AI-based analysis of patient rotation in chest X-ray images – Evaluation of an algorithm for fully automated radiological image assessment

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00037781

Enrollment

8000

Registered

2025-12-09

Start date

2025-12-01

Completion date

Unknown

Last updated

2026-01-12

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Thoracic X-ray images of varying image quality in p.a. projection, independent of patient age, sex, and underlying findings.

Interventions

Group 1: This study is a retrospective analysis of chest X-ray images in p.a. projection acquired between 2016 and 2025. The aim is to evaluate AI-based assessment of patient rotation in order to stan

analyses are performed exclusively on anonymized imaging data.

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: Thoracic X-ray images of varying image quality in p.a. projection, independent of patient age, sex, and underlying findings.

Exclusion criteria

Exclusion criteria: None

Design outcomes

Primary

Measure	Time frame
Agreement between the AI-based assessment of patient rotation and the evaluation by human experts.	—

Secondary

Measure	Time frame
Distribution of image quality scores in the overall cohort, interrater reliability of radiologists, and comparison between human ratings and AI-generated results.	—

Countries

Germany

Contacts

Public ContactBastian Sabel

Klinikum der Universität München, Klinik und Poliklinik für Radiologie

Bastian.Sabel@med.uni-muenchen.de089 4400 73620

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Feb 4, 2026