The clinical burden of colorectal cancer (CRC) is high. Population-based screening and early detection are essential to improve the long-term clinical outcome. Nonetheless, a significant proportion of patients still present at an advanced stage, including with acute large bowel obstruction. Image-enhanced endoscopy and artificial intelligence can improve the detection and diagnosis of colonic adenomas and early cancer. Endoscopic resection is regarded as the preferred curative treatment option for colonic adenoma and T0 and T1 CRC limited to the superficial submucosa. Emergency colonic stenting as bridge to interval curative surgery is increasingly accepted as a first-line option when technically feasible. Minimally invasive resection techniques such as laparoscopic colectomy and robot-assisted colorectal surgery have also come of age. These techniques reduce post-treatment morbidity, shorten the recovery process and can be cost-effective while maintaining long-term oncological cure. These outcome measures are relevant to our patients; therefore, minimally invasive approaches to curative resection should be embraced.
Humans ; Colorectal Neoplasms/surgery* ; Minimally Invasive Surgical Procedures/methods* ; Laparoscopy/methods* ; Colectomy/methods* ; Robotic Surgical Procedures/methods* ; Treatment Outcome ; Colonoscopy/methods*

BACKGROUND: Over 20 million colonoscopies are performed in China annually. An automatic clinical decision support system (CDSS) with accurate semantic recognition of colonoscopy reports and guideline-based is helpful to relieve the increasing medical burden and standardize the healthcare. In this study, the CDSS was built under a hierarchical-label interpretable classification framework, trained by a state-of-the-art transformer-based model, and validated in a multi-center style. METHODS: We conducted stratified sampling on a previously established dataset containing 302,965 electronic colonoscopy reports with pathology, identified 2041 patients' records representative of overall features, and randomly divided into the training and testing sets (7:3). A total of five main labels and 22 sublabels were applied to annotate each record on a network platform, and the data were trained respectively by three pre-training models on Chinese corpus website, including bidirectional encoder representations from transformers (BERT)-base-Chinese (BC), the BERT-wwm-ext-Chinese (BWEC), and ernie-3.0-base-zh (E3BZ). The performance of trained models was subsequently compared with a randomly initialized model, and the preferred model was selected. Model fine-tuning was applied to further enhance the capacity. The system was validated in five other hospitals with 3177 consecutive colonoscopy cases. RESULTS: The E3BZ pre-trained model exhibited the best performance, with a 90.18% accuracy and a 69.14% Macro-F1 score overall. The model achieved 100% accuracy in identifying cancer cases and 99.16% for normal cases. In external validation, the model exhibited favorable consistency and good performance among five hospitals. CONCLUSIONS The novel CDSS possesses high-level semantic recognition of colonoscopy reports, provides appropriate recommendations, and holds the potential to be a powerful tool for physicians and patients. The hierarchical multi-label strategy and pre-training method should be amendable to manage more medical text in the future.
Humans ; Colonoscopy/methods* ; Deep Learning ; Decision Support Systems, Clinical ; Female ; Male

Screening and early diagnosis and treatment have been proven effective in reducing the incidence and mortality of colorectal cancer. Colonoscopy combined with pathological examination is the gold standard for colorectal cancer screening. However, due to the invasiveness, high cost and the need for professional endoscopists of colonoscopy, it is not feasible to directly use this method for mass population screening. Fecal immunochemical test (FIT) is one of the screening techniques recommended by authoritative international guidelines for colorectal cancer screening, and has been widely used in population-based colorectal cancer screening programs in countries around the world. This paper elaborates on the value of FIT in colorectal cancer screening from different aspects, such as the technical principles, the screening efficiency, the screening strategies, and the population effects and benefits. Additionally, it describes the current situation of colorectal cancer screening in China and summarizes the challenges faced in colorectal cancer screening in order to optimize the FIT-based colorectal cancer screening strategies in the population and provide theoretical reference for effective colorectal cancer screening.
Humans ; Early Detection of Cancer/methods* ; Colonoscopy ; Mass Screening ; Colorectal Neoplasms/pathology* ; Occult Blood

BACKGROUND: Colorectal cancer (CRC) screening is effective in reducing CRC incidence and mortality. The aim of this study was to retrospectively determine and compare the detection rate of adenomas, advanced adenomas (AAs) and CRCs, and the number needed to screen (NNS) of individuals in an average-risk Chinese population of different ages and genders. METHODS: This was a retrospective study performed at the Institute of Health Management, Chinese People's Liberation Army General Hospital. Colonoscopy results were analyzed for 53,152 individuals finally enrolled from January 2013 to December 2019. The detection rate of adenomas, AAs, or CRCs was computed and the characteristics between men and women were compared using chi-squared test. RESULTS: The average age was 48.8 years (standard deviation [SD], 8.5 years) for men and 50.0 years (SD, 9.0 years) for women, and the gender rate was 66.27% (35,226) vs . 33.73% (17,926). The detection rates of adenomas, AAs, serrated adenomas, and CRCs were 14.58% (7750), 3.09% (1641), 1.23% (653), and 0.59% (313), respectively. Men were statistically significantly associated with higher detection rates than women in adenomas (17.20% [6058/35,226], 95% confidence interval [CI] 16.74-17.53% vs . 9.44% [1692/17,926], 95% CI 8.94-9.79%, P  < 0.001), AAs (3.72% [1309], 95% CI 3.47-3.87% vs . 1.85% [332], 95% CI 1.61-2.00%, P  < 0.001), and serrated adenomas (1.56% [548], 95% CI 1.43-1.69% vs . 0.59% [105], 95% CI 0.47-0.70%, P  < 0.001). The detection rate of AAs in individuals aged 45 to 49 years was 3.17% (270/8510, 95% CI 2.80-3.55%) in men and 1.69% (69/4091, 95% CI 1.12-1.86%) in women, and their NNS was 31.55 (95% CI 28.17-35.71) in men and 67.11 (95% CI 53.76-89.29) in women. The NNS for AAs in men aged 45 to 49 years was close to that in women aged 65 to 69 years (29.07 [95% CI 21.05-46.73]). CONCLUSIONS The detection rates of adenomas, AAs, and serrated adenomas are high in the asymptomatic population undergoing a physical examination and are associated with gender and age. Our findings will provide important references for effective population-based CRC screening strategies in the future.
Humans ; Male ; Female ; Middle Aged ; Retrospective Studies ; Early Detection of Cancer ; Colonoscopy/methods* ; Adenoma/epidemiology* ; Colorectal Neoplasms/epidemiology*

Objective: To explore the utility of stool-based DNA test of methylated SDC2 (mSDC2) for colorectal cancer (CRC) screening in residents of Shipai Town, Dongguan City. Methods: This was a cross-sectional study. Using a cluster sampling method, residents of 18 villages in Shipai Town, Dongguan City were screened for CRC from May 2021 to February 2022. In this study, mSDC2 testing was employed as a preliminary screening method. Colonoscopy examination was recommended for individuals identified as high-risk based on the positive mSDC2 tests. The final screening results, including the rate of positive mSDC2 tests, the rate of colonoscopy compliance, the rate of lesions detection, and the cost-effectiveness of screening, were analyzed to explore the benefits of this screening strategy. Results: A total of 10 708 residents were enrolled and completed mSDC2 testing, giving a participation rate of 54.99% (10 708/19 474) and a pass rate of 97.87% (10 708/10 941). These individuals included 4 713 men (44.01%) and 5 995 women (55.99%) with a mean age of (54.52±9.64) years. The participants were allocated to four age groups (40-49, 50-59, 60-69, and 70-74 years), comprising 35.21%(3770/10 708), 36.25% (3882/10 708), 18.84% (2017/10 708), and 9.70% (1039/10 708) of all participants, respectively. mSDC2 testing was positive in 821/10 708 (7.67%) participants, 521 of whom underwent colonoscopy, resulting in a compliance rate of 63.46% (521/821). After eliminating of 8 individuals without pathology results, data from 513 individuals were finally analyzed. Colonoscopy detection rate differed significantly between age groups (χ²=23.155, P<0.001),ranging from a low of 60.74% in the 40-49 year age group to a high of 86.11% in the 70-74 year age group. Colonoscopies resulted in the diagnosis of 25 (4.87%) CRCs, 192 (37.43%) advanced adenomas, 67 (13.06%) early adenomas, 15 (2.92%) serrated polyps, and 86 (16.76%) non- adenomatous polyps. The 25 CRCs were Stage 0 in 14 (56.0%) individuals, stage I in 4 (16.0%), and Stage II in 7(28.0%). Thus, 18 of the detected CRCs were at an early stage. The early detection rate of CRCs and advanced adenomas was 96.77% (210/217). The rate of mSDC2 testing for all intestinal lesions was 75.05% (385/513). In particular, the financial benefit of this screening was 32.64 million yuan, and the benefit-cost ratio was 6.0. Conclusion: Screening for CRCs using stool-based mSDC2 testing combined with colonoscopy has a high lesion detection rate and a high cost-effectiveness ratio. This is a CRC screening strategy that deserves to be promoted in China.
Male ; Humans ; Female ; Adult ; Middle Aged ; Cross-Sectional Studies ; Early Detection of Cancer/methods* ; Colorectal Neoplasms/pathology* ; Colonoscopy/methods* ; Mass Screening/methods* ; Adenoma/diagnosis* ; DNA ; Syndecan-2/genetics*

OBJECTIVE: To study the effect of propofol used for painless gastroscopy and colonoscopy on psychomotility recovery. METHODS: One hundred adult patients undergoing painless gastroscopy and colonoscopy were recruited, aged 18-72 years, with American Society of Anesthesiologist (ASA) physical status Ⅰ-Ⅱ. According to age, the patients were divided into youth group (20-39 years old, 27 cases), middle age group (40-54 years old, 37 cases), and elder group (55-64 years old, 36 cases). Propofol was continuously infused according to the patients' condition to mantain the bispectal index (BIS) score 55-64. All the patients received psychomotility assesment 30 min before the operations when the discharge criteria were met including number cancellation test, number connection test and board test. The heart rate, blood pressure, saturation of pulse oximetry, electrocardiograph and BIS were monitored during the operation. The operating time, recovery time, total volume of propofol and discharge time were recorded. If the results obtained were inferior to those before operation, a third assessment was taken 30 minutes later until the results recovered or being superior to the baseline levels. RESULTS: All the patients completed the first and second assessments, and 25 patients had taken the third assessment. There was no statistically significant difference in the results of psychomotility assessment when the patients met the discharge standard. Furthermore, the results were analyzed by grouping with age, and there was no statistical difference in the test results of the youth and middle age groups compared with the preoperative group, among which, the efficiency of the number cancellation test was significantly better than that before operation in the youth group (P < 0.05). However, in the elderly patients the number cancellation efficiency, number connection test and board test were significantly inferior to that before operation (P < 0.05). There was no significant difference in the accuracy of number cancellation compared with that before operation. The patients who needed the third test in the elder group were significantly more than in the other groups (P < 0.05). Compared with the preoperative results, there was no statistical difference in the test results of those who completed the third test. CONCLUSION The psychomotility function of the patients who underwent painless gastroscopy and colonoscopy was recovered when they met discharge criteria. The elderly patients had a prolonged recovery period.
Adult ; Aged ; Middle Aged ; Adolescent ; Humans ; Young Adult ; Propofol ; Hypnotics and Sedatives ; Gastroscopy/methods* ; Conscious Sedation/methods* ; Colonoscopy/methods*

Screening and early diagnosis and treatment have been proven effective in reducing the incidence and mortality of colorectal cancer. Colonoscopy combined with pathological examination is the gold standard for colorectal cancer screening. However, due to the invasiveness, high cost and the need for professional endoscopists of colonoscopy, it is not feasible to directly use this method for mass population screening. Fecal immunochemical test (FIT) is one of the screening techniques recommended by authoritative international guidelines for colorectal cancer screening, and has been widely used in population-based colorectal cancer screening programs in countries around the world. This paper elaborates on the value of FIT in colorectal cancer screening from different aspects, such as the technical principles, the screening efficiency, the screening strategies, and the population effects and benefits. Additionally, it describes the current situation of colorectal cancer screening in China and summarizes the challenges faced in colorectal cancer screening in order to optimize the FIT-based colorectal cancer screening strategies in the population and provide theoretical reference for effective colorectal cancer screening.
Humans ; Early Detection of Cancer/methods* ; Colonoscopy ; Mass Screening ; Colorectal Neoplasms/pathology* ; Occult Blood

Colonoscopy with endoscopic resection of detected colonic adenomas interrupts the adenoma-carcinoma sequence and reduces the incidence of colorectal cancer and cancer-related mortality. In the past decade, there have been significant developments in instruments and techniques for endoscopic polypectomy. Guidelines have been formulated by various professional bodies in Europe, Japan and the United States, but some of the recommendations differ between the various bodies. An expert professional workgroup under the auspices of the Academy of Medicine, Singapore, was set up to provide guidance on the endoscopic management of colonic polyps in Singapore. A total of 23 recommendations addressed the following issues: accurate description and diagnostic evaluation of detected polyps; techniques to reduce the risk of post-polypectomy bleeding and delayed perforation; the role of specific endoscopic resection techniques; the histopathological criteria for defining endoscopic cure; and the role of surveillance colonoscopy following curative resection.
Adenoma/surgery* ; Colonic Neoplasms/surgery* ; Colonic Polyps/surgery* ; Colonoscopy/methods* ; Colorectal Neoplasms/pathology* ; Humans ; Singapore ; United States

Colonoscopy is the reference standard procedure for the prevention and diagnosis of colorectal cancer, which is a leading cause of cancer-related deaths in Singapore. Artificial intelligence systems are automated, objective and reproducible. Artificial intelligence-assisted colonoscopy has recently been introduced into clinical practice as a clinical decision support tool. This review article provides a summary of the current published data and discusses ongoing research and current clinical applications of artificial intelligence-assisted colonoscopy.
Artificial Intelligence ; Colonic Polyps/diagnosis* ; Colonoscopy/methods* ; Colorectal Neoplasms/diagnosis* ; Diagnosis, Computer-Assisted ; Humans

Objective: To investigate the value of stool-based methylated SDC2 test in physical examination population for the screening of colorectal neoplasms. Methods: Using the prospective cohort study method, from December 2020 to November 2021, 2 107 participants from the First People's Hospital of Xiushui County, Jiangxi Province were enrolled, consisted of 1 012 males and 1 094 females, aged 20-90 years with the median age of 49 years old. Fresh stool samples were collected and SDC2 DNA methylation tests were carried out as the primary screening method. The participants with positive results were recommended to undergo colonoscopy, and those who were negative were followed up by telephone. The positive rate of screening, the compliance of colonoscopy, and the detection of colorectal lesions were analyzed by chi-square test. Combined the follow-up results of negative subjects, the value of SDC2 DNA methylation test for the screening of colorectal neoplasms was evaluated. Results: Among the 2 107 participants, 2 106 completed the SDC2 methylation test. 113 participants (5.4%) were positive. The positive rate of primary screening increased with age significantly (χ²=32.135, P<0.001). Out of 113 cases, 72 (63.7%) underwent colonoscopy examinations. Finally, 3 (4.2%) cases of colorectal cancer, 12 (16.7%) cases of advanced adenoma, 31 (43.1%) cases of non-advanced adenoma, and 16 (22.2%) cases of non-adenomatous polyp were detected. The positive predictive value (PPV) of stool-based SDC2 DNA methylation test for intestinal lesions and colorectal neoplasms were 86.1% and 63.9%, respectively. Among the 1 374 follow-up participants, the negative predictive value (NPV) of this test for intestinal lesions and colorectal neoplasms were 97.7% and 99.4%, respectively. Conclusion: Primary stool-based SDC2 DNA methylation test and subsequent colonoscopy examination can effectively find colorectal neoplasms. This strategy may be a potential tool for the screening of colorectal neoplasms in general risk population.
Male ; Female ; Humans ; Middle Aged ; Sensitivity and Specificity ; Prospective Studies ; Early Detection of Cancer/methods* ; Colorectal Neoplasms/diagnosis* ; Mass Screening/methods* ; Feces ; DNA Methylation ; Colonoscopy ; Physical Examination ; Syndecan-2/genetics*