Unique ID issued by UMIN | UMIN000052643 |
---|---|
Receipt number | R000058283 |
Scientific Title | Clinical performance evaluation of the landmark photo checker in upper gastrointestinal endoscopy |
Date of disclosure of the study information | 2023/12/31 |
Last modified on | 2025/04/29 10:47:23 |
Clinical performance evaluation of the landmark photo checker in upper gastrointestinal endoscopy
Clinical performance evaluation of the landmark photo checker in upper gastrointestinal endoscopy
Clinical performance evaluation of the landmark photo checker in upper gastrointestinal endoscopy
Clinical performance evaluation of the landmark photo checker in upper gastrointestinal endoscopy
Japan |
Non-disabled individuals
Gastroenterology |
Others
NO
To support proper photodocumentation during screening exams, a new artificial Intelligence system (AI) function called the Landmark Photo Checker (LMPC) has been implemented in CAD EYETM (FUJIFILM. Co, Tokyo). This endoscopic AI function facilitates endoscopic photodocumentation by providing a visual indication of completion when appropriate still images of seven anatomical landmarks in the stomach (including the oesophagogastric junction, cardia and fundus, cardia near field view, body greater curvature forward view, body lesser curvature retroflex view, angulus, and pylorus near field view) are captured during the exam. This study is an evaluation of the performance of the LMPC in clinical practice.
Efficacy
Confirmatory
Pragmatic
Not applicable
This study aimed to evaluate the sensitivity of LMPC for these seven landmarks as the primary endpoint.
The secondary evaluation criteria were defined as the specificity and diagnostic accuracy of LMPC.
Interventional
Single arm
Non-randomized
Open -no one is blinded
Uncontrolled
1
Diagnosis
Maneuver |
The participants were randomly assigned to two groups of equal size: the sensitivity verification group and the specificity verification group. In the sensitivity verification group, the endoscopists captured appropriate still images of the seven landmarks during the examination. Conversely, in the specificity verification group, the endoscopists intentionally captured inappropriate images of the seven landmarks. Sensitivity was defined as the proportion of images marked as "good" by LMPC in the sensitivity verification group, while specificity was defined as the proportion of images not marked as "good" by LMPC in the specificity verification group.
28 | years-old | <= |
79 | years-old | >= |
Male and Female
Individuals who participated in this study, including asymptomatic individuals undergoing gastric endoscopy screening and upper gastrointestinal endoscopy recipients for surveillance purposes after Helicobacter pylori eradication, and provided written consent.
Patients after gastric surgery.
140
1st name | Hirotaka |
Middle name | |
Last name | Nakashima |
Foundation for Detection of Early Gastric Carcinoma
Kayabacho clinic
103-0025
2-6-12, Nihombashikayabacho, Chuo Ward, Tokyo, Japan
03-3668-6803
nakashima@soiken.or.jp
1st name | Hirotaka |
Middle name | |
Last name | Nakashima |
Foundation for Detection of Early Gastric Carcinoma
Kayabacho clinic
103-0025
2-6-12, Nihombashikayabacho, Chuo Ward, Tokyo, Japan
03-3668-6803
nakashima@soiken.or.jp
Foundation for Detection of Early Gastric Carcinoma
FUJIFILM Corporation
Profit organization
Foundation for Detection of Early Gastric Carcinoma
2-6-12, Nihombashikayabacho, Chuo Ward, Tokyo, Japan
03-3668-6803
nakashima@soiken.or.jp
NO
2023 | Year | 12 | Month | 31 | Day |
GIE, 2024, 99(6) Supplement: AB7-AB8
Published
GIE, 2024, 99(6) Supplement: AB7-AB8
121
The sensitivity of the landmark was 87.4%. The specificity and accuracy rate, were 75.5% and 81.9%, respectively. The individual sensitivities (%) and specificities (%) for the seven landmarks were as follows: esophagogastric junction, 93.0 and 92.0; cardia near field view, 80.0 and 66.6; cardia and fundus, 75.4 and 41.5; greater curvature of the body, 89.2 and 87.4; lesser curvature of the body, 94.9 and 79.2; angles, 88.1 and 83.3; and pylorus, 93.3 and 88.9.
2023 | Year | 09 | Month | 20 | Day |
The inclusion criteria were (1) Cases where the purpose of the procedure was gastric endoscopic screening or examination, and (2) written informed consent was obtained. The exclusion criteria were (1) a history of gastric surgery and (2) cases with obvious gastrointestinal clinical symptoms.The study involved 121 participants, with an average age of 56.1 years, of whom 67 (55.4%) were male.
All 121 participants were randomly assigned to a sensitivity validation group (66 participants) or a specificity validation group (55 participants). Randomization was performed using the envelope method according to the recommendations in the CONSORT guidelines (the numbered container method). Random allocation messages were pre-generated by a computer program (the python random module) for each examination and placed in sealed envelopes with consecutive registration numbers. The endoscopists opened the envelopes sequentially for each eligible examination and assigned participants to either the sensitivity or specificity validation group based on the message inside the envelope.
None.
This study aimed to evaluate the sensitivity of LMPC for these seven landmarks as the primary endpoint, with specificity and accuracy rate as secondary endpoints.
Completed
2023 | Year | 01 | Month | 15 | Day |
2023 | Year | 02 | Month | 02 | Day |
2023 | Year | 03 | Month | 01 | Day |
2024 | Year | 01 | Month | 31 | Day |
2023 | Year | 10 | Month | 29 | Day |
2025 | Year | 04 | Month | 29 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000058283