Evaluation of the use of Large Language Models for diagnosis of psychiatric disorders

Evaluation of the use of Large Language Models for diagnosis of psychiatric disorders - PSY-LLM

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00037071

Enrollment

Registered

2025-08-08

Start date

2025-09-17

Completion date

Unknown

Last updated

2025-11-24

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

Conditions

F31

Interventions

Group 1: In the observation group, structured psychiatric interviews with patients with affective disorders are conducted and anonymized. The anonymized interviews are analyzed both by psychiatric exp

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: - Age = 18 years - Written informed consent - Participation in a diagnostic interview to clarify bipolar disorder or depression in Charité outpatient clinic - Control group: no psychiatric diagnosis

Exclusion criteria

Exclusion criteria: - Language barriers - Not able to give consent

Design outcomes

Primary

Measure	Time frame
Agreement between the LLMs and the experts (precision, recall, F1 score)	—

Secondary

Measure	Time frame
Expert assessment of the quality of the summaries generated by LLMs	—

Countries

Germany

Contacts

Public ContactStefanie Schreiter

Charité - Universitätsmedizin Berlin

bipolar@charite.de+4930450517148

Outcome results

None listed

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