Ying JX, Yan SY, Fu XY, Zhou YJ, Zhou JJ, Yang Y, Zhou XB, Wang ZZ, Li SW, Fang LN, Mao XL. Artificial intelligence-assisted endoscopists improve the detection rate of high-risk gastric lesions: A propensity score-matched retrospective study. World J Gastroenterol 2026; 32(21): 117299 [DOI: 10.3748/wjg.v32.i21.117299]
Reader's ID:
08940508
Submitted on:
May 29, 2026, 15:45
Reader Expertise:
Reader’s expertise on the topic of the manuscript
Conflicts-of-Interest Statement:
Does the reader have a conflict of interest?
Reader Comment Standards for Published Articles:
1 Title
Does the title reflect the main subject/hypothesis of the manuscript?
2 Abstract
Does the abstract summarize and reflect the work described in the manuscript?
3 Key Words
Do the key words reflect the focus of the manuscript?
4 Background
Does the manuscript adequately describe the background, present status and significance of the study?
5 Methods
Does the manuscript describe methods (e.g., experiments, data analysis, surveys, and clinical trials, etc.) in adequate detail?
6 Results
Are the research objectives achieved by the experiments used in this study?
Has the study made meaningful contributions towards research progress in this field?
7 Discussion
Does the manuscript interpret the findings adequately and appropriately, highlighting the key points concisely, clearly and logically?
Are the findings and their applicability/relevance to the literature stated in a clear and definite manner?
Is the Discussion accurate and does it discuss the paper’s scientific significance and/or relevance to clinical practice sufficiently?
8 Illustrations and Tables
Are the figures, diagrams and tables sufficient, good quality and appropriately illustrative of the paper contents?
Do figures require labeling with arrows, asterisks, etc., or better legends?
9 Biostatistics
Does the manuscript meet the requirements of biostatistics?
10 Units
Does the manuscript meet the requirements of use of SI units?
11 References
Does the manuscript appropriately cite the latest, important and authoritative references in the Introduction and Discussion sections?
Does the author self-cite, omit, incorrectly cite and/or over-cite references?
12 Quality of manuscript organization and presentation
Is the manuscript concisely and coherently organized and presented?
Are the style, language and grammar accurate and appropriate?
13 Ethics statements
For all manuscripts involving human studies and/or animal experiments, author(s) must submit the related formal ethics documents that were reviewed and approved by their local ethical review committee. Did the manuscript meet the requirements of ethics?
Scientific Quality:
The overall quality of the manuscript, based on the above-listed criteria, should be evaluated and classified according to the following five categories
Language Quality:
Language quality (style, grammar, and spelling) should be evaluated and classified according to the following five categories.
Reader Comments:
As a pathologist, I find this study directly addresses the familiar disconnect between endoscopic biopsy and surgical resection—a discrepancy rooted in sampling bias rather than diagnostic error. The AI-assisted system compensates for this by guiding targeted biopsies: 95.1% of the detection gain came from precise recognition and localization of subtle lesions, not from simply taking more biopsies.
The rigorous double-reading with blinded pathology review strongly supports the findings. Grouping low-grade, high-grade intraepithelial neoplasia, and early gastric cancer as endpoints is clinically pragmatic, and the marked AI advantage at blind spots like the gastric angle aligns with everyday practice.
To deepen the evidence, future work could add positive predictive value, compare biopsy-to-surgery upgrade rates between groups, and characterize the pathology of false-positive AI detections (e.g., reactive changes). Correlating endoscopic morphology with histopathology would further transform AI from a detection tool into a diagnostic aid. Overall, this high-quality study offers a promising means to reduce sampling error and bridge the gap between endoscopic detection and pathological confirmation.
Reader's ID:
08518582
Submitted on:
May 27, 2026, 03:51
Reader Expertise:
Reader’s expertise on the topic of the manuscript
Conflicts-of-Interest Statement:
Does the reader have a conflict of interest?
Reader Comment Standards for Published Articles:
1 Title
Does the title reflect the main subject/hypothesis of the manuscript?
2 Abstract
Does the abstract summarize and reflect the work described in the manuscript?
3 Key Words
Do the key words reflect the focus of the manuscript?
4 Background
Does the manuscript adequately describe the background, present status and significance of the study?
5 Methods
Does the manuscript describe methods (e.g., experiments, data analysis, surveys, and clinical trials, etc.) in adequate detail?
6 Results
Are the research objectives achieved by the experiments used in this study?
Has the study made meaningful contributions towards research progress in this field?
7 Discussion
Does the manuscript interpret the findings adequately and appropriately, highlighting the key points concisely, clearly and logically?
Are the findings and their applicability/relevance to the literature stated in a clear and definite manner?
Is the Discussion accurate and does it discuss the paper’s scientific significance and/or relevance to clinical practice sufficiently?
8 Illustrations and Tables
Are the figures, diagrams and tables sufficient, good quality and appropriately illustrative of the paper contents?
Do figures require labeling with arrows, asterisks, etc., or better legends?
9 Biostatistics
Does the manuscript meet the requirements of biostatistics?
10 Units
Does the manuscript meet the requirements of use of SI units?
11 References
Does the manuscript appropriately cite the latest, important and authoritative references in the Introduction and Discussion sections?
Does the author self-cite, omit, incorrectly cite and/or over-cite references?
12 Quality of manuscript organization and presentation
Is the manuscript concisely and coherently organized and presented?
Are the style, language and grammar accurate and appropriate?
13 Ethics statements
For all manuscripts involving human studies and/or animal experiments, author(s) must submit the related formal ethics documents that were reviewed and approved by their local ethical review committee. Did the manuscript meet the requirements of ethics?
Scientific Quality:
The overall quality of the manuscript, based on the above-listed criteria, should be evaluated and classified according to the following five categories
Language Quality:
Language quality (style, grammar, and spelling) should be evaluated and classified according to the following five categories.
Reader Comments:
This retrospective study evaluates the real-world clinical performance of the deep learning-based ENDOANGEL system in detecting high-risk gastric lesions (HrGLs), demonstrating high readiness for academic publication. Utilizing a massive, propensity score-matched cohort of 15,528 patients to effectively control for major confounding variables, the authors convincingly establish that AI integration nearly doubles the HrGL detection rate (0.94% vs. 0.48%) while providing critical mechanistic validation through causal mediation analysis, proving that this diagnostic gain stems directly from AI-driven image recognition rather than a mere increase in blind biopsies. As an unwearied "second observer," the system holds extensive application prospects for mitigating diagnostic subjectivity, reducing early gastric cancer miss rates, and stabilizing quality control across lower-tier or high-workload endoscopic centers. Moving forward, while future development trends will naturally pivot toward multi-center video-stream integration and diverse ethnic cohort validation, the immediate clinical hurdles that must be surmounted include bridging the performance-gain variance observed across different endoscopist seniority levels, enhancing algorithmic robustness against real-world artifacts like gastric mucus and motion blur, and perfecting low-latency, seamless hardware-software integration.