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

Combination of artificial intelligence endoscopic diagnosis and Kimura-Takemoto classification determined by endoscopic experts may effectively evaluate the stratification of gastric atrophy in post-eradication status

Background

Since it is difficult for expert endoscopists to diagnose early gastric cancer in post-eradication status, it may be critical to evaluate the stratification of high-risk groups using the advance of gastric atrophy or intestinal metaplasia. We tried to determine whether the combination of endoscopic artificial intelligence (AI) diagnosis for the evaluation of gastric atrophy could be a useful tool in both pre- and post-eradication status.

Methods

270 Helicobacter pylori-positive outpatients (Study I) were enrolled and Study II was planned to compare patients (n = 72) with pre-eradication therapy with post-eradication therapy. Assessment of endoscopic appearance was evaluated by the Kyoto classification and Kimura-Takemoto classification. The trained neural network generated a continuous number between 0 and 1 for gastric atrophy.

Results

There were significant associations between the severity of gastric atrophy determined by AI endoscopic diagnosis and not having a regular arrangement of collecting venules in angle, visibility of vascular pattern, and mucus using Kyoto classification in H. pylori-positive gastritis. There were significant differences (p = 0.037 and p = 0.014) in the severity of gastric atrophy between the high-risk group and low-risk group based on the combination of Kimura-Takemoto classification and endoscopic AI diagnosis in pre- and post-eradication status. The area under the curve values of the severity of gastric atrophy (0.674) determined by the combination of Kimura-Takemoto classification and gastric atrophy determined by AI diagnosis was higher than that determined by Kimura-Takemoto classification alone in post-eradication status.

Conclusion

A combination of gastric atrophy determined by AI endoscopic diagnosis and Kimura-Takemoto classification may be a useful tool for the prediction of high-risk groups in post-eradication status.

Artificial intelligence model on images of functional dyspepsia

BACKGROUND

Recently, it has been suggested that the duodenum may be the pathological locus of functional dyspepsia (FD). Additionally, an image-based artificial intelligence (AI) model was shown to discriminate colonoscopy images of irritable bowel syndrome from healthy subjects with an area under the curve (AUC) 0.95.

AIM

To evaluate an AI model to distinguish duodenal images of FD patients from healthy subjects.

METHODS

Duodenal images were collected from hospital records and labeled as "functional dyspepsia" or non-FD in electronic medical records. Helicobacter pylori (HP) infection status was obtained from the Japan Endoscopy Database. Google Cloud AutoML Vision was used to classify four groups: FD/HP current infection (n = 32), FD/HP uninfected (n = 35), non-FD/HP current infection (n = 39), and non-FD/HP uninfected (n = 33). Patients with organic diseases (e.g., cancer, ulcer, postoperative abdomen, reflux) and narrow-band or dye-spread images were excluded. Sensitivity, specificity, and AUC were calculated.

RESULTS

In total, 484 images were randomly selected for FD/HP current infection, FD/HP uninfected, non-FD/current infection, and non-FD/HP uninfected. The overall AUC for the four groups was 0.47. The individual AUC values were as follows: FD/HP current infection (0.20), FD/HP uninfected (0.35), non-FD/current infection (0.46), and non-FD/HP uninfected (0.74). Next, using the same images, we constructed models to determine the presence or absence of FD in the HP-infected or uninfected patients. The model exhibited a sensitivity of 58.3%, specificity of 100%, positive predictive value of 100%, negative predictive value of 77.3%, and an AUC of 0.85 in HP uninfected patients.

CONCLUSION

We developed an image-based AI model to distinguish duodenal images of FD from healthy subjects, showing higher accuracy in HP-uninfected patients. These findings suggest AI-assisted endoscopic diagnosis of FD may be feasible.

Prevalence of Helicobacter pylori infection in the general population in Wuzhou, China: a cross-sectional study

BACKGROUND

Helicobacter pylori (H. pylori) is a global infectious carcinogen. We aimed to evaluate the prevalence of H. pylori infection in the healthcare-utilizing population undergoing physical examinations at a tertiary hospital in Guangxi, China. Furthermore, gastroscopies were performed on selected participants to scrutinize the endoscopic features of H. pylori infection among asymptomatic individuals.

SUBJECTS AND METHODS

This study involved 22,769 participants who underwent H. pylori antibody serology screenings at the hospital between 2020 and 2023. The 14C-urea breath test was employed to determine the current H. pylori infection status of 19,307 individuals. Concurrently, 293 participants underwent gastroscopy to evaluate their endoscopic mucosal abnormalities. The risk correlation and predictive value of endoscopic mucosal traits, Hp infection status, and 14C-urea breath test(14C-UBT) outcomes were investigated in subsequent analyses.

RESULTS

Serum Ure, CagA, and VacA antibodies were detected in 43.3%, 27.4%, and 23.6% of the 22,769 subjects that were screened, respectively. The population exhibited 27.5% and 17.2% positive rates for immune type I and II, respectively. Male participants exhibited lower positive rates of serum antibodies than females. The positive rates and predictive risks of the antibodies increased with age, and the highest positive rates were observed in the 50-60 age subgroup. Based on the outcomes of serological diagnostic techniques, it was observed that the positive rate was significantly higher compared to that of non-serological diagnostic methods, specifically the 14C-UBT results (43.3% versus 14.97%). Among the other cohort (n = 19,307), the 14C-UBT revealed a 14.97% positivity rate correlated with age. The 293 individuals who underwent gastroscopy from 14C-UBT Cohort were found to be at an increased risk of a positive breath test if they exhibited duodenal bulb inflammation, diffuse redness, or mucosal edema during the gastroscopy visit.

CONCLUSION

The prevalence of Helicobacter pylori infection is high among the population of Wuzhou, Guangxi, China. Type I H. pylori strains, distinguished by their enhanced virulence, are predominant in this region. In the framework of this population-based study, age has been identified as an independent risk factor for H. pylori infection. Additionally, distinct mucosal manifestations observed during gastroscopy can facilitate the identification of healthcare-utilizing individuals with active H. pylori infections.

Novel endoscopic techniques for the diagnosis of gastric Helicobacter pylori infection: a systematic review and network meta-analysis

Objective

This study aimed to conduct a network meta-analysis to compare the diagnostic efficacy of diverse novel endoscopic techniques for detecting gastric Helicobacter pylori infection.

Methods

From inception to August 2023, literature was systematically searched across Pubmed, Embase, and Web of Science databases. Cochrane's risk of bias tool assessed the methodological quality of the included studies. Data analysis was conducted using the R software, employing a ranking chart to determine the most effective diagnostic method comprehensively. Convergence analysis was performed to assess the stability of the results.

Results

The study encompassed 36 articles comprising 54 observational studies, investigating 14 novel endoscopic techniques and involving 7,230 patients diagnosed with gastric H. pylori infection. Compared with the gold standard, the comprehensive network meta-analysis revealed the superior diagnostic performance of two new endoscopic techniques, Magnifying blue laser imaging endoscopy (M-BLI) and high-definition magnifying endoscopy with i-scan (M-I-SCAN). Specifically, M-BLI demonstrated the highest ranking in both sensitivity (SE) and positive predictive value (PPV), ranking second in negative predictive value (NPV) and fourth in specificity (SP). M-I-SCAN secured the top position in NPV, third in SE and SP, and fifth in PPV.

Conclusion

After thoroughly analyzing the ranking chart, we conclude that M-BLI and M-I-SCAN stand out as the most suitable new endoscopic techniques for diagnosing gastric H. pylori infection.

Systematic review registration

https://inplasy.com/inplasy-2023-11-0051/, identifier INPLASY2023110051.

Artificial intelligence for gastric cancer in endoscopy: From diagnostic reasoning to market

Recognition of gastric conditions during endoscopy exams, including gastric cancer, usually requires specialized training and a long learning curve. Besides that, the interobserver variability is frequently high due to the different morphological characteristics of the lesions and grades of mucosal inflammation. In this sense, artificial intelligence tools based on deep learning models have been developed to support physicians to detect, classify, and predict gastric lesions more efficiently. Even though a growing number of studies exists in the literature, there are multiple challenges to bring a model to practice in this field, such as the need for more robust validation studies and regulatory hurdles. Therefore, the aim of this review is to provide a comprehensive assessment of the current use of artificial intelligence applied to endoscopic imaging to evaluate gastric precancerous and cancerous lesions and the barriers to widespread implementation of this technology in clinical routine.

Applications of artificial intelligence in gastroscopy: a narrative review

Gastroscopy, a critical tool for the diagnosis of upper gastrointestinal diseases, has recently incorporated artificial intelligence (AI) technology to alleviate the challenges involved in endoscopic diagnosis of some lesions, thereby enhancing diagnostic accuracy. This narrative review covers the current status of research concerning various applications of AI technology to gastroscopy, then discusses future research directions. By providing this review, we hope to promote the integration of gastroscopy and AI technology, with long-term clinical applications that can assist patients.