Sessile serrated lesion(SSL)is a major precancerous lesion type of colorectal cancer and one of the main causes of colorectal cancer.SSL has unique tissue structures and morphological features,with low detection rate under endoscopy and high variability in histopathological diagnosis,making it one of the most easily missed lesions in colorectal cancer screening.In recent years,the application of artificial intelligence(AI)in the diagnosis of colorectal cancer has been rapidly increasing.Previous studies have found that AI-assisted endoscopic technology can improve the detection rate and diagnostic accuracy of colorectal SSL,and AI-assisted pathological diagnosis can improve diagnostic efficiency and consistency.This article aims to provide a review of current research on AI technology in colorectal SSL.

Colorectal cancer(CRC)is one of the most common malignant tumors worldwide,and its incidence has been increasing in recent years,especially among young adults.Non-genetic factors,such as dietary habits,lifestyle and intestinal flora,play an important role in the development of CRC.Dietary factors have a close relationship with CRC development.Insufficient fiber intake and excessive consumption of red and processed meat are generally considered major high-risk factors for CRC,while vegetables and fruits are considered as beneficial factors.The roles of calcium supplements,vitamin D,dairy products,and different dietary patterns in the development of CRC are still controversial.Furthermore,obesity,smoking,alcohol consumption,and lack of physical exercise are also associated with the risk of CRC.The imbalance of intestinal flora is also believed to be associated with the development of CRC.Optimizing dietary habits and maintaining a healthy lifestyle can significantly reduce the risk of CRC.Non-steroidal anti-inflammatory drugs and estrogen supplementation may have beneficial effects in reducing the risk of CRC.For certain individuals at high risk,pharmacological intervention may serve as an effective preventive measure.

Biological clock is a pattern of rhythms in which organisms exhibit cycles approaching 24 h in order to adapt to periodic changes in the external environment.Gut microbiota is the sum of extremely large number of microorganisms parasitized in humans and animals.Disorders of the biological clock increase the risk of metabolic diseases,and the occurrence of these disorders is closely related to the interaction with the dysbiosis of the gut microbiota.With the deepening of the understanding of the brain-gut axis,targeting gut microbiota to ameliorate biological clock disorders and associated diseases has achieved major theoretical breakthroughs and was partially applied in clinical practice,including dietary interventions such as time restricted feeding,development of microbial-related products(probiotics and postbiotics),and fecal microbiota transplantation.This article reviews the research progress of intestinal flora and rhythmicity,as well as targeting intestinal flora for the treatment of biological clock disorders,so as to provide new ideas for the prevention and treatment of rhythm disorders and concurrent diseases.

Objective:To explore the effects of medication interval on the quality of split-dose bowel preparation and analyze the independent risk factors affecting the quality of bowel preparation.Methods:This pilot study involved two centers. Adult outpatients who underwent screening, surveillance, and diagnostic colonoscopy in the First Affiliated Hospital of Naval Medical University ( n=46) and the Fifth Hospital of Zhangjiakou ( n=20) between April and June 2023 were enrolled. Bowel preparation was conducted based on the guideline. Patients were divided into the short-interval group (4-<10 hours, n=45) and the long-interval group (10-16 hours, n=21) based on the time between the two administrations of polyethylene glycol during bowel preparation. Differences in terms of patient-reported outcome measurements (patient-reported willingness to repeat the bowel preparation regimen, satisfaction with bowel preparation, satisfaction with sleep), defecation frequency, Boston bowel preparation scale scores, bowel preparation bubble scores, bowel preparation qualified rates, polyp detection rates and incidence of adverse events were compared. Relevant factors influencing bowel preparation quality were analyzed by univariate logistic regression. Results:There were no significant differences in patient-reported willingness to repeat the bowel preparation regimen [88.9% (40/45) VS 85.7% (18/21), χ2<0.001, P>0.999], the satisfaction with bowel preparation [65.9% (29/45) VS 57.1% (12/21), χ2=0.469, P=0.493], or the satisfaction with sleep quality [35.6% (16/45) VS 28.6% (6/21), χ2=0.314, P=0.575] between the short-interval and long-interval groups. Similarly, no significant differences were observed between the groups in defecation frequency (11.3±4.8 VS 10.2±4.4, t=0.861, P=0.395), Boston bowel preparation scale scores (8.2±1.4 scores VS 7.9±1.2 scores, t=1.024, P=0.311), bowel preparation bubble scores (8.6±1.0 scores VS 8.4±1.5 scores, t=0.672, P=0.506), bowel preparation qualified rates [88.9% (40/45) VS 90.5% (19/21), χ2<0.001, P>0.999], polyp detection rates [33.3% (15/45) VS 47.6% (10/21), χ2=1.242, P=0.265], or incidence of adverse events [24.4% (11/45) VS 14.3% (3/21), χ2=0.381, P=0.537]. Univariate logistic analysis suggested that a low-fiber diet ( OR=8.100, 95% CI:1.400-46.849, P=0.019) was an influencing factor for qualified bowel preparation. Conclusion:Medication interval of the two doses of polyethylene glycol in a split-dose bowel preparation regimen for colonoscopy has no significant impact on bowel preparation quality. Notably, preoperative low-fiber diet emerges as an independent protective factor for qualified bowel preparation.

Objective:To explore the effects of medication interval on the quality of split-dose bowel preparation and analyze the independent risk factors affecting the quality of bowel preparation.Methods:This pilot study involved two centers. Adult outpatients who underwent screening, surveillance, and diagnostic colonoscopy in the First Affiliated Hospital of Naval Medical University ( n=46) and the Fifth Hospital of Zhangjiakou ( n=20) between April and June 2023 were enrolled. Bowel preparation was conducted based on the guideline. Patients were divided into the short-interval group (4-<10 hours, n=45) and the long-interval group (10-16 hours, n=21) based on the time between the two administrations of polyethylene glycol during bowel preparation. Differences in terms of patient-reported outcome measurements (patient-reported willingness to repeat the bowel preparation regimen, satisfaction with bowel preparation, satisfaction with sleep), defecation frequency, Boston bowel preparation scale scores, bowel preparation bubble scores, bowel preparation qualified rates, polyp detection rates and incidence of adverse events were compared. Relevant factors influencing bowel preparation quality were analyzed by univariate logistic regression. Results:There were no significant differences in patient-reported willingness to repeat the bowel preparation regimen [88.9% (40/45) VS 85.7% (18/21), χ2<0.001, P>0.999], the satisfaction with bowel preparation [65.9% (29/45) VS 57.1% (12/21), χ2=0.469, P=0.493], or the satisfaction with sleep quality [35.6% (16/45) VS 28.6% (6/21), χ2=0.314, P=0.575] between the short-interval and long-interval groups. Similarly, no significant differences were observed between the groups in defecation frequency (11.3±4.8 VS 10.2±4.4, t=0.861, P=0.395), Boston bowel preparation scale scores (8.2±1.4 scores VS 7.9±1.2 scores, t=1.024, P=0.311), bowel preparation bubble scores (8.6±1.0 scores VS 8.4±1.5 scores, t=0.672, P=0.506), bowel preparation qualified rates [88.9% (40/45) VS 90.5% (19/21), χ2<0.001, P>0.999], polyp detection rates [33.3% (15/45) VS 47.6% (10/21), χ2=1.242, P=0.265], or incidence of adverse events [24.4% (11/45) VS 14.3% (3/21), χ2=0.381, P=0.537]. Univariate logistic analysis suggested that a low-fiber diet ( OR=8.100, 95% CI:1.400-46.849, P=0.019) was an influencing factor for qualified bowel preparation. Conclusion:Medication interval of the two doses of polyethylene glycol in a split-dose bowel preparation regimen for colonoscopy has no significant impact on bowel preparation quality. Notably, preoperative low-fiber diet emerges as an independent protective factor for qualified bowel preparation.

Objective:To explore the feasibility of estimating adenoma detection rate (ADR) based on polyp detection rate (PDR) in colonscopy.Methods:In the present single-center retrospective study, the conversion coefficient was calculated based on the total colonoscopy cases in 2017. ADR of each colonoscopists was estimated based on PDR and conversion coefficient, which was then verified compared with the actual ADR for consistency.Results:A total of 25 112 colonoscopies with 20 experienced colonoscopists were included. The overall conversion coefficient was 0.483. The intraclass correlation coefficient of the actual ADR and the estimated ADR was 0.818 (95% CI: 0.596-0.924, P<0.01). Conclusion:It is feasible to estimate ADR based on PDR, but this method is only an expediency. More attention should be paid to the establishment of a standardized electronic database.

Objective:To investigate the current application of colonoscopy at hospitals in China.Methods:From November 2019 to January 2020, an online questionnaire survey was conducted among gastroenterologists and colonoscopists in hospitals of different levels. The contents of questionnaire survey included basic information of colonoscopy at the respondent′s hospital, protocols and patient education of bowel preparation, implementation of colonoscopy quality control, and colonoscopists′ understanding of polypectomy techniques and post-polypectomy follow-up.Results:A total of 236 valid questionnaires were collected, involving 187 hospitals, and 143 (76.5%) had an annual operation capacity of more than 5 000 cases. In terms of bowel preparation, split-dosed polyethylene glycol electrolyte powder (PEG) was the most commonly used (60.4%, 113/187) and the most common volume of PEG was 3 L (67.4%, 126/187). Verbal (90.9%, 170/187) and written (79.7%, 149/187) instructions were given more often than other methods for patient education of bowel preparation. Antifoaming agent was routinely used in 124 (66.3%) hospitals. In terms of quality control, only 11.5% (20/174) hospitals implemented all four measures. In terms of polypectomy techniques, 98.1% (203/207) colonoscopists chose hot snare polypectomy or endoscopic mucosal resection for lesions of diameter>1 cm, while options varied for lesions of diameter<1 cm. The interval of follow-up after polypectomy recommended by colonoscopists was shorter than that by guidelines.Conclusion:Several problems are found in the survey in the application of colonoscopy in China, i. e., patient education of bowel preparation is not diversified; quality control of colonoscopy still needs to be strengthened; polypectomy techniques and follow-up after polypectomy need to be further standardized.

Objective:To establish an artificial intelligence (AI)-assisted colorectal polyps classification system (AI polyps system) by using clinical big data, and to conduct the clinical verification.Methods:From June 2018 to June 2019, the colonoscopy images of polyps from 16 participating research centers were prospectively collected. The basic information of the polyps (location, size, shape and pathological biopsy results) in colonoscopy images of colorectal polyps were marked by senior colonoscopist, and the outline of the polyp was circled for the development of the AI polyps system. Taking pathological biopsy results of polyps as the gold standard, the sensitivity, specificity, and positivity predictive value (PPV), negative predictive value (NPV) and accuracy of white light model, narrow band imaging (NBI) model, the combination of white light and NBI model and colonoscopists′ identification of polyps were calculated respectively. Paired McNemar test and Kappa test were used for statistical analysis. Results:A total of 15 441 qualified colonoscopy images were collected, including 9 109 images in white light model and 6 332 images in NBI model. At laboratory level, the sensitivity, specificity, PPV, NPV and accuracy of white light model and NBI model in the identification of the polyps were 90.3%, 98.3%, 89.8%, 98.4%, 97.2%, and 90.5%, 92.5%, 92.3%, 90.6%, 91.5%, respectively. In clinical verification phase, a total of 78 polyps of 56 patients with colorectal polyps were enrolled. The sensitivity, specificity, PPV, NPV and accuracy of the white light model and NBI model in the identification of polyps were 70.3%, 82.1%, 78.8%, 74.4%, 76.3%, and 78.4%, 87.2%, 85.3%, 81.0%, 82.9%, respectively. There were no statistically significant differences between the diagnostic results of colonoscopists, the white light model, the NBI model and the results of pathological results (all McNemar test, all P>0.05), but the consistency were general and the Kappa values were 0.632, 0.525 and 0.657, respectively (all P<0.01). The Kappa value of combination of the white light and NBI model and the pathological results was 0.575, however the consistency was general, but the difterence was statistically significant (McNemar test, P=0.004). Conclusions:The established AI polyps system has a certain role in assisting diagnosis, but the accuracy still needs to be improved.

Objective: To evaluate the clinical value of a commercial low-residue diet (LRD) for bowel preparation of colonoscopy. Methods: This study was a prospective, endoscopist-blind, and randomized controlled trial. Participants were randomly assigned to two groups according to administration of LRD: the experimental group and the control group. Bowel preparation quality, compliance and tolerability of the two groups were compared. Results: A total of 61 patients were enrolled, with 32 in the experimental group and 29 in the control group. The outcomes were as follows: Boston Bowel Preparation Scale (BBPS) (7.8±1.0 VS 7.1±1.3, P=0.037), the rate of bowel preparation adequacy (87.5% VS 79.3%, P=0.388), compliance rate of dietary restriction (78.1% VS 55.2%, P=0.057), preparation completion rate (93.8% VS 93.1%, P=0.919), cecal intubation rate (both were 100.0%) and cecum arrival time (9.1±2.9 min VS 9.8±3.7 min, P=0.417), incidence of adverse (3.1% VS 3.4%, P=0.944), and hunger rate before colonoscopy (34.4% VS 48.3%, P=0.102). Conclusion The LRD for bowel preparation of colonoscopy significantly improves BBPS, but its effect on improving the bowel preparation adequacy, patient compliance and tolerability needs to be confirmed by further larger-scale trials.

With the development of computer science and technology, artificial intelligence and big data have made key breakthroughs in various areas. The medical and health field has also been greatly affected. Although the diagnosis, treatment, monitoring and management of pancreatic diseases is relatively difficult, artificial intelligence and medical big data are being applied in these aspects and showing obvious advantages and potential for the application.