Cost-effectiveness and cost-utility of a digital technology-driven hierarchical healthcare screening pattern in China.

Utilization of digital technologies for cataract screening in primary care is a potential solution for addressing the dilemma between the growing aging population and unequally distributed resources. Here, we propose a digital technology-driven hierarchical screening (DH screening) pattern implemented in China to promote the equity and accessibility of healthcare. It consists of home-based mobile artificial intelligence (AI) screening, community-based AI diagnosis, and referral to hospitals. We utilize decision-analytic Markov models to evaluate the cost-effectiveness and cost-utility of different cataract screening strategies (no screening, telescreening, AI screening and DH screening). A simulated cohort of 100,000 individuals from age 50 is built through a total of 30 1-year Markov cycles. The primary outcomes are incremental cost-effectiveness ratio and incremental cost-utility ratio. The results show that DH screening dominates no screening, telescreening and AI screening in urban and rural China. Annual DH screening emerges as the most economically effective strategy with 341 (338 to 344) and 1326 (1312 to 1340) years of blindness avoided compared with telescreening, and 37 (35 to 39) and 140 (131 to 148) years compared with AI screening in urban and rural settings, respectively. The findings remain robust across all sensitivity analyses conducted. Here, we report that DH screening is cost-effective in urban and rural China, and the annual screening proves to be the most cost-effective option, providing an economic rationale for policymakers promoting public eye health in low- and middle-income countries.

Effect of Premedication With Pronase Before Upper Gastrointestinal Endoscopy: A Multicenter Prospective Randomized Controlled Study.

OBJECTIVES: This study aimed to confirm whether premedication with pronase before endoscopy improves mucosal visualization and increases precancerous lesion and cancer lesion detection rates. MATERIALS AND METHODS: From June 2018 to April 2019, out-patients scheduled for endoscopy from 13 hospitals were screened to be randomly allocated in a 2:1 ratio to premedication with pronase (group A) and water (group B). The primary endpoint was mucosal visibility scores, and the secondary endpoint was precancerous and cancer lesion detection rates. This trial was registered at Chinese Clinical Trial Registry, and the registration number was ChiCTR1800016853. RESULTS: Group A showed significantly lower mucosal visibility scores (better mucosal visibility) of esophagus, stomach, and duodenum than group B, with all P -values <0.001. The overall cancer detection rates between group A and group B were 0.83 and 1.08%, and overall detection rates of precancerous and cancer lesion were 4.4 and 4.9%, both without significant difference ( P =1.000 and 0.824). In addition, the flushing volume (milliliter) of group A (10.52±23.41) was less than group B (36.30±52.11) ( P <0.001), and the flushing frequency of group A (0.46±1.01) was fewer than group B (1.62±2.12) ( P <0.001). CONCLUSIONS: Premedication with pronase could achieve better mucosal visibility and decrease flushing frequency and volume, but may not increase lesion detection rates.

FFMAVP: a new classifier based on feature fusion and multitask learning for identifying antiviral peptides and their subclasses.

Antiviral peptides (AVPs) are widely found in animals and plants, with high specificity and strong sensitivity to drug-resistant viruses. However, due to the great heterogeneity of different viruses, most of the AVPs have specific antiviral activities. Therefore, it is necessary to identify the specific activities of AVPs on virus types. Most existing studies only identify AVPs, with only a few studies identifying subclasses by training multiple binary classifiers. We develop a two-stage prediction tool named FFMAVP that can simultaneously predict AVPs and their subclasses. In the first stage, we identify whether a peptide is AVP or not. In the second stage, we predict the six virus families and eight species specifically targeted by AVPs based on two multiclass tasks. Specifically, the feature extraction module in the two-stage task of FFMAVP adopts the same neural network structure, in which one branch extracts features based on amino acid feature descriptors and the other branch extracts sequence features. Then, the two types of features are fused for the following task. Considering the correlation between the two tasks of the second stage, a multitask learning model is constructed to improve the effectiveness of the two multiclass tasks. In addition, to improve the effectiveness of the second stage, the network parameters trained through the first-stage data are used to initialize the network parameters in the second stage. As a demonstration, the cross-validation results, independent test results and visualization results show that FFMAVP achieves great advantages in both stages.

Real-Time Evaluation of Helicobacter pylori Infection by Convolution Neural Network During White-Light Endoscopy: A Prospective, Multicenter Study (With Video).

INTRODUCTION: Convolutional neural network during endoscopy may facilitate evaluation of Helicobacter pylori infection without obtaining gastric biopsies. The aim of the study was to evaluate the diagnosis accuracy of a computer-aided decision support system for H. pylori infection (CADSS-HP) based on convolutional neural network under white-light endoscopy. METHODS: Archived video recordings of upper endoscopy with white-light examinations performed at Sir Run Run Shaw Hospital (January 2019-September 2020) were used to develop CADSS-HP. Patients receiving endoscopy were prospectively enrolled (August 2021-August 2022) from 3 centers to calculate the diagnostic property. Accuracy of CADSS-HP for H. pylori infection was also compared with endoscopic impression, urea breath test (URT), and histopathology. H. pylori infection was defined by positive test on histopathology and/or URT. RESULTS: Video recordings of 599 patients who received endoscopy were used to develop CADSS-HP. Subsequently, 456 patients participated in the prospective evaluation including 189 (41.4%) with H. pylori infection. With a threshold of 0.5, CADSS-HP achieved an area under the curve of 0.95 (95% confidence interval [CI], 0.93-0.97) with sensitivity and specificity of 91.5% (95% CI 86.4%-94.9%) and 88.8% (95% CI 84.2%-92.2%), respectively. CADSS-HP demonstrated higher sensitivity (91.5% vs 78.3%; mean difference = 13.2%, 95% CI 5.7%-20.7%) and accuracy (89.9% vs 83.8%, mean difference = 6.1%, 95% CI 1.6%-10.7%) compared with endoscopic diagnosis by endoscopists. Sensitivity of CADSS-HP in diagnosing H. pylori was comparable with URT (91.5% vs 95.2%; mean difference = 3.7%, 95% CI -1.8% to 9.4%), better than histopathology (91.5% vs 82.0%; mean difference = 9.5%, 95% CI 2.3%-16.8%). DISCUSSION: CADSS-HP achieved high sensitivity in the diagnosis of H. pylori infection in the real-time test, outperforming endoscopic diagnosis by endoscopists and comparable with URT. Clinicaltrials.gov ; ChiCTR2000030724.

Advances of endoscopic and surgical management in gastrointestinal stromal tumors.

As one of the most common mesenchymal malignancies in the digestive system, gastrointestinal stromal tumors (GISTs) occur throughout the alimentary tract with diversified oncological characteristics. With the advent of the tyrosine kinase inhibitor era, the treatment regimens of patients with GISTs have been revolutionized and GISTs have become the paradigm of multidisciplinary therapy. However, surgery resection remains recognized as the potentially curative management for the radical resection and provided with favorable oncological outcomes. The existing available surgery algorithms in clinical practice primarily incorporate open procedure, and endoscopic and laparoscopic surgery together with combined operation techniques. The performance of various surgery methods often refers to the consideration of risk evaluation of recurrence and metastases; the degree of disease progression; size, location, and growth pattern of tumor; general conditions of selected patients; and indications and safety profile of various techniques. In the present review, we summarize the fundamental principle of surgery of GISTs based on risk assessment as well as tumor size, location, and degree of progress with an emphasis on the indications, strengths, and limitations of current surgery techniques.

Disease Burden of Total and Early-Onset Colorectal Cancer in China from 1990 to 2019 and Predictions of Cancer Incidence and Mortality.

Background: Understanding the temporal trends in the epidemiology of colorectal cancer (CRC) and early-onset CRC (EOCRC) in China is essential for policymakers to develop appropriate strategies to reduce the CRC burden. Methods: The prevalence, incidence, mortality, years of life lived with disability (YLDs), years of life lost (YLLs), and disability-adjusted life years (DALYs) of CRC were obtained from the Global Burden of Disease (GBD) Study 2019. The incidence and mortality of CRC over the next 25 years were predicted. Results: From 1990 to 2019, the prevalence, incidence, and mortality of total CRC and EOCRC significantly increased in males, with milder trends in females. In 2019, the number of people living with CRC (or EOCRC) in China was approximately 3.4 (0.59) million, which was over seven (five) times higher than that in 1990. The DALYs, YLDs, and YLLs moderately increased from 1990 to 2019 in both sexes. The age-standardized mortality rate (ASMR) for females has shown a stable trend in total CRC, and a downward trend in EOCRC since 2000. While the ASMR for males showed increasing trends in total CRC and EOCRC. In 2019, the highest incidence, prevalence, YLDs, YLLs, and DALYs were all observed in the 65 to 69 age group, while the highest mortality was in the 70 to 74. By 2044, the incidence and deaths of CRC are expected to reach 1310 thousand and 484 thousand, respectively. For EOCRC, the incidence will peak at about 101 thousand around 2034, and the mortality will continuously decrease to a nadir at about 18 thousand around 2044. Conclusion: Although the age-standardized incidence and mortality of total CRC and EOCRC in China will reach a plateau, the number of incident cases and deaths of CRC have been increasing in the last three decades and will continue to increase in the next 25 years.

SHP2 inhibition mitigates adaptive resistance to MEK inhibitors in KRAS-mutant gastric cancer through the suppression of KSR1 activity.

Despite the promising antitumor activity of RAF/MEK inhibitors for RAS-driven cancers, not all patients respond to these therapies. Adaptive resistance has been reported as a major culprit in non-responders, which can be reversed by SHP2 inhibitors (SHP2is) in multiple cancer cells; however, the underlying mechanisms remain unknown. In this study, we found that KRAS-mutant gastric cancer cells respond to MEK inhibitors (MEKis) with adaptive resistance. Markedly, SHP2 activation accompanied by ERK signaling restoration in MEKi-treated cells, and a MEKi and SHP2i combination had a synergistic effect on downstream signaling blockade. In vivo, SHP099 combined with AZD6244 (selumetinib) was highly efficacious for the treatment of xenografts. Mechanistically, SHP2 was found to interact with the scaffold protein KSR1 through its protein tyrosine phosphatase domain. KSR1 knockdown sensitized cells to AZD6244, whereas a KSR1 activating mutation (S269A) diminished the synergistic anti-proliferative effect of SHP2i and MEKi. Interestingly, activated SHP2, during adaptive resistance to MEKis, impaired the interaction with KSR1, activating KSR1 to promote MAPK signaling. In conclusion, SHP2 promotes adaptive resistance to MEKis by activating KSR1; selumetinib combined with SHP099 might be an available therapeutic strategy for KRAS-mutant gastric cancers.

Multiple Bismuth Quadruple Therapy Containing Tetracyclines Combined with Other Antibiotics and Helicobacter pylori Eradication Therapy.

Helicobacter pylori (HP) infection is closely associated with the development of chronic gastritis, peptic ulcer, and gastric cancer. However, the resistance rate of H. pylori strains to antibiotics such as clarithromycin, metronidazole, and levofloxacin has increased significantly, resulting in a significant decrease in the eradication efficacy of commonly used regimens. Tetracycline has received the attention of domestic and foreign scholars because of its low resistance. The purpose of this review is to provide an update on the tetracycline-containing bismuth quadruple eradication therapy for H. pylori infection and review the efficacy and safety of the regimens, hoping to provide guidance for clinical practice.

An overview of agents and treatments for PDGFRA-mutated gastrointestinal stromal tumors.

Platelet-derived growth factor receptor A (PDGFRA) mutations occur in approximately 10-15% of gastrointestinal stromal tumors (GISTs). These tumors with PDGFRA mutations have a different pathogenesis, clinical characteristics, and treatment response compared to tumors with receptor tyrosine kinase protein (KIT) mutations (60-70%). Many clinical studies have investigated the use of tyrosine kinase inhibitors mainly in patients with KIT mutations; however, there is a lack of attention to the PDGFRA-mutated molecular subtype. The main effective inhibitors of PDGFRA are ripretinib, avapritinib, and crenolanib, and their mechanisms and efficacy in GIST (as confirmed in clinical trials) are described in this review. Some multi-targeted tyrosine kinase inhibitors with inhibitory effects on this molecular subtype are also introduced and summarized in this paper. This review focuses on PDGFRA-mutated GISTs, introduces their clinical characteristics, downstream molecular signaling pathways, and existing resistance mechanisms. We focus on the most recent literature that describes the development of PDGFRA inhibitors and their use in clinical trials, as well as the potential benefits from different combination therapy strategies.

Might Patients with Metastatic Gastrointestinal Stromal Tumors Benefit from Operative Management? A Population-Based Retrospective Study.

Background: With respect to effect of surgery on the therapy of patients with metastatic gastrointestinal stromal tumors (mGISTs), still no consensus has been reached. This research designed to investigate the effect of surgical treatment on prognosis in patients with mGISTs. Methods: The population-based study consisted of 6282 GIST patients diagnosed between 2001 and 2016, from the Surveillance, Epidemiology, and End Results (SEER) database registry. The Kaplan-Meier method and Cox model were employed for the exploration of the effect of surgery on overall survival (OS) and GIST-specific survival (GSS). Results: In total, 6282 patients were diagnosed with GISTs, including 1238 (19.7%) mGIST patients and 5044 (80.3%) non-mGIST patients. Compared with the patients with non-mGISTs, metastatic patients assumed relatively lower proportion of surgical management (756 [61.1%] vs. 4666 [92.5%], P < 0.001). Based on unadjusted analysis, mGIST patients with operative management presented higher five years OS together with GSS in comparison with those without operative management (OS: 58.3% vs. 33.1%, P < 0.001; GSS: 61.6% vs. 36.7%, P < 0.001). Multivariable analysis found that no surgery was correlated to more than 2-fold increased death risk (OS, adjusted HR = 2.27, 95% CI: 1.90-2.71; GSS, adjusted HR = 2.42, 95% CI: 2.00-2.93). Conclusion: Metastatic GIST patients could potentially benefit from operative management with improved GSS and OS.

An end-to-end tracking method for polyp detectors in colonoscopy videos.

Deep learning based computer-aided diagnosis technology demonstrates an encouraging performance in aspect of polyp lesion detection on reducing the miss rate of polyps during colonoscopies. However, to date, few studies have been conducted for tracking polyps that have been detected in colonoscopy videos, which is an essential and intuitive issue in clinical intelligent video analysis task (e.g. lesion counting, lesion retrieval, report generation). In the paradigm of conventional tracking-by-detection system, detection task for lesion localization is separated from the tracking task for cropped lesions re-identification. In the multi object tracking problem, each target is supposed to be tracked by invoking a tracker after the detector, which introduces multiple inferences and leads to external resource and time consumption. To tackle these problems, we proposed a plug-in module named instance tracking head (ITH) for synchronous polyp detection and tracking, which can be simply inserted into object detection frameworks. It embeds a feature-based polyp tracking procedure into the detector frameworks to achieve multi-task model training. ITH and detection head share the model backbone for low level feature extraction, and then low level feature flows into the separate branches for task-driven model training. For feature maps from the same receptive field, the region of interest head assigns these features to the detection head and the ITH, respectively, and outputs the object category, bounding box coordinates, and instance feature embedding simultaneously for each specific polyp target. We also proposed a method based on similarity metric learning. The method makes full use of the prior boxes in the object detector to provide richer and denser instance training pairs, to improve the performance of the model evaluation on the tracking task. Compared with advanced tracking-by-detection paradigm methods, detectors with proposed ITH can obtain comparative tracking performance but approximate 30% faster speed. Optimized model based on Scaled-YOLOv4 detector with ITH illustrates good trade-off between detection (mAP 91.70%) and tracking (MOTA 92.50% and Rank-1 Acc 88.31%) task at the frame rate of 66 FPS. The proposed structure demonstrates the potential to aid clinicians in real-time detection with online tracking or offline retargeting of polyp instances during colonoscopies.

Multi-label recognition of cancer-related lesions with clinical priors on white-light endoscopy.

Deep learning-based computer-aided diagnosis techniques have demonstrated encouraging performance in endoscopic lesion identification and detection, and have reduced the rate of missed and false detections of disease during endoscopy. However, the interpretability of the model-based results has not been adequately addressed by existing methods. This phenomenon is directly manifested by a significant bias in the representation of feature localization. Good recognition models experience severe feature localization errors, particularly for lesions with subtle morphological features, and such unsatisfactory performance hinders the clinical deployment of models. To effectively alleviate this problem, we proposed a solution to optimize the localization bias in feature representations of cancer-related recognition models that is difficult to accurately label and identify in clinical practice. Optimization was performed in the training phase of the model through the proposed data augmentation method and auxiliary loss function based on clinical priors. The data augmentation method, called partial jigsaw, can "break" the spatial structure of lesion-independent image blocks and enrich the data feature space to decouple the interference of background features on the space and focus on fine-grained lesion features. The annotation-based auxiliary loss function used class activation maps for sample distribution correction and led the model to present localization representation converging on the gold standard annotation of visualization maps. The results show that with the improvement of our method, the precision of model recognition reached an average of 92.79%, an F1-score of 92.61%, and accuracy of 95.56% based on a dataset constructed from 23 hospitals. In addition, we quantified the evaluation representation of visualization feature maps. The improved model yielded significant offset correction results for visualized feature maps compared with the baseline model. The average visualization-weighted positive coverage improved from 51.85% to 83.76%. The proposed approach did not change the deployment capability and inference speed of the original model and can be incorporated into any state-of-the-art neural network. It also shows the potential to provide more accurate localization inference results and assist in clinical examinations during endoscopies.

Application of Surgical Decision Model for Patients With Childhood Cataract: A Study Based on Real World Data.

Reliable validated methods are necessary to verify the performance of diagnosis and therapy-assisted models in clinical practice. However, some validated results have research bias and may not reflect the results of real-world application. In addition, the conduct of clinical trials has executive risks for the indeterminate effectiveness of models and it is challenging to finish validated clinical trials of rare diseases. Real world data (RWD) can probably solve this problem. In our study, we collected RWD from 251 patients with a rare disease, childhood cataract (CC) and conducted a retrospective study to validate the CC surgical decision model. The consistency of the real surgical type and recommended surgical type was 94.16%. In the cataract extraction (CE) group, the model recommended the same surgical type for 84.48% of eyes, but the model advised conducting cataract extraction and primary intraocular lens implantation (CE + IOL) surgery in 15.52% of eyes, which was different from the real-world choices. In the CE + IOL group, the model recommended the same surgical type for 100% of eyes. The real-recommended matched rates were 94.22% in the eyes of bilateral patients and 90.38% in the eyes of unilateral patients. Our study is the first to apply RWD to complete a retrospective study evaluating a clinical model, and the results indicate the availability and feasibility of applying RWD in model validation and serve guidance for intelligent model evaluation for rare diseases.

Simultaneous Recognition of Atrophic Gastritis and Intestinal Metaplasia on White Light Endoscopic Images Based on Convolutional Neural Networks: A Multicenter Study.

INTRODUCTION: Patients with atrophic gastritis (AG) or gastric intestinal metaplasia (GIM) have elevated risk of gastric adenocarcinoma. Endoscopic screening and surveillance have been implemented in high incidence countries. The study aimed to evaluate the accuracy of a deep convolutional neural network (CNN) for simultaneous recognition of AG and GIM. METHODS: Archived endoscopic white light images with corresponding gastric biopsies were collected from 14 hospitals located in different regions of China. Corresponding images by anatomic sites containing AG, GIM, and chronic non-AG were categorized using pathology reports. The participants were randomly assigned (8:1:1) to the training cohort for developing the CNN model (TResNet), the validation cohort for fine-tuning, and the test cohort for evaluating the diagnostic accuracy. The area under the curve (AUC), sensitivity, specificity, and accuracy with 95% confidence interval (CI) were calculated. RESULTS: A total of 7,037 endoscopic images from 2,741 participants were used to develop the CNN for recognition of AG and/or GIM. The AUC for recognizing AG was 0.98 (95% CI 0.97-0.99) with sensitivity, specificity, and accuracy of 96.2% (95% CI 94.2%-97.6%), 96.4% (95% CI 94.8%-97.9%), and 96.4% (95% CI 94.4%-97.8%), respectively. The AUC for recognizing GIM was 0.99 (95% CI 0.98-1.00) with sensitivity, specificity, and accuracy of 97.9% (95% CI 96.2%-98.9%), 97.5% (95% CI 95.8%-98.6%), and 97.6% (95% CI 95.8%-98.6%), respectively. DISCUSSION: CNN using endoscopic white light images achieved high diagnostic accuracy in recognizing AG and GIM.

High Accuracy of Convolutional Neural Network for Evaluation of Helicobacter pylori Infection Based on Endoscopic Images: Preliminary Experience.

OBJECTIVES: Application of artificial intelligence in gastrointestinal endoscopy is increasing. The aim of the study was to examine the accuracy of convolutional neural network (CNN) using endoscopic images for evaluating Helicobacter pylori (H. pylori) infection. METHODS: Patients who received upper endoscopy and gastric biopsies at Sir Run Run Shaw Hospital (January 2015-June 2015) were retrospectively searched. A novel Computer-Aided Decision Support System that incorporates CNN model (ResNet-50) based on endoscopic gastric images was developed to evaluate for H. pylori infection. Diagnostic accuracy was evaluated in an independent validation cohort. H. pylori infection was defined by the presence of H. pylori on immunohistochemistry testing on gastric biopsies and/or a positive 13C-urea breath test. RESULTS: Of 1,959 patients, 1,507 (77%) including 847 (56%) with H. pylori infection (11,729 gastric images) were assigned to the derivation cohort, and 452 (23%) including 310 (69%) with H. pylori infection (3,755 images) were assigned to the validation cohort. The area under the curve for a single gastric image was 0.93 (95% confidence interval [CI] 0.92-0.94) with sensitivity, specificity, and accuracy of 81.4% (95% CI 79.8%-82.9%), 90.1% (95% CI 88.4%-91.7%), and 84.5% (95% CI 83.3%-85.7%), respectively, using an optimal cutoff value of 0.3. Area under the curve for multiple gastric images (8.3 ± 3.3) per patient was 0.97 (95% CI 0.96-0.99) with sensitivity, specificity, and accuracy of 91.6% (95% CI 88.0%-94.4%), 98.6% (95% CI 95.0%-99.8%), and 93.8% (95% CI 91.2%-95.8%), respectively, using an optimal cutoff value of 0.4. DISCUSSION: In this pilot study, CNN using multiple archived gastric images achieved high diagnostic accuracy for the evaluation of H. pylori infection.

Real-time gastric polyp detection using convolutional neural networks.

Computer-aided polyp detection in gastric gastroscopy has been the subject of research over the past few decades. However, despite significant advances, automatic polyp detection in real time is still an unsolved problem. In this paper, we report on a convolutional neural network (CNN) for polyp detection that is constructed based on Single Shot MultiBox Detector (SSD) architecture and which we call SSD for Gastric Polyps (SSD-GPNet). To take full advantages of feature maps' information from the feature pyramid and to acquire higher accuracy, we re-use information that is abandoned by Max-Pooling layers. In other words, we reuse the lost data from the pooling layers and concatenate that data as extra feature maps to contribute to classification and detection. Meanwhile, in the feature pyramid, we concatenate feature maps of the lower layers and feature maps that are deconvolved from upper layers to make explicit relationships between layers and to effectively increase the number of channels. The results show that our enhanced SSD for gastric polyp detection can realize real-time polyp detection with 50 frames per second (FPS) and can improve the mean average precision (mAP) from 88.5% to 90.4%, with only a little loss in time-performance. And the further experiment shows that SSD-GPNet has excellent performance in improving polyp detection recalls over 10% (p = 0.00053), especially in small polyp detection. This can help endoscopic physicians more easily find missed polyps and decrease the gastric polyp miss rate. It may be applicable in daily clinical practice to reduce the burden on physicians.

Outcomes of furazolidone- and amoxicillin-based quadruple therapy for Helicobacter pylori infection and predictors of failed eradication.

AIM: To evaluate the outcomes of furazolidone- and amoxicillin-based quadruple therapy for treatment of Helicobacter pylori (H. pylori) infection and identify predictors of failed eradication. METHODS: Patients with H. pylori infection treated with furazolidone, amoxicillin, bismuth, and proton pump inhibitor therapy (January 2015 to December 2015) who received the 13C-urea breath test > 4 wk after treatment were evaluated. Demographic and clinical data including prior H. pylori treatment attempts, medication adherence, alcohol and cigarette consumption during therapy, and treatment-related adverse events were recorded by reviewing medical records and telephone surveys. H. pylori eradication rates for overall and subgroups were evaluated. Multivariate analysis was performed to identify independent predictors of failed H. pylori eradication. RESULTS: Of the 992 patients treated and retested for H. pylori infection, the overall eradication rate was 94.5% [95% confidence interval (CI): 94.1%-95.9%]. H. pylori eradication rate of primary therapy was 95.0% (95%CI: 93.5%-96.5%), while that of rescue therapy was 91.3% (95%CI: 86.8%-95.8%). Among the 859 patients who completed the study protocol, 144 (17%) reported treatment-related adverse events including 24 (3%) leading to premature discontinuation. On multivariate analysis, poor medication adherence [adjusted odds ratio (AOR) = 6.7, 95%CI: 2.8-15.8], two or more previous H. pylori treatments (AOR = 7.4, 95%CI: 2.2-24.9), alcohol consumption during therapy (AOR = 4.4, 95%CI: 1.5-12.3), and possibly smoking during therapy (AOR = 1.9, 95%CI: 0.9-4.3) were associated with failed H. pylori eradication. CONCLUSION: Furazolidone- and amoxicillin-based quadruple therapy for H. pylori infection in an area with a high prevalence of clarithromycin resistance demonstrated high eradication rates as primary and rescue therapies with a favorable safety profile. Patient education targeting abstinence from alcohol during therapy and strict medication adherence may further optimize H. pylori eradication.

Gastric precancerous diseases classification using CNN with a concise model.

Gastric precancerous diseases (GPD) may deteriorate into early gastric cancer if misdiagnosed, so it is important to help doctors recognize GPD accurately and quickly. In this paper, we realize the classification of 3-class GPD, namely, polyp, erosion, and ulcer using convolutional neural networks (CNN) with a concise model called the Gastric Precancerous Disease Network (GPDNet). GPDNet introduces fire modules from SqueezeNet to reduce the model size and parameters about 10 times while improving speed for quick classification. To maintain classification accuracy with fewer parameters, we propose an innovative method called iterative reinforced learning (IRL). After training GPDNet from scratch, we apply IRL to fine-tune the parameters whose values are close to 0, and then we take the modified model as a pretrained model for the next training. The result shows that IRL can improve the accuracy about 9% after 6 iterations. The final classification accuracy of our GPDNet was 88.90%, which is promising for clinical GPD recognition.

Diagnostic accuracy of DNA methylation in detection of gastric cancer: a meta-analysis.

Emerging studies demonstrate the diagnostic utility of DNA methylation-based blood test for gastric cancer. The aim of the meta-analysis is to evaluate the accuracy of blood DNA methylation markers for detecting patients with gastric cancer. A systematic literature search to November 2016 that evaluated DNA methylation markers utilizing blood specimen to detect gastric cancer were selected to derive pooled sensitivities and specificities. 32 studies including 4,172 patients (gastric cancer (N = 2,098), control (N = 2,074)) met the study criteria. Overall sensitivity of DNA methylation-based blood test for detecting gastric cancer was 57% (95% CI 50-63%); specificity was 97% (95% CI 95-98%). Among patients who received plasma-based testing, sensitivity was 71% (95% CI 59-81%); specificity was 89% (95% CI 78-94%). Among patients who received serum-based testing, sensitivity was 50% (95% CI 43-58%); specificity was 98% (95% CI 96-99%). Using multiple methylated genes had sensitivity of 76% (95% CI 64-84%); specificity of 85% (95% CI 65-95%). DNA methylation test had sensitivity of 55% (95% CI 47-64%) and specificity of 96% (95% CI 92-98%) for detecting TNM stage I+II gastric cancer. In conclusion, blood-based DNA methylation test had high specificity but modest sensitivity for detecting gastric cancer. Evaluating multiple methylated genes or using plasma sample may improve the diagnostic sensitivity.