Data from: Artificial intelligence model for detecting duodenal endoscopic changes on images of functional dyspepsia
Data files
Apr 14, 2025 version files 47.20 MB
-
FDHP.zip
15.22 MB
-
nonFDHPpositive_(2).zip
31.98 MB
-
README.md
884 B
Abstract
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.
https://doi.org/10.5061/dryad.pvmcvdntc
We will post 70 duodenal images from 32 patients who were treated for Functional Dyspepsia (FD) and had Helicobacter pylori infection, and 141 images from 39 asymptomatic individuals with Helicobacter pylori infection. Using the presence or absence of symptoms as training data, we constructed an image AI to distinguish between the two groups.
Description of the data and file structure
In the FDHP box, there are duodenal images in jpg format of patients who were treated for Functional Dyspepsia (FD) and had Helicobacter pylori infection. In the nonFDHPpositive box, there are duodenal images in jpg format of asymptomatic individuals with Helicobacter pylori infection.