Search

Background/Aims: We investigated how interactions between humans and computer-aided detection (CADe) systems are influenced by the user’s experience and polyp characteristics.Methods: We developed a CADe system using YOLOv4, trained on 16,996 polyp images from 1,914 patients and 1,800 synthesized sessile serrated lesion (SSL) images. The performance of polyp detection with CADe assistance was evaluated using a computerized test module. Eighteen participants were grouped by colonoscopy experience (nurses, fellows, and experts). The value added by CADe based on the histopathology and detection difficulty of polyps were analyzed.Results: The area under the curve for CADe was 0.87 (95% confidence interval [CI], 0.83 to 0.91). CADe assistance increased overall polyp detection accuracy from 69.7% to 77.7% (odds ratio [OR], 1.88; 95% CI, 1.69 to 2.09). However, accuracy decreased when CADe inaccurately detected a polyp (OR, 0.72; 95% CI, 0.58 to 0.87). The impact of CADe assistance was most and least prominent in the nurses (OR, 1.97; 95% CI, 1.71 to 2.27) and the experts (OR, 1.42; 95% CI, 1.15 to 1.74), respectively. Participants demonstrated better sensitivity with CADe assistance, achieving 81.7% for adenomas and 92.4% for easy-to-detect polyps, surpassing the standalone CADe performance of 79.7% and 89.8%, respectively. For SSLs and difficult-to-detect polyps, participants' sensitivities with CADe assistance (66.5% and 71.5%, respectively) were below those of standalone CADe (81.1% and 74.4%). Compared to the other two groups (56.1% and 61.7%), the expert group showed sensitivity closest to that of standalone CADe in detecting SSLs (79.7% vs 81.1%, respectively).Conclusions: CADe assistance boosts polyp detection significantly, but its effectiveness depends on the user’s experience, particularly for challenging lesions.

Abstract Background Dementia is associated with older adults; however, it can also affect younger individuals, known as young-onset dementia (YOD), when diagnosed before the age of 65 years. We aimed to conduct a retrospective cohort study involving middle-aged women to investigate the association between premorbid depression and YOD development. Methods We included 1.6 million women aged 40–60 years who underwent health checkups under the Korean National Health Insurance Service and investigated the association between depression and YOD. Results Women with depression had a significantly higher risk of developing YOD than women without depression. Among premenopausal women, those with depression had a 2.67-fold increased risk, whereas postmenopausal women with depression had a 2.50-fold increased risk. Late age at menarche (> 16 years) and young age at menopause (

Background/Aims: The pathophysiology of lean nonalcoholic fatty liver disease (NAFLD) is unclear but has been shown to be associated with more diverse pathogenic mechanisms than that of obese NAFLD. We investigated the characteristics of genetic or metabolic lean NAFLD in a health checkup cohort. Methods : This retrospective cross-sectional study analyzed single nucleotide polymorphism data for 6,939 health examinees. Lean individuals were categorized according to a body mass index cutoff of 23 kg/m2. Single nucleotide polymorphisms were analyzed using genotyping arrays. Results : The prevalence of lean NAFLD was 21.6% among all participants with NAFLD, and the proportion of lean NAFLD was 18.5% among lean participants. The prevalence of metabolic syndrome and diabetes among lean patients with NAFLD was 12.4% and 10.4%, respectively. Lean NAFLD appeared to be metabolic-associated in approximately 20.1% of patients. The homozygous minor allele (GG) of PNPLA3 (rs738409) and heterozygous minor alleles (CT, TT) of TM6SF2 (rs58542926) were associated with lean NAFLD. However, the prevalence of fatty liver was not associated with the genetic variants MBOAT7 (rs641738), HSD17B13 (rs72613567), MARC1 (rs2642438), or AGXT2 (rs2291702) in lean individuals. Lean NAFLD appeared to be associated with PNPLA3 or TM6SF2 genetic variation in approximately 32.1% of cases. Multivariate risk factor analysis showed that metabolic risk factors, genetic risk variants, and waist circumference were independent risk factors for lean NAFLD. Conclusion : s: In a considerable number of patients, lean NAFLD did not appear to be associated with known genetic or metabolic risk factors. Further studies are required to investigate additional risk factors and gain a more comprehensive understanding of lean NAFLD.

IntroductionThe decreasing Helicobacter pylori eradication rate is primarily attributed to antibiotic resistance, and further exacerbated by uniform drug administration disregarding a host’s metabolic capability. Consequently, applying personalized treatment based on antibiotic resistance-associated variants and the host’s metabolic phenotype can potentially increase the eradication rate.MethodA custom next-generation sequencing panel for personalized H. pylori eradication treatment (NGS-PHET) was designed which targeted the regions for amoxicillin, clarithromycin, metronidazole, tetracycline, and levofloxacin-resistance in H. pylori and human proton-pump inhibitor (PPI) metabolism. The libraries were constructed following customized methods and sequenced simultaneously. The customized framework criteria, grounded in previously reported antibiotic resistance associated variants and the host’s PPI metabolism, was applied to the NGS-PHET results and suggested a personalized treatment for each subject, which was validated through each subject’s actual eradication outcome.ResultsBoth previously reported and novel variants were identified from H. pylori sequencing results. Concurrently, five CYP2C19 homozygous extensive metabolizers and three CYP3A4 intermediate metabolizers were identified. Among the total of 12 subjects, clarithromycin triple therapy was suggested for five subjects, bismuth quadruple therapy was suggested for six subjects, and rifabutin triple therapy was suggested for one subject by following the customized framework criteria. The treatment suggestion for nine of the 12 subjects was consistent with the treatment that each subject achieved eradication with.DiscussionApplying the methodology using the NGS-PHET and customized framework helps to perform eradication treatment quickly and effectively in most patients with antibiotic-resistant H. pylori strains, and is also useful in research to find novel antibiotic-resistance candidates.

Abstract 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.

Abstract Recognizing anatomical sections during colonoscopy is crucial for diagnosing colonic diseases and generating accurate reports. While recent studies have endeavored to identify anatomical regions of the colon using deep learning, the deformable anatomical characteristics of the colon pose challenges for establishing a reliable localization system. This study presents a system utilizing 100 colonoscopy videos, combining density clustering and deep learning. Cascaded CNN models are employed to estimate the appendix orifice (AO), flexures, and "outside of the body," sequentially. Subsequently, DBSCAN algorithm is applied to identify anatomical sections. Clustering-based analysis integrates clinical knowledge and context based on the anatomical section within the model. We address challenges posed by colonoscopy images through non-informative removal preprocessing. The image data is labeled by clinicians, and the system deduces section correspondence stochastically. The model categorizes the colon into three sections: right (cecum and ascending colon), middle (transverse colon), and left (descending colon, sigmoid colon, rectum). We estimated the appearance time of anatomical boundaries with an average error of 6.31 s for AO, 9.79 s for HF, 27.69 s for SF, and 3.26 s for outside of the body. The proposed method can facilitate future advancements towards AI-based automatic reporting, offering time-saving efficacy and standardization.

Abstract 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

Background Little is known about the adverse events (AEs) associated with coronavirus disease 2019 (COVID-19) vaccination in patients with type 2 diabetes mellitus (T2DM). Methods This study used vaccine AE reporting system data to investigate severe AEs among vaccinated patients with T2DM. A natural language processing algorithm was applied to identify people with and without diabetes. After 1:3 matching, we collected data for 6,829 patients with T2DM and 20,487 healthy controls. Multiple logistic regression analysis was used to calculate the odds ratio for severe AEs. Results After COVID-19 vaccination, patients with T2DM were more likely to experience eight severe AEs than controls: cerebral venous sinus thrombosis, encephalitis myelitis encephalomyelitis, Bell’s palsy, lymphadenopathy, ischemic stroke, deep vein thrombosis (DVT), thrombocytopenia (TP), and pulmonary embolism (PE). Moreover, patients with T2DM vaccinated with BNT162b2 and mRNA-1273 were more vulnerable to DVT and TP than those vaccinated with JNJ-78436735. Among patients with T2DM administered mRNA vaccines, mRNA-1273 was safer than BNT162b2 in terms of the risk of DVT and PE. Conclusion Careful monitoring of severe AEs in patients with T2DM may be necessary, especially for those related to thrombotic events and neurological dysfunctions after COVID-19 vaccination.

Artificial intelligence is becoming increasingly important in the air combat domain. Most air combat research now assumes that all aircraft information is known. In practical applications, however, some aircraft information, such as their position, attitude, velocity, etc., can be incorrect or impossible to obtain due to realistic limitations and sensor errors. In this paper, we propose a deep reinforcement learning-based framework for developing a model capable of performing within visual range (WVR) air-to-air combat under the conditions of a partially observable Markov decision process (POMDP) with insufficient information. To deal robustly with such a situation, we use recurrent neural networks and apply a soft actor-critic (SAC) algorithm to cope effectively with realistic limitations and sensor errors. Additionally, to raise the efficiency and effectiveness of learning, we apply the curriculum learning technique to restrict the scope of exploration in state space. Finally, simulations and experiments show that the proposed techniques can deal with practical problems caused by sensor limitations and errors in a noisy environment while also being efficient and effective in reducing the training time for learning.

Background and aimsThe 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.MethodsFrom a nationwide population-based cohort, individuals

Introduction: The standard management of orbital cellulitis is to administer a combination of intravenous broad-spectrum antibiotics along with treatment of associated sinusitis. Objective: The purpose of this study was to evaluate whether the addition of corticosteroids could lead to earlier resolution of inflammation and improve disease outcome. Methods: We independently searched five databases (PubMed, SCOPUS, Embase, the Web of Science, and the Cochrane database) for studies published as recent as December 2019. Of the included studies, we reviewed orbital cellulitis and disease morbidity through lengths of hospitalization, incidence of surgical drainage, periorbital edema, vision, levels or C-reactive protein, and serum WBC levels in order to focus on comparing steroid with antibiotics treated group and only antibiotics treated group. Results: Lengths of hospitalization after admission as diagnosed as orbital cellulitis (SMD = −4.02 [−7.93; −0.12], p-value = 0.04, I2 = 96.9%) decrease in steroid with antibiotics treated group compared to antibiotics only treated group. Incidence of surgical drainage (OR = 0.78 [0.27; 2.23], p-value = 0.64, I2 = 0.0%) was lower in the steroid with antibiotics treated group compared to the antibiotics only treated group. Conclusion: Use of systemic steroids as an adjunct to systemic antibiotic therapy for orbital cellulitis may decrease orbital inflammation with a low risk of exacerbating infection. Based on our analysis, we concluded that early use of steroids for a short period can help shorten hospitalization days and prevent inflammation progression.

Abstract Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. To be an effective system, it is important to detect additional polyps that may be easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor to colorectal cancer with a relatively higher miss rate, owing to their flat and subtle morphology. Colonoscopy CADe systems could help endoscopists; however, the current systems exhibit a very low performance for detecting SSLs. We propose a polyp detection system that reflects the morphological characteristics of SSLs to detect unrecognized or easily missed polyps. To develop a well-trained system with imbalanced polyp data, a generative adversarial network (GAN) was used to synthesize high-resolution whole endoscopic images, including SSL. Quantitative and qualitative evaluations on GAN-synthesized images ensure that synthetic images are realistic and include SSL endoscopic features. Moreover, traditional augmentation methods were used to compare the efficacy of the GAN augmentation method. The CADe system augmented with GAN synthesized images showed a 17.5% improvement in sensitivity on SSLs. Consequently, we verified the potential of the GAN to synthesize high-resolution images with endoscopic features and the proposed system was found to be effective in detecting easily missed polyps during a colonoscopy.

Despite the growing demand for unmanned aerial vehicles (UAVs), the use of conventional UAVs is limited, as most of them require being remotely operated by a person who is not within the vehicle’s field of view. Recently, many studies have introduced reinforcement learning (RL) to address hurdles for the autonomous flight of UAVs. However, most previous studies have assumed overly simplified environments, and thus, they cannot be applied to real-world UAV operation scenarios. To address the limitations of previous studies, we propose a stepwise soft actor–critic (SeSAC) algorithm for efficient learning in a continuous state and action space environment. SeSAC aims to overcome the inefficiency of learning caused by attempting challenging tasks from the beginning. Instead, it starts with easier missions and gradually increases the difficulty level during training, ultimately achieving the final goal. We also control a learning hyperparameter of the soft actor–critic algorithm and implement a positive buffer mechanism during training to enhance learning effectiveness. Our proposed algorithm was verified in a six-degree-of-freedom (DOF) flight environment with high-dimensional state and action spaces. The experimental results demonstrate that the proposed algorithm successfully completed missions in two challenging scenarios, one for disaster management and another for counter-terrorism missions, while surpassing the performance of other baseline approaches.

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Central skull base osteomyelitis (CSBO) is a rare, fatal condition seen mostly in elderly diabetic or immunocompromised patients; it mainly involves the sphenoid or occipital bones and diagnosis is often delayed. A 72-year-old male with diabetes was referred to our department with severe pain in the maxillary gingiva. Endoscopic biopsy of the pterygoid bone confirmed the presence of mucormycosis combined with Klebsiella pneumoniae infection. Sinus surgery was performed with bilateral alveolar bone sequestrectomy. Long-term intravenous broad-spectrum antibiotic therapy using meropenem and ampicillin/sulbactam and antifungal therapy using amphotericin B (100 mg/day) was administered; an oral antifungal agent, posaconazole (800 mg/day), was also prescribed for 11 weeks. At the 6-month follow-up visit, there were no complications and no progression of the CSBO lesion was observed. Timely diagnosis and multidisciplinary treatment including endoscopic surgery, alveolar bone sequestrectomy, and combined antifungal and antibiotic therapy can reduce mortality and minimize complications associated with CSBO.

BackgroundManual 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. ObjectiveWe 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. MethodsThe 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. ResultsThe 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. ConclusionsThe 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.

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Colonoscopy is one of the most useful procedures for making the diagnosis and treating various colorectal diseases, but this procedure rarely causes serious complications such as perforation. The incidence of colon perforation during colonoscopy is low. However, as the demand for screening and surveillance colonoscopy has gradually increased and colonoscopic polypectomy has become a commoner procedure in daily clinical practice, endoscopists should pay attention to prevent and manage colonoscopy-related perforation. The purpose of this review is to briefly summarize the guidelines from the World Journal of Emergency Surgery for the management of colonoscopy-related perforation.

Endoscopic resection has been shown to reduce incidence and mortality of colorectal cancer. Endoscopic management has become an established therapeutic option for colorectal neoplasia, and therefore, polypectomy is among the most important colonoscopy skills to develop. An endoscopist performing polypectomy, such as cold snare polypectomy, hot snare polypectomy, and endoscopic mucosal resection (EMR), should be knowledgeable and skilled in selecting and performing the proper endoscopic technique to ensure curability and safety. Here, we report and summarize the key recommendations made in the recent guideline for polypectomy and EMR developed by European Society of Gastrointestinal Endoscopy.

Amyloidosis is a disease in which amyloid is abnormally accumulated in the tissue. The kidney and heart are the most commonly involved organs. Gastric involvement is relatively common in systemic disease; however, localized gastric amyloidosis is rare. Here, we report a case of localized gastric amyloidosis with two separate lesions. A 56-year-old woman underwent a health surveillance checkup without any noticeable symptoms. She was under medication for diabetes and dyslipidemia, and was otherwise healthy. On surveillance upper endoscopy, an irregularly shaped hyperemic elevated erosion at the gastric fundus and a 1.5-cm, yellowish subepithelial tumor-like lesion with intact overlying mucosa at the lesser curvature of the lower body of the stomach were detected. Endoscopic biopsy revealed submucosal eosinophilic material deposition in both lesions. Congo-red staining showed amyloid deposit appearing as a yellow-green birefringence under polarizing microscopy. Echocardiography, abdominal sonography, and colonoscopy revealed no abnormality. The patient was diagnosed as having localized gastric amyloidosis and is now undergoing regular follow-up without any treatment. Localized gastric amyloidosis is a rare disease that may mimic nonspecific gastritis or subepithelial tumor. However, endoscopic biopsy with appropriate staining may be diagnostic and thorough evaluation for systemic involvement is important.

Ulcerative colitis (UC) is a chronic inflammatory condition of the colon, characterized by diffuse mucosal inflammation with bloody diarrhea. The therapeutic goals in UC have evolved from symptomatic relief to deep remission, including sustained steroid-free clinical remission, mucosal healing, and ideally histologic remission. The management of UC has significantly been improved by advance of biologic agents including anti-tumor necrosis factor alpha (TNF-α) antibodies. Anti-TNF-α agent have progressively been introduced earlier in treatment algorithms for UC in order to minimize steroid exposure and dependence and to maximize disease control and quality of life. We reviewed the therapeutic recommendations of biologic agents for UC in the Korean and European Crohn’s and Colitis Organization guidelines.

Background/AimsWe attempted to investigate the prognosis of signet-ring cell carcinoma (SRC) patients who underwent curative surgery by comparing them with age-, sex-, and stage-matched non-mucinous adenocarcinoma (NMAC) patients.MethodsBetween January 2003 and December 2011, 19 patients with primary SRC of the colorectum underwent curative surgery. Four SRC patients under the age of 40 were excluded, and the clinicopathological data of 15 patients (7 men; median age, 56 years) were reviewed and compared with the data of 75 NMAC patients matched by age, sex, and pathologic stage.ResultsThe median follow-up duration was 30.1 months for the SRC group and 43.7 months for the NMAC group (P=0.141). Involvement of the left side of the colon (73.3% vs. 26.7%, P=0.003) and infiltrative lesions such as Borrmann types 3 and 4 (85.7% vs. 24.0%, P=0.001) were more common in the SRC group than in the NMAC group. The five-year overall survival rate was significantly lower for patients with SRC than for those with NMAC (46.0% vs. 88.7%, hazard ratio, 6.99; 95% confidence interval, 2.33-20.95, P=0.001).ConclusionsPatients with even resectable primary colorectal SRC had a poorer prognosis than age-, sex-, and stage-matched colorectal NMAC patients.

This study was designed to measure the efficacy of a nasal valve suspension technique and determine the adequate traction length without creation of nasofacial fullness in a cadaveric model. Seven fresh frozen cadaveric heads were evaluated. Minimal cross-sectional (MCA) areas were measured with a transient-signal acoustic rhinometer (Ecco Vision; Hood Instruments, Pembroke, MA) before and after suspension. The adequate traction length, which did not cause obvious changes, was determined. Five millimeters of lateral nasal valve traction was determined to be the maximal traction achievable without creating facial fullness. After lateral nasal suspension, average MCA increased by 13.7%. Average distance to the MCA from the nostril changed from 1.57 to 1.76 cm. Postsuspension values were significantly higher than the presuspension values (p < 0.05). Nasal valve suspension with 5 mm of lateral traction has a significant impact on nasal valve area without obvious nasofacial changes.

Background/Aims Although the 3-second rule has been shown in our previous study to improve high-confidence (HC) assessment in optical diagnosis, the process remains not well-established. Additionally, the impact of recent advances in artificial intelligence and its interaction with endoscopists remains uncertain. This study aimed to evaluate the effectiveness of a new computer-aided diagnosis (CADx) system, combined with the 3-second rule, in the optical diagnosis of colorectal polyps among endoscopists with varying levels of experience. Methods This multicenter ex vivo study involved 35 endoscopists, each of whom evaluated 100 polyps (51 adenomas, 39 hyperplastic polyps, 10 sessile serrated lesions) using narrow-band imaging (NBI) video clips via an online test platform. The evaluations were conducted in two stages: independent diagnosis and diagnosis with CADx assistance. HC was defined by the 3-second rule established in a previous study. Performance metrics included HC accuracy, HC rate, and adherence to the Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) and Simple Optical Diagnosis Accuracy (SODA) thresholds. Results The stand-alone performance of CADx demonstrated accuracy, sensitivity, specificity, and positive and negative predictive values of 90.0%, 95.1%, 82.1%, 89.2%, and 91.4%, respectively. The CADx-assisted phase, using the 3-second rule, significantly improved both HC accuracy (78.3% vs. 89.8%; p<0.001) and HC rates (64.2% vs. 75.4%; p<0.001) across all groups. Notably, novice endoscopists exhibited a substantial increase in accuracy with CADx assistance (74.1% vs. 88.8%; p<0.0001) (Table). The CADx-assisted performance for HC diagnoses nearly achieved the SODA standards and PIVI thresholds when combined with the use of the 3-second rule (Figure). Conclusion The new CADx system, when used in conjunction with the 3-second rule, significantly enhances the optical diagnosis of colorectal polyps, particularly among less experienced endoscopists. This combined approach could be valuable for cost-effective management strategies for colorectal polyps. [ABSTRACT FROM AUTHOR]