Epidemiological monitoring and genetic variation analysis of pathogens associated with porcine viral diarrhea in southern China from 2021 to 2023.

Large-scale outbreaks of virus-associated severe diarrhea have occurred in pig populations since 2010. To investigate the prevalence and genetic evolution of the diarrhea-associated viruses responsible for the outbreaks, we tested 1,791 diarrhea samples collected from 213 pig farms in five provinces in southern China between 2021 and 2023. The test results showed that porcine epidemic diarrhea virus (PEDV) was the most frequently detected virus. The prevalence rates ranged from 47.40 to 52.22% in samples and 76.06% (162/213) in pig farms. Porcine rotavirus (PoRV) was the second common virus, with prevalence rates ranging from 25.81 to 50.81% in samples and 72.77%(155/213) in pig farms. Porcine delta coronavirus (PDCoV) was the third common virus, with prevalence rates ranging from 16.33 to 17.48% in samples and 38.50% (82/213) in pig farms. The detection rates of both transmissible gastroenteritis virus (TGEV) and porcine acute diarrheal syndrome coronavirus (SADS-CoV) were very low, less than 1.01% in samples and less than 3.76% in pig farms. In this study, we found SADS-CoV only in piglet diarrhea samples from Jiangxi, Guangdong, and Guangxi provinces in China, with a prevalence rate of 5.16% (11/213) in pig farms. Co-infection with these diarrhea-associated viruses is a common occurrence. The most common co-infections were PEDV and PoRV, with a prevalence rate of 6.64% (119/1,791), followed by PDCoV and PoRV, with a prevalence rate of 4.19% (75/1,791). Phylogenetic analyses showed that PEDV and PEDV variants prevalent in southern China during the past three years clustered into genotype GIIb and recombinant PEDV subtypes. Among the currently endemic PEDV, the most common mutations occurred in the collagenase equivalent (COE) and epitope regions of the spike gene. PoRV strains were mainly dominated by the G9 subtype, followed by the G5, G3 and G4 subtypes. Our results suggest that variant PEDV, PDCoV and PoRV are the main pathogens of swine diarrhea, and singular- or co-infection with pathogenic enteric CoV is common in pig herds in southern China. Therefore, prevention and control of porcine viral diarrhea should be given high attention.

Chemical control of CRISPR/Cpf1 editing via orthogonal activation and deactivation of crosslinked crRNA.

Through the integration of CRISPR/Cpf1 with optogenetics and a reduction-responsive motif, we have developed a photoactivatable cross-linked crRNA that enables precise genome editing upon light exposure. This system also allows for termination of editing activity through external application of reducing agent. The dual-stimuli-responsive CRISPR/Cpf1 editing process operates in a unique OFF → ON → OFF sequence, making it a valuable tool for investigating time-sensitive biological events.

Development and implementation of a high-fidelity simulation training course for medical and nursing collaboration based on the Fink integrated course design model.

Aim: The purpose of this study is to examine the design and implementation of a high-fidelity simulation training course for medical and nursing collaboration, based on the Fink integrated course design model. Additionally, the study aims to validate the teaching effectiveness of the course. Background: Previous empirical studies have highlighted the effectiveness of collaborative healthcare education in institutional teaching and hospital training. However, the development of healthcare collaborative education in China has been slow to develop in China. In recent years, Chinese nursing educators and researchers have shown interest in utilizing high-fidelity simulators for healthcare collaborative education. These simulators help address the limitations of traditional nursing teaching and healthcare separation simulation. Nevertheless, a standardized simulation interprofessional education curriculum is still lacking. Therefore, nursing educators need to develop a standardized high-fidelity simulation training curriculum for healthcare collaboration, guided by established science curriculum development theories. Methods: A high-fidelity simulation training course on healthcare collaboration was designed based on the Fink integrated curriculum design model. The course was taught to 14 nursing students and 8 clinical medicine students from March to July 2022. To comprehensively evaluate the effectiveness of the healthcare collaboration high-fidelity simulation training course, several assessment tools were used. These included course grades, satisfaction and self-confidence scales, simulation teaching practice scales, healthcare collaboration attitude scales, critical thinking skills scales, and semi-structured interviews. Results: After the course was implemented, students demonstrated high overall scores (79.19 ± 5.12) and reported high satisfaction ratings (4.44 ± 0.37). They also exhibited increased self-confidence (4.16 ± 0.33). Additionally, students evaluated all four dimensions of the course teaching practice scale positively. Furthermore, the study demonstrated significant improvements in various aspects, such as attitudes toward medical and nursing collaboration (t = -7.135, P < 0.01), shared education and teamwork (t = -3.247, P = 0.002), job autonomy for nurses (t = -1.782, P = 0.000), and reduced physician dominance (t = -6.768, P = 0.000). The critical thinking skills of the students showed significant improvement, with higher scores in truth-seeking (t = -3.052, P = 0.004), analytical ability (t = -2.561, P = 0.014), systematic ability (t = -3.491, P = 0.001), self-confidence in critical thinking (t = -4.024, P = 0.000), and curiosity (t = -5.318, P = 0.000) compared to their scores before the course (all P < 0.05). The interviews showed that the course's student-centered approach enabled active learning. Students suggested enhancing teaching cases and allocating more time for reflection and summarization. Conclusion: The study successfully designed a high-fidelity simulation training course for healthcare collaboration by utilizing the Fink integrated curriculum design model. The findings provide valuable insights for the development of standardized curricula and healthcare collaboration education in China. Moreover, the course adheres to best practice principles, fostering improved attitudes toward healthcare collaboration and enhancing students' healthcare collaboration and clinical thinking skills.

Detection and genetic diversity of subgroup K avian leukosis virus in local chicken breeds in Jiangxi from 2021 to 2023.

Avian leukosis virus subgroup K (ALV-K) is a new subgroup of avian leukosis virus (ALV) that was first identified in Chinese native chickens in recent years. To further understand the molecular epidemiology and evolutionary diversity of ALV-K, this study investigated the molecular epidemiology of 73,664 chicken plasma samples collected from Jiangxi native chicken flocks. The results showed that ALV-J was the most predominant ALV subtype in Jiangxi native chickens, with a high positivity rate of 4.34%. From 2021 to 2023, there was a gradual upward trend in the proportion of positive numbers of ALV-K among ALV-positive samples, and there was a trend of outbreaks. ALV-J and ALV-K were the main co-infection patterns. Genetic evolutionary analysis based on ALV-K gp85 gene showed that the isolated ALV-K in this study were distributed in various branches of the evolutionary tree with genetic diversity. The homology results showed that the amino acid homology of the isolated ALV-K gp85 gene ranged from 33.9 to 88.1% with the reference strains of subtypes A, B, C, D, E, and J, and from 91.9 to 100% with the other ALV-K reference strains. Multiple mutations were present in the ALV-K gp85, and especially significant mutations were found in the highly variable region hr2. The results of ALV-K replication efficiency showed that the replication efficiency of ALV-K was significantly lower than that of ALV-J. These results enriched the genome sequence data of ALV-K in Chinese geoducks, and laid the foundation for further research on the pathogenesis and prevention of ALV-K.

[Advances in the coronavirus nonstructural protein 13].

Coronaviruses pose significant threats to animal and human health, leading to the development of various infectious diseases. It is critical to develop effective vaccines and antiviral medicines to prevent and treat these diseases. The coronavirus genome encodes several types of proteins, including structural, nonstructural, and accessory proteins. Among them, nonstructural protein 13 (NSP13) helicase plays a crucial role in regulating viral replication and the innate immune response of the host. Therefore, it serves as a vital target for the development of anti-coronavirus drugs. This paper presents a comprehensive review of NSP13 research, covering its source, structure, sequence conservation, unwinding mechanism, enzyme inhibitors, protein interaction, and immune regulation. Additionally, the paper analyzes the current challenges in NSP13 research and aims to provide a theoretical foundation for the development of broad-spectrum antiviral drugs targeting NSP13.

The effect of multimodal care based on Peplau's interpersonal relationship theory on postoperative recovery in lung cancer surgery: a retrospective analysis.

BACKGROUND: Lung cancer remains a major global health concern due to its high incidence and mortality rates. With advancements in medical treatments, an increasing number of early-stage lung cancer cases are being detected, making surgical treatment the primary option for such cases. However, this presents challenges to the physical and mental recovery of patients. Peplau known as the "mother of psychiatric associations" has formulated a theory of interpersonal relationships in nursing. Through effective communication between nurses and patients over four periods, she has established a good therapeutic nurse-patient relationship. Therefore, this study aimed to explore the effect of perioperative multimodal nursing based on Peplau's interpersonal relationship theory on the rehabilitation of patients with surgical lung cancer. METHODS: We retrospectively analyzed 106 patients with non-small cell lung cancer who underwent thoracoscopic lobectomy at our department between June 2021 and April 2022. Patients were categorized into two groups according to the different nursing intervention techniques. The Peplau's group comprised 53 patients who received targeted nursing interventions, and the control group comprised 53 patients who received conventional nursing care. We observed the patients' illness uncertainty, quality of life, and clinical symptoms in both groups. RESULTS: Patients in the Peplau's group had significantly lower illness uncertainty scores and a significantly higher quality of recovery than those in the control group. However, there were no significant differences in length of post-anesthesia care unit stay, complication rates, and visual analog scores between both groups. CONCLUSION: The multimodal perioperative nursing based on Peplau's interpersonal relationship theory not only reduces the illness uncertainty of patients with lung cancer surgery and improves their QoR but also expands the application of this theory in clinical practice, guiding perioperative nursing of patients with lung cancer. IMPLICATIONS: These findings provide practical information for standardized care in a hectic anesthetic care setting. IMPACT: The assessed anesthesia nursing model helps reduce uncertainty and promote early recovery in patients with cancer at various stages of their disease, which expands the scope of therapeutic practice and existing theories. It also serves as a guide for care in the anesthesia recovery room. REPORTING METHOD: We adhered to the relevant Equator guidelines and the checklist of items in the case-control study report. PATIENT OR PUBLIC CONTRIBUTION: Patients cooperated with medical staff to complete relevant scales.

Artificial intelligence approaches for molecular representation in drug response prediction.

Drug response prediction is essential for drug development and disease treatment. One key question in predicting drug response is the representation of molecules, which has been greatly advanced by artificial intelligence (AI) techniques in recent years. In this review, we first describe different types of representation methods, pinpointing their key principles and discussing their limitations. Thereafter we discuss potential ways how these methods could be further developed. We expect that this review will provide useful guidance for researchers in the community.

Promotion of uterine reconstruction by a tissue-engineered uterus with biomimetic structure and extracellular matrix microenvironment.

The recurrence rate for severe intrauterine adhesions is as high as 60%, and there is still lack of effective prevention and treatment. Inspired by the nature of uterus, we have developed a bilayer scaffold (ECM-SPS) with biomimetic heterogeneous features and extracellular matrix (ECM) microenvironment of the uterus. As proved by subtotal uterine reconstruction experiments, the mechanical and antiadhesion properties of the bilayer scaffold could meet the requirement for uterine repair. With the modification with tissue-specific cell-derived ECM, the ECM-SPS had the ECM microenvironment signatures of both the endometrium and myometrium and exhibited the property of inducing stem cell-directed differentiation. Furthermore, the ECM-SPS has recruited more endogenous stem cells to promote endometrial regeneration at the initial stage of repair, which was accompanied by more smooth muscle regeneration and a higher pregnancy rate. The reconstructed uterus could also sustain normal pregnancy and live birth. The ECM-SPS may thereby provide a potential treatment for women with severe intrauterine adhesions.

Knowledge, perceptions and behaviours of endoscopists towards the use of artificial intelligence-aided colonoscopy.

BACKGROUND: Recent developments in artificial intelligence (AI) systems have enabled advancements in endoscopy. Deep learning systems, using convolutional neural networks, have allowed for real-time AI-aided detection of polyps with higher sensitivity than the average endoscopist. However, not all endoscopists welcome the advent of AI systems. METHODS: We conducted a survey on the knowledge of AI, perceptions of AI in medicine, and behaviours regarding use of AI-aided colonoscopy, in a single centre 2 months after the implementation of Medtronic's GI Genius in colonoscopy. We obtained a response rate of 66.7% (16/24) amongst consultant-grade endoscopists. Fisher's exact test was used to calculate the significance of correlations. RESULTS: Knowledge of AI varied widely amongst endoscopists. Most endoscopists were optimistic about AI's capabilities in performing objective administrative and clinical tasks, but reserved about AI providing personalised, empathetic care. 68.8% (n = 11) of endoscopists agreed or strongly agreed that GI Genius should be used as an adjunct in colonoscopy. In analysing the 31.3% (n = 5) of endoscopists who disagreed or were ambivalent about its use, there was no significant correlation with their knowledge or perceptions of AI, but a significant number did not enjoy using the programme (p-value = 0.0128) and did not think it improved the quality of colonoscopy (p-value = 0.033). CONCLUSIONS: Acceptance of AI-aided colonoscopy systems is more related to the endoscopist's experience with using the programme, rather than general knowledge or perceptions towards AI. Uptake of such systems will rely greatly on how the device is delivered to the end user.

A newly proposed heatstroke-induced coagulopathy score in patients with heat illness: A multicenter retrospective study in China.

PURPOSE: In patients with heatstroke, disseminated intravascular coagulation (DIC) is associated with greater risk of in-hospital mortality. However, time-consuming assays or a complex diagnostic system may delay immediate treatment. Therefore, the present study proposes a new heatstroke-induced coagulopathy (HIC) score in patients with heat illness as an early warning indicator for DIC. METHODS: This retrospective study enrolled patients with heat illness in 24 Chinese hospitals from March 2021 to May 2022. Patients under 18 years old, with a congenital clotting disorder or liver disease, or using anticoagulants were excluded. Data were collected on demographic characteristics, routine blood tests, conventional coagulation assays and biochemical indexes. The risk factors related to coagulation function in heatstroke were identified by regression analysis, and used to construct a scoring system for HIC. The data of patients who met the diagnostic criteria for HIC and International Society on Thrombosis and Haemostasis defined-DIC were analyzed. All statistical analyses were performed using SPSS 26.0. RESULTS: The final analysis included 302 patients with heat illness, of whom 131 (43.4%) suffered from heatstroke, including 7 death (5.3%). Core temperature (OR = 1.681 (1.291 - 2.189), p < 0.001), prothrombin time (OR = 1.427 (1.175 - 1.733), p < 0.001) and D-dimer (OR = 1.242 (1.049 - 1.471), p = 0.012) were independent risk factors for heatstroke, and therefore used to construct an HIC scoring system because of their close relation with abnormal coagulation. A total score ≥ 3 indicated HIC, and HIC scores correlated with the score for International Society of Thrombosis and Hemostasis -DIC (r = 0.8848, p < 0.001). The incidence of HIC (27.5%) was higher than that of DIC (11.2%) in all of 131 heatstroke patients. Meanwhile, the mortality rate of HIC (19.4%) was lower than that of DIC (46.7%). When HIC developed into DIC, parameters of coagulation dysfunction changed significantly: platelet count decreased, D-dimer level rose, and prothrombin time and activated partial thromboplastin time prolonged (p < 0.05). CONCLUSIONS: The newly proposed HIC score may provide a valuable tool for early detection of HIC and prompt initiation of treatment.

Microglia in Alzheimer's disease: pathogenesis, mechanisms, and therapeutic potentials.

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by protein aggregation in the brain. Recent studies have revealed the critical role of microglia in AD pathogenesis. This review provides a comprehensive summary of the current understanding of microglial involvement in AD, focusing on genetic determinants, phenotypic state, phagocytic capacity, neuroinflammatory response, and impact on synaptic plasticity and neuronal regulation. Furthermore, recent developments in drug discovery targeting microglia in AD are reviewed, highlighting potential avenues for therapeutic intervention. This review emphasizes the essential role of microglia in AD and provides insights into potential treatments.

Correction: Zhang, N.; Lin, C. The Image Definition Assessment of Optoelectronic Tracking Equipment Based on the BRISQUE Algorithm with Gaussian Weights. Sensors 2023, 23, 1621.

There was an error in the original publication [...].

CellBRF: a feature selection method for single-cell clustering using cell balance and random forest.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) offers a powerful tool to dissect the complexity of biological tissues through cell sub-population identification in combination with clustering approaches. Feature selection is a critical step for improving the accuracy and interpretability of single-cell clustering. Existing feature selection methods underutilize the discriminatory potential of genes across distinct cell types. We hypothesize that incorporating such information could further boost the performance of single cell clustering. RESULTS: We develop CellBRF, a feature selection method that considers genes' relevance to cell types for single-cell clustering. The key idea is to identify genes that are most important for discriminating cell types through random forests guided by predicted cell labels. Moreover, it proposes a class balancing strategy to mitigate the impact of unbalanced cell type distributions on feature importance evaluation. We benchmark CellBRF on 33 scRNA-seq datasets representing diverse biological scenarios and demonstrate that it substantially outperforms state-of-the-art feature selection methods in terms of clustering accuracy and cell neighborhood consistency. Furthermore, we demonstrate the outstanding performance of our selected features through three case studies on cell differentiation stage identification, non-malignant cell subtype identification, and rare cell identification. CellBRF provides a new and effective tool to boost single-cell clustering accuracy. AVAILABILITY AND IMPLEMENTATION: All source codes of CellBRF are freely available at https://github.com/xuyp-csu/CellBRF.

Computational approaches for detecting disease-associated alternative splicing events.

Alternative splicing (AS) is a key transcriptional regulation pathway. Recent studies have shown that AS events are associated with the occurrence of complex diseases. Various computational approaches have been developed for the detection of disease-associated AS events. In this review, we first describe the metrics used for quantitative characterization of AS events. Second, we review and discuss the three types of methods for detecting disease-associated splicing events, which are differential splicing analysis, aberrant splicing detection and splicing-related network analysis. Third, to further exploit the genetic mechanism of disease-associated AS events, we describe the methods for detecting genetic variants that potentially regulate splicing. For each type of methods, we conducted experimental comparison to illustrate their performance. Finally, we discuss the limitations of these methods and point out potential ways to address them. We anticipate that this review provides a systematic understanding of computational approaches for the analysis of disease-associated splicing.

The imitation game: a review of the use of artificial intelligence in colonoscopy, and endoscopists' perceptions thereof.

The development of deep learning systems in artificial intelligence (AI) has enabled advances in endoscopy, and AI-aided colonoscopy has recently been ushered into clinical practice as a clinical decision-support tool. This has enabled real-time AI-aided detection of polyps with a higher sensitivity than the average endoscopist, and evidence to support its use has been promising thus far. This review article provides a summary of currently published data relating to AI-aided colonoscopy, discusses current clinical applications, and introduces ongoing research directions. We also explore endoscopists' perceptions and attitudes toward the use of this technology, and discuss factors influencing its uptake in clinical practice.

One-year review of real-time artificial intelligence (AI)-aided endoscopy performance.

BACKGROUND: Colonoscopies have long been the gold standard for detection of pre-malignant neoplastic lesions of the colon. Our previous study tried real-time artificial intelligence (AI)-aided colonoscopy over a three-month period and found significant improvements in collective and individual endoscopist's adenoma detection rates compared to baseline. As an expansion, this study evaluates the 1-year performance of AI-aided colonoscopy in the same institution. METHODS: A prospective cohort study was conducted in a single institution in Singapore. The AI software used was GI Genius™ Intelligent Endoscopy Module, US-DG-2000309 © 2021 Medtronic. Between July 2021 and June 2022, polypectomy rates in non-AI-aided colonoscopies and AI-aided colonoscopies were calculated and compared. Some of the AI-aided colonoscopies were recorded and video reviewed. A "hit" was defined as a sustained detection of an area by the AI. If a polypectomy was performed for a "hit," its histology was reviewed. Additional calculations for polyp detection rate (PDR), adenoma detection rate (ADR), and adenoma detection per colonoscopy (ADPC) were performed. Cost analysis was performed to determine cost effectiveness of subscription to the AI program. RESULTS: 2433 AI-aided colonoscopies were performed between July 2021 and June 2022 and compared against 1770 non-AI-aided colonoscopies. AI-aided colonoscopies yielded significantly higher rates of polypectomies (33.6%) as compared with non-AI-aided colonoscopies (28.4%) (p < 0.001). Among the AI-aided colonoscopies, 1050 were reviewed and a final 843 were included for additional analysis. The polypectomy to "hit" ratio was 57.4%, PDR = 45.6%, ADR = 32.4%, and ADPC = 2.08. Histological review showed that 25 polyps (3.13%) were sessile-serrated adenomas. Cost analysis found that the increased polypectomy rates in AI-aided colonoscopes led to an increase in revenue, which covered the subscription cost with an excess of USD 20,000. CONCLUSION: AI-aided colonoscopy is a cost effective means of improving colonoscopy quality and may help advance colorectal cancer screening in Singapore.

The Image Definition Assessment of Optoelectronic Tracking Equipment Based on the BRISQUE Algorithm with Gaussian Weights.

Defocus is an important factor that causes image quality degradation of optoelectronic tracking equipment in the shooting range. In this paper, an improved blind/referenceless image spatial quality evaluator (BRISQUE) algorithm is formulated by using the image characteristic extraction technology to obtain a characteristic vector (CV). The CV consists of 36 characteristic values that can effectively reflect the defocusing condition of the corresponding image. The image is evaluated and scored subjectively by the human eyes. The subjective evaluation scores and CVs constitute a set of training data samples for the defocusing evaluation model. An image database that contains sufficiently many training samples is constructed. The training model is trained to obtain the support vector machine (SVM) model by using the regression function of the SVM. In the experiments, the BRISQUE algorithm is used to obtain the image feature vector. The method of establishing the image definition evaluation model via SVM is feasible and yields higher subjective and objective consistency.

Results from a systematic programme of evaluating COVID-19 reinfection cases in the early phase of the pandemic, Singapore.

OBJECTIVES: The objectives of this study were to describe the coronavirus disease caused by SARS-CoV-2 (COVID-19) reinfection evaluation algorithm used in the early phase of the pandemic in Singapore and analyze the clinical and laboratory characteristics of the cases evaluated. METHODS: We performed a retrospective case-control analysis including all COVID-19 cases evaluated for possible reinfection under the local COVID-19 reinfection evaluation programme between 1 June 2020-30 June 2021. Whole genome sequencing (WGS) was used as confirmatory testing. We compared all reinfection ("RI") cases against those who were evaluated but eventually assessed not to be reinfection ("non-RI"). RESULTS: There were 74 possible reinfection cases evaluated through the programme, of which 32 were subsequently classified as RI. There was strong statistical evidence that RI cases had a longer interval between 1st and 2nd episode (mean 297 days; 95%-confidence interval (CI) 267-327) compared to non-RI cases (mean 186 days; 95%-CI 144-228). The cycle threshold (Ct) value of initial polymerase chain rection (PCR) at 2nd episode was also found to be significantly lower in RI cases (mean 23; 95%-CI 20-26) compared to non-RI cases (mean 34; 95%-CI 32-36). There was no significant difference in the proportion of individuals who had fever, acute respiratory symptoms or asymptomatic in both groups. Delta and beta variants were most commonly identified from WGS and provide indication of re-infection as these were not 'wild-type' and were not circulating during the time period of the index infection. CONCLUSIONS: Using a combination of serologic, microbiologic and genomic criteria to evaluate possible reinfection cases is useful and can provide a framework for evaluation that may be modified for future similar situations.

Real-time artificial intelligence (AI)-aided endoscopy improves adenoma detection rates even in experienced endoscopists: a cohort study in Singapore.

BACKGROUND: Colonoscopy is a mainstay to detect premalignant neoplastic lesions in the colon. Real-time Artificial Intelligence (AI)-aided colonoscopy purportedly improves the polyp detection rate, especially for small flat lesions. The aim of this study is to evaluate the performance of real-time AI-aided colonoscopy in the detection of colonic polyps. METHODS: A prospective single institution cohort study was conducted in Singapore. All real-time AI-aided colonoscopies, regardless of indication, performed by specialist-grade endoscopists were anonymously recorded from July to September 2021 and reviewed by 2 independent authors (FHK, JL). Sustained detection of an area by the program was regarded as a "hit". Histology for the polypectomies were reviewed to determine adenoma detection rate (ADR). Individual endoscopist's performance with AI were compared against their baseline performance without AI endoscopy. RESULTS: A total of 24 (82.8%) endoscopists participated with 18 (62.1%) performing ≥ 5 AI-aided colonoscopies. Of the 18, 72.2% (n = 13) were general surgeons. During that 3-months period, 487 "hits" encountered in 298 colonoscopies. Polypectomies were performed for 51.3% and 68.4% of these polypectomies were adenomas on histology. The post-intervention median ADR was 30.4% was higher than the median baseline polypectomy rate of 24.3% (p = 0.02). Of the adenomas excised, 14 (5.6%) were sessile serrated adenomas. Of those who performed ≥ 5 AI-aided colonoscopies, 13 (72.2%) had an improvement of ADR compared to their polypectomy rate before the introduction of AI, of which 2 of them had significant improvement. CONCLUSIONS: Real-time AI-aided colonoscopy have the potential to improved ADR even for experienced endoscopists and would therefore, improve the quality of colonoscopy.