Bright Bifacial White-Light Illumination by Highly Deformable Electroluminescent Devices Based on Transparent Ionic-Hydrogel Electrodes and Quantum-Dot Color Conversion.

Deformable alternating-current electroluminescent (ACEL) devices are of increasing interest because of their potential to drive innovation in soft optoelectronics. Despite the research focus on efficient white ACEL devices, achieving deformable devices with high luminance remains difficult. In this study, this challenge is addressed by fabricating white ACEL devices using color-conversion materials, transparent and durable hydrogel electrodes, and high-k nanoparticles. The incorporation of quantum dots enables the highly efficient generation of red and green light through the color conversion of blue electroluminescence. Although the ionic-hydrogel electrode provides high toughness, excellent light transmittance, and superior conductivity, the luminance of the device is remarkably enhanced by the incorporation of a high-k dielectric, BaTiO3. The fabricated ACEL device uniformly emits very bright white light (489 cd m-2) with a high color-rendering index (91) from both the top and bottom. The soft and tough characteristics of the device allow seamless operation in various deformed states, including bending, twisting, and stretching up to 400%, providing a promising platform for applications in a wide array of soft optoelectronics.

A crossover study to evaluate the pharmacokinetics and bioequivalence of hydroxychloroquine tablets in healthy Chinese subjects.

AIMS: Hydroxychloroquine (HCQ) has a high variability and a long half-life in the human body. The purpose of this study was to evaluate the bioequivalence of a generic HCQ tablet (test preparation) versus a brand HCQ tablet (reference preparation) under fasting and fed conditions in a crossover design. MATERIALS AND METHODS: This was an open-label, two-period randomized, single-dose, crossover study in 47 healthy Chinese subjects who were sequentially and randomly allocated either to the fed group (high-fat meal; n = 23) or the fasting group (n = 24). Participants in each group were randomized to the two arms to receive either a single 200-mg dose of the test preparation or a 200-mg dose of the reference preparation. The application of the two preparations in each patient was separated by a 28-day washout period, regarded as sufficiently long to avoid significant interference from residual drug in the body. Whole blood samples were collected over 72 hours after drug administration. RESULTS: A total of 23 subjects completed both the fed and the fasting parts of the trial. There were no significant differences in Cmax, AUC0-72h, and T1/2 between the test and reference preparation (p > 0.05). Food had no significant effect on Cmax and T1/2 (p > 0.05), but AUC0-72h values were significantly reduced under fed condition compared to fasting condition (p < 0.05). The 90% confidence intervals (CIs) for the geometric mean ratios (GMRs) of Cmax and AUC0-72h were 0.84 - 1.05 and 0.89 - 0.98 in the fed study, and 0.97 - 1.07 and 0.97 - 1.05 in the fasting study, respectively. The carryover effect due to non-zero blood concentrations resulted in higher AUC0-72h values in the second period for both test and reference formulations and had no effect on the statistical results. No serious adverse events were reported. CONCLUSION: The investigation demonstrated that the test and reference preparations are bioequivalent and well tolerated under both fasting and fed conditions in healthy Chinese subjects.

The effect of incorporating domain knowledge with deep learning in identifying benign and malignant gastric whitish lesions: A retrospective study.

BACKGROUND AND AIM: Early whitish gastric neoplasms can be easily misdiagnosed; differential diagnosis of gastric whitish lesions remains a challenge. We aim to build a deep learning (DL) model to diagnose whitish gastric neoplasms and explore the effect of adding domain knowledge in model construction. METHODS: We collected 4558 images from two institutions to train and test models. We first developed two sole DL models (1 and 2) using supervised and semi-supervised algorithms. Then we selected diagnosis-related features through literature research and developed feature-extraction models to determine features including boundary, surface, roundness, depression, and location. Then predictions of the five feature-extraction models and sole DL model were combined and inputted into seven machine-learning (ML) based fitting-diagnosis models. The optimal model was selected as ENDOANGEL-WD (whitish-diagnosis) and compared with endoscopists. RESULTS: Sole DL 2 had higher sensitivity (83.12% vs 68.67%, Bonferroni adjusted P = 0.024) than sole DL 1. Adding domain knowledge, the decision tree performed best among the seven ML models, achieving higher specificity than DL 1 (84.38% vs 72.27%, Bonferroni adjusted P < 0.05) and higher accuracy than DL 2 (80.47%, Bonferroni adjusted P < 0.001) and was selected as ENDOANGEL-WD. ENDOANGEL-WD showed better accuracy compared with 10 endoscopists (75.70%, P < 0.001). CONCLUSIONS: We developed a novel system ENDOANGEL-WD combining domain knowledge and traditional DL to detect gastric whitish neoplasms. Adding domain knowledge improved the performance of traditional DL, which provided a novel solution for establishing diagnostic models for other rare diseases potentially.

A newly developed deep learning-based system for automatic detection and classification of small bowel lesions during double-balloon enteroscopy examination.

BACKGROUND: Double-balloon enteroscopy (DBE) is a standard method for diagnosing and treating small bowel disease. However, DBE may yield false-negative results due to oversight or inexperience. We aim to develop a computer-aided diagnostic (CAD) system for the automatic detection and classification of small bowel abnormalities in DBE. DESIGN AND METHODS: A total of 5201 images were collected from Renmin Hospital of Wuhan University to construct a detection model for localizing lesions during DBE, and 3021 images were collected to construct a classification model for classifying lesions into four classes, protruding lesion, diverticulum, erosion & ulcer and angioectasia. The performance of the two models was evaluated using 1318 normal images and 915 abnormal images and 65 videos from independent patients and then compared with that of 8 endoscopists. The standard answer was the expert consensus. RESULTS: For the image test set, the detection model achieved a sensitivity of 92% (843/915) and an area under the curve (AUC) of 0.947, and the classification model achieved an accuracy of 86%. For the video test set, the accuracy of the system was significantly better than that of the endoscopists (85% vs. 77 ± 6%, p < 0.01). For the video test set, the proposed system was superior to novices and comparable to experts. CONCLUSIONS: We established a real-time CAD system for detecting and classifying small bowel lesions in DBE with favourable performance. ENDOANGEL-DBE has the potential to help endoscopists, especially novices, in clinical practice and may reduce the miss rate of small bowel lesions.

An artificial intelligence system for chronic atrophic gastritis diagnosis and risk stratification under white light endoscopy.

BACKGROUND AND AIMS: The diagnosis and stratification of gastric atrophy (GA) predict patients' gastric cancer progression risk and determine endoscopy surveillance interval. We aimed to construct an artificial intelligence (AI) system for GA endoscopic identification and risk stratification based on the Kimura-Takemoto classification. METHODS: We constructed the system using two trained models and verified its performance. First, we retrospectively collected 869 images and 119 videos to compare its performance with that of endoscopists in identifying GA. Then, we included original image cases of 102 patients to validate the system for stratifying GA and comparing it with endoscopists with different experiences. RESULTS: The sensitivity of model 1 was higher than that of endoscopists (92.72% vs. 76.85 %) at image level and also higher than that of experts (94.87% vs. 85.90 %) at video level. The system outperformed experts in stratifying GA (overall accuracy: 81.37 %, 73.04 %, p = 0.045). The accuracy of this system in classifying non-GA, mild GA, moderate GA, and severe GA was 80.00 %, 77.42 %, 83.33 %, and 85.71 %, comparable to that of experts and better than that of seniors and novices. CONCLUSIONS: We established an expert-level system for GA endoscopic identification and risk stratification. It has great potential for endoscopic assessment and surveillance determinations.

The effect of metformin on urate metabolism: Findings from observational and Mendelian randomization analyses.

AIM: To evaluate the effect of metformin on urate metabolism. MATERIALS AND METHODS: Using the UK Biobank, we first performed association analyses of metformin use with urate levels, risk of hyperuricaemia and incident gout in patients with diabetes. To explore the causal effect of metformin on urate and gout, we identified genetic variants proxying the glycated haemoglobin (HbA1c)-lowering effect of metformin targets and conducted a two-sample Mendelian randomization (MR) utilizing the urate and gout genetic summary-level data from the CKDGen (n = 288 649) and the FinnGen cohort. We conducted two-step MR to explore the mediation effect of body mass index and systolic blood pressure. We also performed non-linear MR in the UK Biobank (n = 414 055) to show the results across HbA1c levels. RESULTS: In 18 776 patients with type 2 diabetes in UK Biobank, metformin use was associated with decreased urate [ß = -4.3 µmol/L, 95% confidence interval (CI) -7.0, -1.7, p = .001] and reduced hyperuricaemia risk (odds ratio = 0.87, 95% CI 0.79, 0.96, p = .004), but not gout. Genetically proxied averaged HbA1c-lowering effects of metformin targets, equivalent to a 0.62% reduction in HbA1c, was associated with reduced urate (ß = -12.5 µmol/L, 95% CI -21.4, -4.2, p = .004). Body mass index significantly mediated this association (proportion mediated = 33.0%, p = .002). Non-linear MR results suggest a linear trend of the effect of metformin on urate reduction across various HbA1c levels. CONCLUSIONS: The effect of metformin may reduce urate levels but not incident gout in the general population.

Sex-specific causality of MRI-derived body compositions on glycaemic traits: Mendelian randomization and observational study.

AIM: To investigate the sex-specific causality of body compositions in type 2 diabetes and related glycaemic traits using Mendelian randomization (MR). MATERIALS AND METHODS: We leveraged sex-specific summary-level statistics from genome-wide association studies for three adipose deposits adjusted for body mass index and height, including abdominal subcutaneous adipose tissue, visceral adipose tissue (VATadj) and gluteofemoral adipose tissue (GFATadj), measured by MRI (20 038 women; 19 038 men), and fat mass-adjusted appendicular lean mass (ALMadj) (244 730 women; 205 513 men) in the UK Biobank. Sex-specific statistics of type 2 diabetes were from the Diabetes Genetics Replication and Meta-analysis Consortium and those for fasting glucose and insulin were from the Meta-analyses of Glucose and Insulin-related Traits Consortium. Univariable and multivariable MR (MVMR) were performed. We also performed MR analyses of anthropometric traits and genetic association analyses using individual-level data of body composition as validation. RESULTS: Univariable MR analysis showed that, in women, higher GFATadj and ALMadj exerted a causally protective effect on type 2 diabetes (GFATadj: odds ratio [OR] 0.59, 95% confidence interval [CI; 0.50, 0.69]; ALMadj: OR 0.84, 95% CI [0.77, 0.91]) and VATadj to be riskier in glycaemic traits. MVMR showed that GFATadj retained a robust effect on type 2 diabetes (OR 0.57, 95% CI [0.42, 0.77]; P = 2.6 × 10-4 ) in women, while it was nominally significant in men (OR 0.58, 95% CI [0.35, 0.96]; P = 3.3 × 10-2 ), after adjustment for ASATadj and VATadj. MR analyses of anthropometric measures and genetic association analyses of glycaemic traits confirmed the results. CONCLUSIONS: Body composition has a sex-specific effect on type 2 diabetes, and higher GFATadj has an independent protective effect on type 2 diabetes in both sexes.

Roles of gut microbiota in atrial fibrillation: insights from Mendelian randomization analysis and genetic data from over 430,000 cohort study participants.

BACKGROUND: Gut microbiota imbalances have been suggested as a contributing factor to atrial fibrillation (AF), but the causal relationship is not fully understood. OBJECTIVES: To explore the causal relationships between the gut microbiota and AF using Mendelian randomization (MR) analysis. METHODS: Summary statistics were from genome-wide association studies (GWAS) of 207 gut microbial taxa (5 phyla, 10 classes, 13 orders, 26 families, 48 genera, and 105 species) (the Dutch Microbiome Project) and two large meta-GWASs of AF. The significant results were validated in FinnGen cohort and over 430,000 UK Biobank participants. Mediation MR analyses were conducted for AF risk factors, including type 2 diabetes, coronary artery disease (CAD), body mass index (BMI), blood lipids, blood pressure, and obstructive sleep apnea, to explore the potential mediation effect of these risk factors in between the gut microbiota and AF. RESULTS: Two microbial taxa causally associated with AF: species Eubacterium ramulus (odds ratio [OR] 1.08, 95% confidence interval [CI] 1.04-1.12, P = 0.0001, false discovery rate (FDR) adjusted p-value = 0.023) and genus Holdemania (OR 1.15, 95% CI 1.07-1.25, P = 0.0004, FDR adjusted p-value = 0.042). Genus Holdemania was associated with incident AF risk in the UK Biobank. The proportion of mediation effect of species Eubacterium ramulus via CAD was 8.05% (95% CI 1.73% - 14.95%, P = 0.008), while the proportion of genus Holdemania on AF via BMI was 12.01% (95% CI 5.17% - 19.39%, P = 0.0005). CONCLUSIONS: This study provided genetic evidence to support a potential causal mechanism between gut microbiota and AF and suggested the mediation role of AF risk factors.

Development and Evaluation of a Surveillance System for Follow-Up After Colorectal Polypectomy.

Importance: The adherence of physicians and patients to published colorectal postpolypectomy surveillance guidelines varies greatly, and patient follow-up is critical but time consuming. Objectives: To evaluate the accuracy of an automatic surveillance (AS) system in identifying patients after polypectomy, assigning surveillance intervals for different risks of patients, and proactively following up with patients on time. Design, Setting, and Participants: In this diagnostic/prognostic study, endoscopic and pathological reports of 47 544 patients undergoing colonoscopy at 3 hospitals between January 1, 2017, and June 30, 2022, were collected to develop an AS system based on natural language processing. The performance of the AS system was fully evaluated in internal and external tests according to 5 guidelines worldwide and compared with that of physicians. A multireader, multicase (MRMC) trial was conducted to evaluate use of the AS system and physician guideline adherence, and prospective data were collected to evaluate the success rate in contacting patients and the association with reduced human workload. Data analysis was conducted from July to September 2022. Exposures: Assistance of the AS system. Main Outcomes and Measures: The accuracy of the system in identifying patients after polypectomy, stratifying patient risk levels, and assigning surveillance intervals in internal (Renmin Hospital of Wuhan University), external 1 (Wenzhou Central Hospital), and external 2 (The First People's Hospital of Yichang) test sets; the accuracy of physicians and their time burden with and without system assistance; and the rate of successfully informed patients of the system were evaluated. Results: Test sets for 16 106 patients undergoing colonoscopy (mean [SD] age, 51.90 [13.40] years; 7690 females [47.75%]) were evaluated. In internal, external 1, and external 2 test sets, the system had an overall accuracy of 99.91% (95% CI, 99.83%-99.95%), 99.54% (95% CI, 99.30%-99.70%), and 99.77% (95% CI, 99.41%-99.91%), respectively, for identifying types of patients and achieved an overall accuracy of at least 99.30% (95% CI, 98.67%-99.63%) in the internal test set, 98.89% (95% CI, 98.33%-99.27%) in external test set 1, and 98.56% (95% CI, 95.86%-99.51%) in external test set 2 for stratifying patient risk levels and assigning surveillance intervals according to 5 guidelines. The system was associated with increased mean (SD) accuracy among physicians vs no AS system in 105 patients (98.67% [1.28%] vs 78.10% [18.01%]; P = .04) in the MRMC trial. In a prospective trial, the AS system successfully informed 82 of 88 patients (93.18%) and was associated with reduced burden of follow-up time vs no AS system (0 vs 2.86 h). Conclusions and Relevance: This study found that an AS system was associated with improved adherence to guidelines among physicians and reduced workload among physicians and nurses.

Exploring the challenge of early gastric cancer diagnostic AI system face in multiple centers and its potential solutions.

BACKGROUND: Artificial intelligence (AI) performed variously among test sets with different diversity due to sample selection bias, which can be stumbling block for AI applications. We previously tested AI named ENDOANGEL, diagnosing early gastric cancer (EGC) on single-center videos in man-machine competition. We aimed to re-test ENDOANGEL on multi-center videos to explore challenges applying AI in multiple centers, then upgrade ENDOANGEL and explore solutions to the challenge. METHODS: ENDOANGEL was re-tested on multi-center videos retrospectively collected from 12 institutions and compared with performance in previously reported single-center videos. We then upgraded ENDOANGEL to ENDOANGEL-2022 with more training samples and novel algorithms and conducted competition between ENDOANGEL-2022 and endoscopists. ENDOANGEL-2022 was then tested on single-center videos and compared with performance in multi-center videos; the two AI systems were also compared with each other and endoscopists. RESULTS: Forty-six EGCs and 54 non-cancers were included in multi-center video cohort. On diagnosing EGCs, compared with single-center videos, ENDOANGEL showed stable sensitivity (97.83% vs. 100.00%) while sharply decreased specificity (61.11% vs. 82.54%); ENDOANGEL-2022 showed similar tendency while achieving significantly higher specificity (79.63%, p < 0.01) making fewer mistakes on typical lesions than ENDOANGEL. On detecting gastric neoplasms, both AI showed stable sensitivity while sharply decreased specificity. Nevertheless, both AI outperformed endoscopists in the two competitions. CONCLUSIONS: Great increase of false positives is a prominent challenge for applying EGC diagnostic AI in multiple centers due to high heterogeneity of negative cases. Optimizing AI by adding samples and using novel algorithms is promising to overcome this challenge.

Evaluation of the Effect of Sodium-Glucose Cotransporter 2 Inhibition on Fracture Risk: Evidence From Mendelian Randomization and Genetic Association Study.

This study aims to evaluate the causal effect of sodium-glucose cotransporter 2 (SGLT2) inhibition on bone mineral density (BMD), osteoporosis, and fracture risk using genetics. Two-sample Mendelian randomization (MR) analyses were performed utilizing two sets of genetic variants as instruments (six and two single-nucleotide polymorphisms [SNPs]) associated with SLC5A2 gene expression and glycated hemoglobin A1c levels. Summary statistics of BMD from the Genetic Factors for Osteoporosis consortium (BMD for total body, n = 66,628; femoral neck, n = 32,735; lumbar spine, n = 28,498; forearm, n = 8143) and osteoporosis (6303 cases, 325,717 controls) and 13 types of fracture (≤17,690 cases, ≤328,382 controls) data from the FinnGen study were obtained. One-sample MR and genetic association analyses were conducted in UK Biobank using the individual-level data of heel BMD (n = 256,286) and incident osteoporosis (13,677 cases, 430,262 controls) and fracture (25,806 cases, 407,081 controls). Using six SNPs as the instrument, genetically proxied SGLT2 inhibition showed little evidence of association with BMD of total body, femoral neck, lumbar spine, and forearm (all p ≥ 0.077). Similar results were observed using two SNPs as instruments. Little evidence was found for the SGLT2 inhibition effect on osteoporosis (all p ≥ 0.112) or any 11 major types of fracture (all p ≥ 0.094), except for a nominal significance for fracture of lower leg (p = 0.049) and shoulder and upper arm (p = 0.029). One-sample MR and genetic association analysis showed that both the weighted genetic risk scores constructed from the six and two SNPs were not causally associated with heel BMD, osteoporosis, and fracture (all p ≥ 0.387). Therefore, this study does not support an effect of genetically proxied SGLT2 inhibition on fracture risk. © 2023 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).

The effectiveness of a computer-aided system in improving the detection rate of gastric neoplasm and early gastric cancer: study protocol for a multi-centre, randomized controlled trial.

BACKGROUND: This protocol is for a multi-centre randomised controlled trial to determine whether the computer-aided system ENDOANGEL-GC improves the detection rates of gastric neoplasms and early gastric cancer (EGC) in routine oesophagogastroduodenoscopy (EGD). METHODS: Study design: Prospective, single-blind, parallel-group, multi-centre randomised controlled trial. SETTINGS: The computer-aided system ENDOANGEL-GC was used to monitor blind spots, detect gastric abnormalities, and identify gastric neoplasms during EGD. PARTICIPANTS: Adults who underwent screening, diagnosis, or surveillance EGD. Randomisation groups: 1. Experiment group, EGD examinations with the assistance of the ENDOANGEL-GC; 2. Control group, EGD examinations without the assistance of the ENDOANGEL-GC. RANDOMISATION: Block randomisation, stratified by centre. PRIMARY OUTCOMES: Detection rates of gastric neoplasms and EGC. SECONDARY OUTCOMES: Detection rate of premalignant gastric lesions, biopsy rate, observation time, and number of blind spots on EGD. BLINDING: Outcomes are undertaken by blinded assessors. SAMPLE SIZE: Based on the previously published findings and our pilot study, the detection rate of gastric neoplasms in the control group is estimated to be 2.5%, and that of the experimental group is expected to be 4.0%. With a two-sided α level of 0.05 and power of 80%, allowing for a 10% drop-out rate, the sample size is calculated as 4858. The detection rate of EGC in the control group is estimated to be 20%, and that of the experiment group is expected to be 35%. With a two-sided α level of 0.05 and power of 80%, a total of 270 cases of gastric cancer are needed. Assuming the proportion of gastric cancer to be 1% in patients undergoing EGD and allowing for a 10% dropout rate, the sample size is calculated as 30,000. Considering the larger sample size calculated from the two primary endpoints, the required sample size is determined to be 30,000. DISCUSSION: The results of this trial will help determine the effectiveness of the ENDOANGEL-GC in clinical settings. TRIAL REGISTRATION: ChiCTR (Chinese Clinical Trial Registry), ChiCTR2100054449, registered 17 December 2021.

A metal-organic framework-supported dinuclear iron catalyst for hydroboration of carbonyl compounds.

Preparation of catalytically active dinuclear transition metal complexes with an open coordination sphere is a challenging task because the metal sites tend to be "saturated" with excess donor atoms around during synthesis. By isolating the binding scaffolds with the metal-organic framework (MOF) skeleton and installing metal sites through post-synthetic modification, we succeed in constructing a MOF-supported metal catalyst, namely FICN-7-Fe2, with dinuclear Fe2 sites. FICN-7-Fe2 effectively catalyses the hydroboration of a broad range of ketone, aldehyde, and imine substrates with a low loading of 0.05 mol%. Remarkably, kinetic measurements showed that FICN-7-Fe2 is 15 times more active than its mononuclear counterpart FICN-7-Fe1, indicating that cooperative substrate activation on the two Fe centres significantly enhances the catalysis.

Explainable artificial intelligence incorporated with domain knowledge diagnosing early gastric neoplasms under white light endoscopy.

White light endoscopy is the most pivotal tool for detecting early gastric neoplasms. Previous artificial intelligence (AI) systems were primarily unexplainable, affecting their clinical credibility and acceptability. We aimed to develop an explainable AI named ENDOANGEL-ED (explainable diagnosis) to solve this problem. A total of 4482 images and 296 videos with focal lesions from 3279 patients from eight hospitals were used for training, validating, and testing ENDOANGEL-ED. A traditional sole deep learning (DL) model was trained using the same dataset. The performance of ENDOANGEL-ED and sole DL was evaluated on six levels: internal and external images, internal and external videos, consecutive videos, and man-machine comparison with 77 endoscopists in videos. Furthermore, a multi-reader, multi-case study was conducted to evaluate the ENDOANGEL-ED's effectiveness. A scale was used to compare the overall acceptance of endoscopists to traditional and explainable AI systems. The ENDOANGEL-ED showed high performance in the image and video tests. In man-machine comparison, the accuracy of ENDOANGEL-ED was significantly higher than that of all endoscopists in internal (81.10% vs. 70.61%, p < 0.001) and external videos (88.24% vs. 78.49%, p < 0.001). With ENDOANGEL-ED's assistance, the accuracy of endoscopists significantly improved (70.61% vs. 79.63%, p < 0.001). Compared with the traditional AI, the explainable AI increased the endoscopists' trust and acceptance (4.42 vs. 3.74, p < 0.001; 4.52 vs. 4.00, p < 0.001). In conclusion, we developed a real-time explainable AI that showed high performance, higher clinical credibility, and acceptance than traditional DL models and greatly improved the diagnostic ability of endoscopists.

An explainable artificial intelligence system for diagnosing Helicobacter Pylori infection under endoscopy: a case-control study.

Background: Changes in gastric mucosa caused by Helicobacter pylori (H. pylori) infection affect the observation of early gastric cancer under endoscopy. Although previous researches reported that computer-aided diagnosis (CAD) systems have great potential in the diagnosis of H. pylori infection, their explainability remains a challenge. Objective: We aim to develop an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) and giving diagnostic basis under endoscopy. Design: A case-control study. Methods: We retrospectively obtained 47,239 images from 1826 patients between 1 June 2020 and 31 July 2021 at Renmin Hospital of Wuhan University for the development of EADHI. EADHI was developed based on feature extraction combining ResNet-50 and long short-term memory networks. Nine endoscopic features were used for H. pylori infection. EADHI's performance was evaluated and compared to that of endoscopists. An external test was conducted in Wenzhou Central Hospital to evaluate its robustness. A gradient-boosting decision tree model was used to examine the contributions of different mucosal features for diagnosing H. pylori infection. Results: The system extracted mucosal features for diagnosing H. pylori infection with an overall accuracy of 78.3% [95% confidence interval (CI): 76.2-80.3]. The accuracy of EADHI for diagnosing H. pylori infection (91.1%, 95% CI: 85.7-94.6) was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3) in internal test. And it showed a good accuracy of 91.9% (95% CI: 85.6-95.7) in external test. Mucosal edema was the most important diagnostic feature for H. pylori positive, while regular arrangement of collecting venules was the most important H. pylori negative feature. Conclusion: The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs. Plain language summary: An explainable AI system for Helicobacter pylori with good diagnostic performance Helicobacter pylori (H. pylori) is the main risk factor for gastric cancer (GC), and changes in gastric mucosa caused by H. pylori infection affect the observation of early GC under endoscopy. Therefore, it is necessary to identify H. pylori infection under endoscopy. Although previous research showed that computer-aided diagnosis (CAD) systems have great potential in H. pylori infection diagnosis, their generalization and explainability are still a challenge. Herein, we constructed an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) using images by case. In this study, we integrated ResNet-50 and long short-term memory (LSTM) networks into the system. Among them, ResNet50 is used for feature extraction, LSTM is used to classify H. pylori infection status based on these features. Furthermore, we added the information of mucosal features in each case when training the system so that EADHI could identify and output which mucosal features are contained in a case. In our study, EADHI achieved good diagnostic performance with an accuracy of 91.1% [95% confidence interval (CI): 85.7-94.6], which was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3%) in internal test. In addition, it showed a good diagnostic accuracy of 91.9% (95% CI: 85.6-95.7) in external tests. The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs. However, we only used data from a single center to develop EADHI, and it was not effective in identifying past H. pylori infection. Future, multicenter, prospective studies are needed to demonstrate the clinical applicability of CADs.

Association between age at diabetes onset or diabetes duration and subsequent risk of pancreatic cancer: Results from a longitudinal cohort and mendelian randomization study.

Background: The aim of the study is to estimate the incidence of pancreatic cancer among individuals with new-onset type 2 Diabetes (T2DM) and evaluate the relationship of pancreatic cancer risk with age at diabetes onset and diabetes duration. Methods: This longitudinal cohort study included 428,362 new-onset T2DM patients in Shanghai and Mendelian randomization (MR) in the east-Asian population were used to investigate the association. Incidence rates of pancreatic cancer in all patients and by subgroups were calculated and compared to the general population. Findings: A total of 1056 incident pancreatic cancer cases were identified during eight consecutive years of follow-up. The overall pancreatic cancer annual incidence rate was 55·28/100,000 person years in T2DM patients, higher than that in the general population, with a standardized incidence ratio (SIR) of 1·54 (95% confidence interval [CI], 1·45-1·64). The incidence of pancreatic cancer increased with age and a significantly higher incidence was observed in the older groups with T2DM. However, the relative pancreatic cancer risk was inversely related to age of T2DM onset, and a higher SIR of 5·73 (95%CI, 4·49-7·22) was observed in the 20-54 years old group. The risk of pancreatic cancer was elevated at any diabetes duration. Fasting blood glucose ≥10·0 mmol/L was associated with increased risk of pancreatic cancer. MR analysis indicated a positive association between T2DM and pancreatic cancer risk. Interpretation: Efforts toward early and close follow-up programs, especially in individuals with young-onset T2DM, and the improvement of glucose control might represent effective strategies for improving the detection and results of treatment of pancreatic cancer. Funding: Chinese National Natural Science Foundation.

A deep-learning based system using multi-modal data for diagnosing gastric neoplasms in real-time (with video).

BACKGROUND: White light (WL) and weak-magnifying (WM) endoscopy are both important methods for diagnosing gastric neoplasms. This study constructed a deep-learning system named ENDOANGEL-MM (multi-modal) aimed at real-time diagnosing gastric neoplasms using WL and WM data. METHODS: WL and WM images of a same lesion were combined into image-pairs. A total of 4201 images, 7436 image-pairs, and 162 videos were used for model construction and validation. Models 1-5 including two single-modal models (WL, WM) and three multi-modal models (data fusion on task-level, feature-level, and input-level) were constructed. The models were tested on three levels including images, videos, and prospective patients. The best model was selected for constructing ENDOANGEL-MM. We compared the performance between the models and endoscopists and conducted a diagnostic study to explore the ENDOANGEL-MM's assistance ability. RESULTS: Model 4 (ENDOANGEL-MM) showed the best performance among five models. Model 2 performed better in single-modal models. The accuracy of ENDOANGEL-MM was higher than that of Model 2 in still images, real-time videos, and prospective patients. (86.54 vs 78.85%, P = 0.134; 90.00 vs 85.00%, P = 0.179; 93.55 vs 70.97%, P < 0.001). Model 2 and ENDOANGEL-MM outperformed endoscopists on WM data (85.00 vs 71.67%, P = 0.002) and multi-modal data (90.00 vs 76.17%, P = 0.002), significantly. With the assistance of ENDOANGEL-MM, the accuracy of non-experts improved significantly (85.75 vs 70.75%, P = 0.020), and performed no significant difference from experts (85.75 vs 89.00%, P = 0.159). CONCLUSIONS: The multi-modal model constructed by feature-level fusion showed the best performance. ENDOANGEL-MM identified gastric neoplasms with good accuracy and has a potential role in real-clinic.

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding.

Bleeding risk factors for gastroesophageal varices (GEV) detected by endoscopy in cirrhotic patients determine the prophylactical treatment patients will undergo in the following 2 years. We propose a methodology for measuring the risk factors. We create an artificial intelligence system (ENDOANGEL-GEV) containing six models to segment GEV and to classify the grades (grades 1-3) and red color signs (RC, RC0-RC3) of varices. It also summarizes changes in the above results with region in real time. ENDOANGEL-GEV is trained using 6034 images from 1156 cirrhotic patients across three hospitals (dataset 1) and validated on multicenter datasets with 11009 images from 141 videos (dataset 2) and in a prospective study recruiting 161 cirrhotic patients from Renmin Hospital of Wuhan University (dataset 3). In dataset 1, ENDOANGEL-GEV achieves intersection over union values of 0.8087 for segmenting esophageal varices and 0.8141 for gastric varices. In dataset 2, the system maintains fairly accuracy across images from three hospitals. In dataset 3, ENDOANGEL-GEV surpasses attended endoscopists in detecting RC of GEV and classifying grades (p < 0.001). When ranking the risk of patients combined with the Child‒Pugh score, ENDOANGEL-GEV outperforms endoscopists for esophageal varices (p < 0.001) and shows comparable performance for gastric varices (p = 0.152). Compared with endoscopists, ENDOANGEL-GEV may help 12.31% (16/130) more patients receive the right intervention. We establish an interpretable system for the endoscopic diagnosis and risk stratification of GEV. It will assist in detecting the first bleeding risk factors accurately and expanding the scope of quantitative measurement of diseases.

Evaluating the effect of an artificial intelligence system on the anesthesia quality control during gastrointestinal endoscopy with sedation: a randomized controlled trial.

BACKGROUND: Sedative gastrointestinal endoscopy is extensively used worldwide. An appropriate degree of sedation leads to more acceptability and satisfaction. Artificial intelligence has rapidly developed in the field of digestive endoscopy in recent years and we have constructed a mature computer-aided diagnosis (CAD) system. This system can identify the remaining parts to be examined in real-time endoscopic procedures, which may help anesthetists use anesthetics properly to keep patients in an appropriate degree of sedation. AIMS: This study aimed to evaluate the effects of the CAD system on anesthesia quality control during gastrointestinal endoscopy. METHODS: We recruited 154 consecutive patients at Renmin Hospital of Wuhan University, including 76 patients in the CAD group and 78 in the control group. Anesthetists in the CAD group were able to see the CAD system's indications, while anesthetists in the control group could not. The primary outcomes included emergence time (from examination completion to spontaneous eye opening when doctors called the patients' names), recovery time (from examination completion to achievement of the primary recovery endpoints) and patient satisfaction scores. The secondary outcomes included anesthesia induction time (from sedative administration to successful sedation), procedure time (from scope insertion to scope withdrawal), total dose of propofol, vital signs, etc. This trial was registered in the Primary Registries of the WHO Registry Network, with registration number ChiCTR2100042621. RESULTS: Emergence time in the CAD group was significantly shorter than that in the control group (p < 0.01). The recovery time was also significantly shorter in the CAD group (p < 0.01). Patients in the CAD group were significantly more satisfied with their sedation than those in control group (p < 0.01). Vital signs were stable during the examinations in both groups. Propofol doses during the examinations were comparable between the two groups. CONCLUSION: This CAD system possesses great potential for anesthesia quality control. It can improve patient satisfaction during endoscopic examinations with sedation. TRIAL REGISTRATION: ChiCTR2100042621.