Training Radiologists to Understand Statistical Pitfalls in AI for Cerebral Aneurysm Detection

Status

Recruiting

Phases

Unknown

Study type

Interventional

Source

DRKS

Registry ID

DRKS00038740

Enrollment

Registered

2025-12-16

Start date

2025-12-15

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

I67.1

Interventions

Group 1: Intervention group: Participants initially review a video tutorial on the Accuracy Paradox. Subsequently, they evaluate 20 TOF-MRA examinations for the presence of cerebral aneurysms with AI

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: Inclusion criteria patients: Retrospective identification of head MRI studies with positive AI aneurysm finding. Age above 18 years. Inclusion criteria radiologists: at least 6 months of experience in reading brain MRI studies.

Exclusion criteria

Exclusion criteria: Exclusion criteria patients: Insufficient MRI image quality

Design outcomes

Primary

Measure	Time frame
Frequency of cases where a false positive AI finding is accepted Frequency of cases where a follow-up examination is recommended for a false positive AI finding	—

Secondary

Measure	Time frame
Frequency of AI-negative lesions rated as aneurysm Level of confidence	—

Countries

Germany

Contacts

Public ContactSu Hwan Kim

Technische Universität München

suhwan.kim@tum.de+498941408834

Outcome results

None listed

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