Artificial Intelligence, Gastric Cancer, Tongue
Conditions
Keywords
Artificial Intelligence, tongue, gastric cancer
Brief summary
This study combines artificial intelligence with tongue images, by collating and collecting tongue images and diagnostic and pathological results of gastroscopic diseases, mining and analysing the correlation between tongue images and OLGA, OLGIM stages, Correa sequences and constructing prediction models, to deeply investigate the relationship between tongue images and precancerous diseases, precancerous lesions and gastric cancer.
Detailed description
Firstly, tongue pictures and patient information will be collected after the patient signed an informed consent form. Secondly, after the patient undergoes gastroscopy, patient gastroscopy reports and pathology reports will be obtained. Thirdly, the investigator will assess the patient's gastroscopy report for the Correa sequence of gastric cancer with OLGA and OLGIM staging. Finally, the patient's tongue image, information and gastric cancer cascade response are matched to construct an artificial intelligence model and assess the quality of the model.
Interventions
None listed
Sponsors
Shandong University
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
40 Years to 80 Years
Healthy volunteers
Yes
Inclusion criteria
* Patients between 40 and 80 years of age who are scheduled for gastroscopy. * Patients all gave their informed consent and signed the informed consent form.
Exclusion criteria
* Persons with severe cardiac, cerebral, pulmonary or renal dysfunction or psychiatric disorders who are unable to participate in gastroscopy. * Patients with previous surgical procedures on the gastrointestinal tract. * Patients taking bismuth or other staining drugs.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity | 3 years | Sensitivity of artificial intelligence models Sensitivity = number of true positives / (number of true positives + number of false negatives) \* 100%. |
| Specificity | 3 years | Specificity of Artificial Intelligence Models Specificity = number of true negatives / (number of true negatives + number of false positives))\*100% |
| Positive predictive values(PPV) | 3 years | Positive predictive values from artificial intelligence models Positive predictive value = true positive / (true positive + false positive)\*100% |
| Negative predictive values(NPV) | 3 years | Negative predictive values for artificial intelligence models Negative predictive value = true negative / (true negative + false negative)\*100% |
| AUC (95% CI) | 3 years | area under the receiver operating characteristic curve (AUC) |
| Accuracy | 3 years | Accuracy of artificial intelligence models Accuracy = (true positives + true negatives) / total number of subjects \* 100% |
Countries
China
Contacts
Primary ContactXiuli Zuo, MD, PhD
Outcome results
None listed