Tokyo, Oct. 16 -- UMIN Clinical Trials Registry (UMIN-CTR) received information related to the study (UMIN000059415) titled 'Prospective Observational Study on the Clinical Utility of AI-based Facial Detection in the Pediatric Intensive Care Unit' on Oct. 16.
Study Type:
Observational
Primary Sponsor:
Institute - Hokkaido Child Health and Rehabilitation Center
Condition:
Condition - All pediatric critical illnesses requiring intensive care
Classification by malignancy - Others
Genomic information - NO
Objective:
Narrative objectives1 - This study aims to evaluate and compare the facial detection performance of the Google Vision API and a custom convolutional neural network (CNN) model using images captured in pediatric intensive care settings.
Detection success rates and bounding box localization accuracy (e.g., IoU) will be compared, considering real-world clinical conditions such as lighting variability, patient positioning, and presence of medical devices. This will inform future development of real-time AI applications in clinical monitoring.
Basic objectives2 - Efficacy
Eligibility:
Age-lower limit - 1
days-old
Gender - Male and Female
Key inclusion criteria - All photo of patients in PICU are included
Key exclusion criteria - none
Target Size - 400
Recruitment Status:
Recruitment status - Open public recruiting
Date of protocol fixation - 2025 Year 08 Month 26 Day
Date of IRB - 2025 Year 08 Month 26 Day
Anticipated trial start date - 2025 Year 09 Month 01 Day
Last follow-up date - 2025 Year 11 Month 01 Day
To know more, visit https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000067953
Disclaimer: Curated by HT Syndication.
