Large Language Models' (LLM) bias in social anxiety detection

Large Language Models' (LLM) bias in social anxiety detection - KI-S BIAS

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00034903

Enrollment

222

Registered

2024-09-04

Start date

2024-07-18

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

F40.1

Interventions

Group 1: The non-experimental cross-sectional design of the study includes two measurement time points, which exist more due to different enquiry modalities. The measurement time point itself is not a

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: Ability to participate in an interview in German

Exclusion criteria

Exclusion criteria: Cancellation of participation

Design outcomes

Primary

Measure	Time frame
Predictive power of AI (Correlation of AI predicted social anxiety with self-report anxiety)	—

Secondary

Measure	Time frame
Accuracy of AI detection	—

Countries

Germany

Contacts

Public ContactYoussef Shiban

PFH Göttingen

shiban@pfh.de+49 551 54700 477

Outcome results

None listed

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