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 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.

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.

Efficacy and safety of first-line therapy in patients with HER2-positive advanced breast cancer: a network meta-analysis of randomized controlled trials.

PURPOSE: The numerous first-line treatment regimens for human epidermal growth factor receptor 2 (HER2)-positive advanced breast cancer (ABC) necessitate a comprehensive evaluation to inform clinical decision-making. We conducted a Bayesian network meta-analysis (NMA) to compare the efficacy and safety of different interventions. METHODS: We systematically searched for relevant randomized controlled trials (RCTs) in Pubmed, Embase, Cochrane Library and online abstracts from inception to June 1, 2023. NMA was performed to calculate and analyze progression-free survival (PFS), overall survival (OS), objective response rate (ORR), and adverse events of grade 3 or higher (≥ 3 AEs). RESULTS: Out of the 10,313 manuscripts retrieved, we included 28 RCTs involving 11,680 patients. Regarding PFS and ORR, the combination of trastuzumab with tyrosine kinase inhibitors (TKIs) was more favorable than dual-targeted therapy. If only using trastuzumab, combination chemotherapy is superior to monochemotherapy in terms of PFS. It is important to note that the addition of anthracycline did not result in improved PFS. For patients with hormone receptor-positive HER2-positive diseases, dual-targeted combined with endocrine therapy showed better benefit in terms of PFS compared to dual-targeted alone, but it did not reach statistical significance. The comprehensive analysis of PFS and ≥ 3 AEs indicates that monochemotherapy combined with dual-targeted therapy still has the optimal balance between efficacy and safety. CONCLUSION: Monochemotherapy (Docetaxel) plus dual-target (Trastuzumab and Pertuzumab) therapy remains the optimal choice among all first-line treatment options for ABC. The combination of trastuzumab with TKIs (Pyrotinib) demonstrated a significant improvement in PFS and ORR, but further data are warranted to confirm the survival benefit.

Facile Synthesis of Diazaanthraquinone Dimers as High-Capacity Organic Cathode Materials for Rechargeable Lithium Batteries.

Organic cathode materials (OCMs) have tremendous potential to construct sustainable and highly efficient batteries beyond conventional Li-ion batteries. Thereinto, quinone/pyrazine hybrids show significant advantages in material availability, energy density, and cycling stability. Herein, we propose a facile method to synthesize quinone/pyrazine hybrids, i.e., the condensation reaction between ortho-diamine and bromoacetyl groups. Based on it, we have successfully synthesized three 1,4-diazaanthraquinone (DAAQ) dimers, including 2,2'-bi(1,4-diazaanthraquinone) (BDAAQ) with an exceptional theoretical capacity of 512 mAh g-1 based on the eight-electron reaction. It can be fully utilized in Li batteries in a wide voltage range of 0.8-3.8 V, at the cost of inferior cycling stability. In an optimal voltage range of 1.4-3.8 V, BDAAQ exhibits one of the best comprehensive electrochemical performances for small-molecule OCMs, including a high specific capacity of 366 mAh g-1, an average discharge voltage of 2.26 V, as well as a respectable capacity retention of 59% after 500 cycles. Moreover, the in-depth investigations reveal the redox reaction mechanisms based on C═O and C═N groups as well as the capacity fading mechanisms based on dissolution-redeposition behaviors. In brief, this work provides an instructive synthesis method and mechanism understanding of high-performance OCMs based on a quinone/pyrazine hybrid structure.

A Blood Hepatocellular Carcinoma Signature Recognizes Very Small Tumor Nodules with Metastatic Traits.

Background and Aims: Hepatocellular carcinoma (HCC) cases with small nodules are commonly treated with radiofrequency ablation (RFA), but the recurrence rate remains high. This study aimed to establish a blood signature for identifying HCC with metastatic traits pre-RFA. Methods: Data from HCC patients treated between 2010 and 2017 were retrospectively collected. A blood signature for metastatic HCC was established based on blood levels of alpha-fetoprotein and des-γ-carboxy-prothrombin, cell-free DNA (cfDNA) mutations, and methylation changes in target genes in frozen-stored plasma samples that were collected before RFA performance. The HCC blood signature was validated in patients prospectively enrolled in 2021. Results: Of 251 HCC patients in the retrospective study, 33.9% experienced recurrence within 1 year post-RFA. The HCC blood signature identified from these patients included des-γ-carboxy-prothrombin ≥40 mAU/mL with cfDNA mutation score, where cfDNA mutations occurred in the genes of TP53, CTNNB1, and TERT promoter. This signature effectively predicted 1-year post-RFA recurrence of HCC with 92% specificity and 91% sensitivity in the retrospective dataset, and with 87% specificity and 76% sensitivity in the prospective dataset (n=32 patients). Among 14 cases in the prospective study with biopsy tissues available, positivity for the HCC blood signature was associated with a higher HCC tissue score and shorter distance between HCC cells and microvasculature. Conclusions: This study established an HCC blood signature in pre-RFA blood that potentially reflects HCC with metastatic traits and may be valuable for predicting the disease's early recurrence post-RFA.

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.