Brief summary highlighting the study methology. a) AI Tool Development and Pediatric Repurposing: The AI tool was originally trained and validated using a large dataset of adult chest radiographs.

<p>For pediatric validation, the tool was retrospectively tested on 958 pediatric chest radiographs (CXR) from children aged 2–14 years. <b>b) Diagnostic Performance Analysis:</b> The AI tool’s diagnostic performance in children was assessed using vendor-recommended thresholds, str...

Full description

Saved in:

Bibliographic Details
Main Author:	Prerana Agarwal (21781515) (author)
Other Authors:	Alexander Rau (11297538) (author), Helen Ngo (7296959) (author), Ambika Seth (21781518) (author), Fabian Bamberg (394751) (author), Elmar Kotter (3279198) (author), Jakob Weiss (4225828) (author)
Published:	2025
Subjects:	Medicine Molecular Biology Sociology Developmental Biology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified yet dedicated solutions support radiological workflows specialized pediatric radiologists pediatric chest x original reports validated optimized thresholds identified mediastinal widening due lunit insight cxr dedicated reading session chest radiograph interpretation 92 &# 8211 9 %] demonstrated 2 &# 8722 continuous ai output commercially available ai 7 &# 8211 significantly higher performance 94 &# 8211 0 &# 8722 repurposing existing ai commercial tool developed adults </ p 7 vs tool developed high performance diagnostic performance xlink "> tool showed stratified analysis second readings relevant findings reference standard ray diagnosis pleural effusion largely unavailable discordant findings deep learning constantly increasing certified radiologist adult threshold adult application 200 radiographs
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	<p>For pediatric validation, the tool was retrospectively tested on 958 pediatric chest radiographs (CXR) from children aged 2–14 years. <b>b) Diagnostic Performance Analysis:</b> The AI tool’s diagnostic performance in children was assessed using vendor-recommended thresholds, stratified by age groups (2–6 and 7–14 years), and optimized pediatric-specific thresholds.</p>

Brief summary highlighting the study methology. a) AI Tool Development and Pediatric Repurposing: The AI tool was originally trained and validated using a large dataset of adult chest radiographs.

Similar Items