A novel Artificial Intelligence-assisted white light endoscopic model in the diagnosis of cardia atrophy: a
Fangmei An1, Yao Shen1, Shuping Si1
1Department of Gastroenterology, The Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical University, National Clinical Research Center for Digestive Diseases (Xi' an) Jiangsu Branch, Wuxi, China.
Insights
An artificial intelligence (AI) system effectively diagnoses cardia atrophy, outperforming senior endoscopists. This AI tool improves diagnostic accuracy and can guide endoscopic procedures for better patient outcomes.
Area of Science:
- Gastroenterology
- Medical Imaging
- Artificial Intelligence
Background:
- Cardia atrophy is closely linked to gastric cancer, posing diagnostic challenges during endoscopy.
- Accurate identification of cardia atrophy is crucial for timely intervention and cancer prevention.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI)-assisted diagnostic model for cardia atrophy.
- To compare the diagnostic performance of the AI system against experienced endoscopists.
Main Methods:
- A multicenter prospective study involved 895 patients for model development and validation.
- Internal and external test sets (220 and 354 patients, respectively) were used for performance evaluation.
- The AI system's diagnoses were compared with those of senior and junior endoscopists.
Main Results:
- The AI system achieved high accuracy (92.7% internal, 91.8% external) and AUC (0.967 internal, 0.953 external) in diagnosing cardia atrophy.
- AI demonstrated superior sensitivity, specificity, and predictive values compared to senior endoscopists.
- Heatmaps indicated strong consistency between AI diagnoses and expert endoscopist assessments.
Conclusions:
- The developed AI-assisted system significantly outperforms senior endoscopists in identifying cardia atrophy.
- This AI tool can enhance endoscopic judgment and guide targeted biopsies for cardia atrophy, improving diagnostic precision.
Background And Aims:
Atrophy extends beyond the cardia is open atrophy and closely related to gastric cancer. However, there is difficulty in determining cardia atrophy under endoscopy.
Methods:
This is multicenter prospective study, a total of 895 patients were assigned to the training and validation sets to establish a cardia atrophy diagnostic model. A total of 220 patients were included in the internal test set. Additionally, a total of 354 patients were included in the external test set. In the internal and external test sets, three senior and three junior endoscopists made online diagnoses, comparing the performance differences to the artificial intelligence (AI)-assisted system.
Results:
In the internal test dataset, the accuracy, sensitivity, and specificity of the AI-assisted cardia atrophy diagnostic system were 0.927, 0.941, and 0.919, respectively, with a positivev predictive value (PPV) of 0.878, negative predictive value (NPV) of 0.962, and area under the curve (AUC) of 0.967. In the external test dataset, the accuracy, sensitivity, and specificity were 0.918, 0.894, and 0.931 respectively, with a PPV of 0.874, NPV of 0.943, and AUC of 0.953. Furthermore, it was found that the diagnosis accuracy, sensitivity, specificity, PPV, and NPV of the AI-assisted system were all higher than those of senior endoscopists. The receiver operating characteristic curve area (AUC) of AI-assisted system was 0.967 and 0.953 in the internal and external test sets, respectively. Heat map showed a high consistency between the AI-system and endoscopists.
Conclusion:
Our newly developed AI-assisted system shows superior performance in identifying cardia atrophy compared to senior endoscopists, and can be used to guide endoscopic judgment and targeted biopsies for cardia atrophy.
