ChatGPT and Patient Safety in the Nuclear Medicine Thyroid Outpatient Clinic

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00037313

Enrollment

Registered

2025-07-01

Start date

2025-07-01

Completion date

Unknown

Last updated

2025-10-06

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

Conditions

E00-E07

Interventions

Group 1: Retrospective, single-arm analysis as part of basic research on pattern recognition and analysis using AI.

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: • Study conducted in the thyroid outpatient clinic of the Department of Nuclear Medicine, Aachen • Inclusion in one of six subgroups (1. Normal finding, 2. Unifocal autonomy, 3. Multifocal autonomy, 4. Disseminated autonomy, 5. Graves’ disease, 6. Hypofunctioning nodule) • Availability of complete imaging, laboratory, and report data

Exclusion criteria

Exclusion criteria: • Insufficient image quality • Incomplete datasets (missing laboratory values, reports, or imaging data)

Design outcomes

Primary

Measure	Time frame
Accuracy of ChatGPT’s Analysis with Respect to Imaging Data, Laboratory Values, and Ultrasound Report Descriptions (Hypothesis: ChatGPT does not adequately recognize nuclear medicine diagnoses in thyroid diagnostics.)	—

Secondary

Measure	Time frame
Implications for Counseling, Communication, and Patient Safety for Patients Informed by ChatGPT Hypothesis Generation for Further AI-Based Studies	—

Countries

Germany

Contacts

Public ContactJonas Ihm

Klinik für Nuklearmedizin

jihm@ukaachen.de02418088735

Outcome results

None listed

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