), 1.27 (95% CI, 1.15-1.41), and 1.50 (95% CI, 1.26-1.79), respectively (P for trend < .0001). We found that higher body mass index and larger waist circumference were significantly associated with increased earlier-onset CRC (P for trend < .0001). These dose-response associations were significant in distal colon and rectal cancers, although not in proximal colon cancers. CONCLUSIONS: MetS and obesity are positively associated with CRC before age 50 years with a similar magnitude of association as people diagnosed after age 50 years. Thus, people younger than 50 years with MetS require effective preventive interventions to help reduce CRC risk.

Natural Language Processing for Information Extraction of Gastric Diseases and Its Application in Large-Scale Clinical Research.

Background and Aims: The utility of clinical information from esophagogastroduodenoscopy (EGD) reports has been limited because of its unstructured narrative format. We developed a natural language processing (NLP) pipeline that automatically extracts information about gastric diseases from unstructured EGD reports and demonstrated its applicability in clinical research. Methods: An NLP pipeline was developed using 2000 EGD and associated pathology reports that were retrieved from a single healthcare center. The pipeline extracted clinical information, including the presence, location, and size, for 10 gastric diseases from the EGD reports. It was validated with 1000 EGD reports by evaluating sensitivity, positive predictive value (PPV), accuracy, and F1 score. The pipeline was applied to 248,966 EGD reports from 2010-2019 to identify patient demographics and clinical information for 10 gastric diseases. Results: For gastritis information extraction, we achieved an overall sensitivity, PPV, accuracy, and F1 score of 0.966, 0.972, 0.996, and 0.967, respectively. Other gastric diseases, such as ulcers, and neoplastic diseases achieved an overall sensitivity, PPV, accuracy, and F1 score of 0.975, 0.982, 0.999, and 0.978, respectively. The study of EGD data of over 10 years revealed the demographics of patients with gastric diseases by sex and age. In addition, the study identified the extent and locations of gastritis and other gastric diseases, respectively. Conclusions: We demonstrated the feasibility of the NLP pipeline providing an automated extraction of gastric disease information from EGD reports. Incorporating the pipeline can facilitate large-scale clinical research to better understand gastric diseases.

Increased Risk of Cancer after Cholecystectomy: A Nationwide Cohort Study in Korea including 123,295 Patients.

Background/Aims: Contradictory findings on the association between cholecystectomy and cancer have been reported. We aimed to investigate the risk of all types of cancers or site-specific cancers in patients who underwent cholecystectomy using a nationwide dataset. Methods: Subjects who underwent cholecystectomy from January 1, 2007, to December 31, 2014, who were older than 20 years and who underwent an initial baseline health check-up within 2 years were enrolled. Those who were diagnosed with any type of cancer before the enrollment or within 1 year after enrollment were excluded. Ultimately, patients (n=123,295) who underwent cholecystectomy and age/sex matched population (n=123,295) were identified from the database of the Korean National Health Insurance Service. The hazard ratio (HR) and 95% confidence interval (CI) for cancer were estimated, and Cox regression analysis was performed. Results: The incidence of cancer in the cholecystectomy group was 9.56 per 1,000 person-years and that in the control group was 7.95 per 1,000 person-years. Patients who underwent cholecystectomy showed an increased risk of total cancer (adjusted HR, 1.19; 95% CI, 1.15 to 1.24; p<0.001), particularly leukemia and malignancies of the colon, liver, pancreas, biliary tract, thyroid, pharynx, and oral cavity. In the subgroup analysis according to sex, the risk of developing cancers in the pancreas, biliary tract, thyroid, lungs and stomach was higher in men than in women. Conclusions: Physicians should pay more attention to the possibility of the occurrence of secondary cancers among patients who undergo cholecystectomy.

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

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

Impact of comprehensive optical diagnosis training using Workgroup serrAted polypS and Polyposis classification on detection of adenoma and sessile serrated lesion.

OBJECTIVES: Many interventions have been attempted to improve adenoma detection rate (ADR) and sessile serrated lesion detection rate (SDR), and one of these interventions is educational training to recognize polyp characteristics. This study aimed to investigate the change in polyp detection rates of endoscopists before and after comprehensive training through the Gangnam-Real Time Optical Diagnosis (Gangnam-READI) program. METHODS: Fifteen gastroenterologists participated in a 1-year comprehensive training program that consisted of ex vivo and in vivo training that encompasses knowledge and skills in endoscopic characterization of colonic polyps using the Workgroup serrAted polypS and Polyposis (WASP) classification. We evaluated the impact of the training program by comparing the overall and individual ADR and SDR 6 months before and after the training. RESULTS: Overall, 18,280 polyps (9337 adenomas and 855 sessile serrated lesion) were collected. The optical diagnosis training had no significant impact on the difference in ADR after training compared to before training (47.7% vs. 46.5%, P = 0.608). A tendency for a decrease in ADR variance was noted among the endoscopists after training (74.9 vs. 32.7, P = 0.121). The overall pre-training period SDR was 4.5% and showed a statistically significant increase to 5.6%, 8.0%, and 7.1% in the first and second half of the training period, and post-training period, respectively (P = 0.003). The optical diagnosis training did not decrease variance in SDR (8.9 vs. 8.8, P = 0.985). CONCLUSION: Comprehensive optical diagnosis training with WASP classification has a significant impact on increasing the overall SDR of expert endoscopists.

Small sessile serrated polyps might not be at a higher risk for future advanced neoplasia than low-risk adenomas or polyp-free groups.

BACKGROUND: Polypectomy surveillance colonoscopy is recommended according to the risk stratification of initially removed polyps. This study aimed to evaluate the risk of advanced neoplasia following low-risk SSPs compared with that following LRAs and polyp-free groups. MATERIALS AND METHODS: From September 2013 to August 2017, asymptomatic Koreans aged 50-75 years who underwent surveillance colonoscopy post-baseline colonoscopy were enrolled. The 1314 participants who met the study design criteria were stratified into three groups according to the presence of LRAs or low-risk SSPs. The rate of advanced neoplasia was then compared between groups by surveillance colonoscopy. RESULTS: A total of 1314 participants were classified according to baseline colonoscopy findings: no polyp (n = 551), LRA (n = 707), and low-risk SSP (n = 56). All participants underwent surveillance colonoscopy after an average of 28.1 ± 8.7 months. The rate of advanced neoplasia at surveillance was not different between groups: no polyp group (13/551, 2.4%), LRA group (27/707, 3.8%), and low-risk SSP group (0/56, 0%). The LRA group exhibited a significantly higher rate of low- and high-risk polyps (47.5, 13.4%) than did the no polyp (35.6, 7.4%, p < .001, p = .001), but no significant differences to the low-risk SSP group (35.7, 7.1%, p = .117, p = .253), respectively. CONCLUSIONS: Patients with low-risk SSPs were not at a higher risk of advanced neoplasia than LRA patients, even in the polyp-free group. We suggest that surveillance colonoscopy after the removal of low-risk SSPs is not required more often than for LRAs.