Identifying Diffuse Glioma Subtypes Based on Pathway Enrichment Evaluation.

Gliomas are highly heterogeneous in molecular, histology, and microenvironment. However, a classification of gliomas by integrating different tumor microenvironment (TME) components remains unexplored. Based on the enrichment scores of 17 pathways involved in immune, stromal, DNA repair, and nervous system signatures in diffuse gliomas, we performed consensus clustering to uncover novel subtypes of gliomas. Consistently in three glioma datasets (TCGA-glioma, CGGA325, and CGGA301), we identified three subtypes: Stromal-enriched (Str-G), Nerve-enriched (Ner-G), and mixed (Mix-G). Ner-G was charactered by low immune infiltration levels, stromal contents, tumor mutation burden, copy number alterations, DNA repair activity, cell proliferation, epithelial-mesenchymal transformation, stemness, intratumor heterogeneity, androgen receptor expression and EGFR, PTEN, NF1 and MUC16 mutation rates, while high enrichment of neurons and nervous system pathways, and high tumor purity, estrogen receptor expression, IDH1 and CIC mutation rates, temozolomide response rate and overall and disease-free survival rates. In contrast, Str-G displayed contrastive characteristics to Ner-G. Our analysis indicates that the heterogeneity between glioma cells and neurons is lower than that between glioma cells and immune and stromal cells. Furthermore, the abundance of neurons is positively associated with clinical outcomes in gliomas, while the enrichment of immune and stromal cells has a negative association with them. Our classification method provides new insights into the tumor biology of gliomas, as well as clinical implications for the precise management of this disease.

Multi-step validation of a Post-Endoscopic Retrograde Cholangiopancreatography Pancreatitis prediction system integrating multi-modal data: A multi-center study.

BACKGROUND AND STUDY AIMS: The impact of various categories of information on the prediction of Post Endoscopic Retrograde Cholangiopancreatography Pancreatitis (PEP) remains uncertain. We aimed to comprehensively investigate the risk factors associated with PEP by constructing and validating a model incorporating multi-modal data through multiple steps. PATIENTS AND METHODS: A total of 1,916 cases underwent ERCP were retrospectively collected from multiple centers for model construction. Through literature research, 49 electronic health record (EHR) features and one image feature related to PEP were identified. The EHR features were categorized into baseline, diagnosis, technique, and prevent strategies, covering pre-ERCP, intra-ERCP, and peri-ERCP phases. We first incrementally constructed models 1-4 incorporating these four feature categories, then added the image feature into models 1-4 and developed models 5-8. All models underwent testing and comparison using both internal and external test sets. Once the optimal model was selected, we conducted comparison among multiple machine learning algorithms. RESULTS: Compared with model 2 incorporating baseline and diagnosis features, adding technique and prevent strategies (model 4) greatly improved the sensitivity (63.89% vs 83.33%, p<0.05) and specificity (75.00% vs 85.92%, p<0.001). Similar tendency was observed in internal and external tests. In model 4, the top three features ranked by weight were previous pancreatitis, NSAIDS, and difficult cannulation. The image-based feature has the highest weight in model 5-8. Lastly, model 8 employed Random Forest algorithm showed the best performance. CONCLUSIONS: We firstly developed a multi-modal prediction model for identifying PEP with clinical-acceptable performance. The image and technique features are crucial for PEP prediction.

A comprehensive comparison of molecular and phenotypic profiles between hepatitis B virus (HBV)-infected and non-HBV-infected hepatocellular carcinoma by multi-omics analysis.

Hepatitis B virus (HBV) infection is a major etiology of hepatocellular carcinoma (HCC). An interesting question is how different are the molecular and phenotypic profiles between HBV-infected (HBV+) and non-HBV-infected (HBV-) HCCs? Based on the publicly available multi-omics data for HCC, including bulk and single-cell data, and the data we collected and sequenced, we performed a comprehensive comparison of molecular and phenotypic features between HBV+ and HBV- HCCs. Our analysis showed that compared to HBV- HCCs, HBV+ HCCs had significantly better clinical outcomes, higher degree of genomic instability, higher enrichment of DNA repair and immune-related pathways, lower enrichment of stromal and oncogenic signaling pathways, and better response to immunotherapy. Furthermore, in vitro experiments confirmed that HBV+ HCCs had higher immunity, PD-L1 expression and activation of DNA damage response pathways. This study may provide insights into the profiles of HBV+ and HBV- HCCs, and guide rational therapeutic interventions for HCC patients.

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.

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.

American society of anesthesiologists physical status classification significantly affects the performances of machine learning models in intraoperative hypotension inference.

STUDY OBJECTIVE: To explore how American Society of Anesthesiologists (ASA) physical status classification affects different machine learning models in hypotension prediction and whether the prediction uncertainty could be quantified. DESIGN: Observational Studies SETTING: UofL health hospital PATIENTS: This study involved 562 hysterectomy surgeries performed on patients (≥ 18 years) between June 2020 and July 2021. INTERVENTIONS: None MEASUREMENTS: Preoperative and intraoperative data is collected. Three parametric machine learning models, including Bayesian generalized linear model (BGLM), Bayesian neural network (BNN), a newly proposed BNN with multivariate mixed responses (BNNMR), and one nonparametric model, Gaussian Process (GP), were explored to predict patients' diastolic and systolic blood pressures (continuous responses) and patients' hypotensive event (binary response) for the next five minutes. Data was separated into American Society of Anesthesiologists (ASA) physical status class 1- 4 before being read in by four machine learning models. Statistical analysis and models' constructions are performed in Python. Sensitivity, specificity, and the confidence/credible intervals were used to evaluate the prediction performance of each model for each ASA physical status class. MAIN RESULTS: ASA physical status classes require distinct models to accurately predict intraoperative blood pressures and hypotensive events. Overall, high sensitivity (above 0.85) and low uncertainty can be achieved by all models for ASA class 4 patients. In contrast, models trained without controlling ASA classes yielded lower sensitivity (below 0.5) and larger uncertainty. Particularly, in terms of predicting binary hypotensive event, for ASA physical status class 1, BNNMR yields the highest sensitivity of 1. For classes 2 and 3, BNN has the highest sensitivity of 0.429 and 0.415, respectively. For class 4, BNNMR and GP are tied with the highest sensitivity of 0.857. On the other hand, the sensitivity is just 0.031, 0.429, 0.165 and 0.305 for BNNMR, BNN, GBLM and GP models respectively, when training data is not divided by ASA physical status classes. In terms of predicting systolic blood pressure, the GP regression yields the lowest root mean squared errors (RMSE) of 2.072, 7.539, 9.214 and 0.295 for ASA physical status classes 1, 2, 3 and 4, respectively, but a RMSE of 126.894 if model is trained without controlling the ASA physical status class. The RMSEs for other models are far higher. RMSEs are 2.175, 13.861, 17.560 and 22.426 for classes 1, 2, 3 and 4 respectively for the BGLM. In terms of predicting diastolic blood pressure, the GP regression yields the lowest RMSEs of 2.152, 6.573, 5.371 and 0.831 for ASA physical status classes 1, 2, 3 and 4, respectively; RMSE of 8.084 if model is trained without controlling the ASA physical status class. The RMSEs for other models are far higher. Finally, in terms of the width of the 95% confidence interval of the mean prediction for systolic and diastolic blood pressures, GP regression gives narrower confidence interval with much smaller margin of error across all four ASA physical status classes. CONCLUSIONS: Different ASA physical status classes present different data distributions, and thus calls for distinct machine learning models to improve prediction accuracy and reduce predictive uncertainty. Uncertainty quantification enabled by Bayesian inference provides valuable information for clinicians as an additional metric to evaluate performance of machine learning models for medical decision making.

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.

Mendelian randomization and transcriptomic analysis reveal an inverse causal relationship between Alzheimer's disease and cancer.

BACKGROUND: Alzheimer's disease (AD) and cancer are common age-related diseases, and epidemiological evidence suggests an inverse relationship between them. However, investigating the potential mechanism underlying their relationship remains insufficient. METHODS: Based on genome-wide association summary statistics for 42,034 AD patients and 609,951 cancer patients from the GWAS Catalog using the two-sample Mendelian randomization (MR) method. Moreover, we utilized two-step MR to identify metabolites mediating between AD and cancer. Furthermore, we employed colocalization analysis to identify genes whose upregulation is a risk factor for AD and demonstrated the genes' upregulation to be a favorable prognostic factor for cancer by analyzing transcriptomic data for 33 TCGA cancer types. RESULTS: Two-sample MR analysis revealed a significant causal influence for increased AD risk on reduced cancer risk. Two-step MR analysis identified very low-density lipoprotein (VLDL) as a key mediator of the negative cause-effect relationship between AD and cancer. Colocalization analysis uncovered PVRIG upregulation to be a risk factor for AD. Transcriptomic analysis showed that PVRIG expression had significant negative correlations with stemness scores, and positive correlations with antitumor immune responses and overall survival in pan-cancer and multiple cancer types. CONCLUSION: AD may result in lower cancer risk. VLDL is a significant intermediate variable linking AD with cancer. PVRIG abundance is a risk factor for AD but a protective factor for cancer. This study demonstrates a causal influence for AD on cancer and provides potential molecular connections between both diseases.

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.

Effect of neuromuscular electrical stimulation combined with early rehabilitation therapy on mechanically ventilated patients: a prospective randomized controlled study.

BACKGROUND: This study aimed to investigate the effectiveness of neuromuscular electrical stimulation (NMES) blended with early rehabilitation on the diaphragm and skeletal muscle in sufferers on mechanical ventilation (MV). METHOD: This is a prospective randomized controlled study. Eighty patients on MV for respiratory failure were divided into a study group (40 cases) and a control group (40 cases) randomly. The study group adopted a treatment method of NMES combined with early rehabilitation and the control group adopted the method of early rehabilitation only. The diaphragmatic excursion (DE), diaphragmatic thickening fraction (DTF), variation of thickness of intercostal muscles (TIM), variation of thickness of rectus abdominis (TRA), and variation of the cross-sectional area of rectus femoris (CSA-RF) were measured to evaluate the therapeutic effect by ultrasound before and after intervention at the first day of MV, the 3rd and 7th day of intervention and the day discharged from ICU. RESULTS: No significant difference was found in the general demographic information and ultrasound indicators between the two groups before treatment (all P > 0.05). After treatment, the variation of DTF (0.15 ± 0.05% vs. 0.12 ± 0.04%, P = 0.034) was significantly higher in the study group than that in the control group on the day discharged from ICU. The variation of TRA (0.05 ± 0.09% vs. 0.10 ± 0.11%, P = 0.029) and variation of CSA-RF (0.13 ± 0.07% vs. 0.19 ± 0.08%, P < 0.001) in the study group were significantly lower than that in the control group. The duration of MV in the study group was significantly shorter than that in the control group [109.5 (88.0, 213.0) hours vs. 189.5 (131.5, 343.5) hours, P = 0.023]. The study group had better muscle strength score than the control group at discharge (52.20 ± 11.70 vs. 44.10 ± 15.70, P = 0.011). CONCLUSION: NMES combined with early rehabilitation therapy is beneficial in reducing muscle atrophy and improving muscle strength in mechanically ventilated patients. This treatment approach may provide a new option for patients to choose a rehabilitation program; however, more research is needed to fully evaluate the effectiveness of this treatment option.

Problem Solving and Emotion Coping Styles for Social Anxiety: A Meta-analysis of Chinese Mainland Students.

Studies of how positive and negative coping styles affect social anxiety show mixed results. Hence, our two meta-analyses determined the overall effect sizes of problem solving-focused coping (PSC) styles and emotion-focused coping (EFC) styles on social anxiety in mainland China (PSC: k = 49 studies, N = 34,669; EFC: k = 52, N = 36,531). PSC was negatively linked to social anxiety (- .198), and EFC was positively linked to social anxiety (.223). In years with more national income, PSC's and EFC's effect sizes were larger. PSC's effect sizes were smaller among rural students (vs. urban students), larger among older students (university, high school, middle school), and larger in cross-sectional (vs. longitudinal) studies. When using SAD (vs. others) social anxiety measures, PSC effect sizes were larger, but EFC effect sizes were smaller. EFC effect sizes were larger in studies with convenience (vs. representative) samples. Gender, single child status, and coping style measurement showed no moderation effects. These findings suggest that using problem solving-focused coping styles rather than emotion-focused may reduce social anxiety, so future experimental studies can test this idea more rigorously.

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.

Robust Cost Volume Generation Method for Dense Stereo Matching in Endoscopic Scenarios.

Stereo matching in binocular endoscopic scenarios is difficult due to the radiometric distortion caused by restricted light conditions. Traditional matching algorithms suffer from poor performance in challenging areas, while deep learning ones are limited by their generalizability and complexity. We introduce a non-deep learning cost volume generation method whose performance is close to a deep learning algorithm, but with far less computation. To deal with the radiometric distortion problem, the initial cost volume is constructed using two radiometric invariant cost metrics, the histogram of gradient angle and amplitude descriptors. Then we propose a new cross-scale propagation framework to improve the matching reliability in small homogenous regions without increasing the running time. The experimental results on the Middlebury Version 3 Benchmark show that the performance of the combination of our method and Local-Expansion, an optimization algorithm, ranks top among non-deep learning algorithms. Other quantitative experimental results on a surgical endoscopic dataset and our binocular endoscope show that the accuracy of the proposed algorithm is at the millimeter level which is comparable to the accuracy of deep learning algorithms. In addition, our method is 65 times faster than its deep learning counterpart in terms of cost volume generation.

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.

Effect of a deep learning-based automatic upper GI endoscopic reporting system: a randomized crossover study (with video).

BACKGROUND AND AIMS: EGD is essential for GI disorders, and reports are pivotal to facilitating postprocedure diagnosis and treatment. Manual report generation lacks sufficient quality and is labor intensive. We reported and validated an artificial intelligence-based endoscopy automatic reporting system (AI-EARS). METHODS: The AI-EARS was designed for automatic report generation, including real-time image capturing, diagnosis, and textual description. It was developed using multicenter datasets from 8 hospitals in China, including 252,111 images for training, 62,706 images, and 950 videos for testing. Twelve endoscopists and 44 endoscopy procedures were consecutively enrolled to evaluate the effect of the AI-EARS in a multireader, multicase, crossover study. The precision and completeness of the reports were compared between endoscopists using the AI-EARS and conventional reporting systems. RESULTS: In video validation, the AI-EARS achieved completeness of 98.59% and 99.69% for esophageal and gastric abnormality records, respectively, accuracies of 87.99% and 88.85% for esophageal and gastric lesion location records, and 73.14% and 85.24% for diagnosis. Compared with the conventional reporting systems, the AI-EARS achieved greater completeness (79.03% vs 51.86%, P < .001) and accuracy (64.47% vs 42.81%, P < .001) of the textual description and completeness of the photo-documents of landmarks (92.23% vs 73.69%, P < .001). The mean reporting time for an individual lesion was significantly reduced (80.13 ± 16.12 seconds vs 46.47 ± 11.68 seconds, P < .001) after the AI-EARS assistance. CONCLUSIONS: The AI-EARS showed its efficacy in improving the accuracy and completeness of EGD reports. It might facilitate the generation of complete endoscopy reports and postendoscopy patient management. (Clinical trial registration number: NCT05479253.).

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.

A deep learning and natural language processing-based system for automatic identification and surveillance of high-risk patients undergoing upper endoscopy: A multicenter study.

Background: Timely identification and regular surveillance of patients at high risk are crucial for early diagnosis of upper gastrointestinal cancer. However, traditional manual surveillance method is time-consuming, and current surveillance rate is below 50%. Here, we aimed to develop a surveillance system named ENDOANGEL-AS (automatic surveillance) for automatic identification and surveillance of high-risk patients. Methods: 7874 patients from Renmin Hospital of Wuhan University between May 1 and July 31, 2021 were used as the training set, 6762 patients between August 1 and October 31, 2021 as the internal test set, and 7570 patients from two other hospitals between August 1 and October 31, 2021 as the external test sets. We first extracted descriptions of abnormalities from endoscopic and pathological reports based on natural language processing techniques to identify individuals. Then patients were classified at nine risk levels according to endoscopic and pathological findings, and a deep learning model was trained to identify demarcation line (DL) in gastric low-grade intraepithelial neoplasia (LGIN) using 1561 white-light still images for risk stratification of gastric LGIN. Finally, patients undergoing upper endoscopy were classified and assigned one of ten surveillance intervals according to guidelines. The performance of ENDOANGEL-AS was evaluated and compared with physicians. Findings: Patient identification module achieved an accuracy of 100% and 99.91% in internal and external test sets, respectively. Risk level classification module achieved an accuracy of 100% and 99.85% in the internal and external test sets, respectively. DL identification module achieved an accuracy of 87.88%. ENDOANGEL-AS on surveillance interval assignment achieved an accuracy of 99.23% and 99.67% in internal and external test sets, respectively. ENDOANGEL-AS had significantly higher accuracy compared with physicians (99.00% vs 38.87%, p < 0.001). The accuracy (63.67%, p < 0.001) of endoscopists with the assistance of ENDOANGEL-AS was significantly improved. Interpretation: We established a surveillance system that can automatically identify patients and assign surveillance intervals with high accuracy and good transferability. Funding: This work was partly supported by a grant from the Hubei Province Major Science and Technology Innovation Project (2018-916-000-008) and the Fundamental Research Funds for the Central Universities (2042021kf0084).

The Variation of Transcriptomic Perturbations is Associated with the Development and Progression of Various Diseases.

Background: Although transcriptomic data have been widely applied to explore various diseases, few studies have investigated the association between transcriptomic perturbations and disease development in a wide variety of diseases. Methods: Based on a previously developed algorithm for quantifying intratumor heterogeneity at the transcriptomic level, we defined the variation of transcriptomic perturbations (VTP) of a disease relative to the health status. Based on publicly available transcriptome datasets, we compared VTP values between the disease and health status and analyzed correlations between VTP values and disease progression or severity in various diseases, including neurological disorders, infectious diseases, cardiovascular diseases, respiratory diseases, liver diseases, kidney diseases, digestive diseases, and endocrine diseases. We also identified the genes and pathways whose expression perturbations correlated positively with VTP across diverse diseases. Results: VTP values were upregulated in various diseases relative to their normal controls. VTP values were significantly greater in define than in possible or probable Alzheimer's disease. VTP values were significantly larger in intensive care unit (ICU) COVID-19 patients than in non-ICU patients, and in COVID-19 patients requiring mechanical ventilatory support (MVS) than in those not requiring MVS. VTP correlated positively with viral loads in acquired immune deficiency syndrome (AIDS) patients. Moreover, the AIDS patients treated with abacavir or zidovudine had lower VTP values than those without such therapies. In pulmonary tuberculosis (TB) patients, VTP values followed the pattern: active TB > latent TB > normal controls. VTP values were greater in clinically apparent than in presymptomatic malaria. VTP correlated negatively with the cardiac index of left ventricular ejection fraction (LVEF). In chronic obstructive pulmonary disease (COPD), VTP showed a negative correlation with forced expiratory volume in the first second (FEV1). VTP values increased with H. pylori infection and were upregulated in atrophic gastritis caused by H. pylori infection. The genes and pathways whose expression perturbations correlated positively with VTP scores across diseases were mainly involved in the regulation of immune, metabolic, and cellular activities. Conclusions: VTP is upregulated in the disease versus health status, and its upregulation is associated with disease progression and severity in various diseases. Thus, VTP has potential clinical implications for disease diagnosis and prognosis.