Predicting events during the treatment of psychiatric patients by applying methods of Machine Learning and NLP (Natural Language Processing) on electronic clinical routine health data

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00032383

Enrollment

5000

Registered

2023-08-03

Start date

2024-05-01

Completion date

Unknown

Last updated

2025-04-07

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

Conditions

All diagnoses from spectrum F of the ICD 10.

Interventions

Group 1: psychiatric inpatients In addition to non-response, there is a whole range of complications during inpatient treatment, such as suicide and suicide attempts, discontinuation of therapy, self

Nurses' Global Assessment of Suicide Risk (NGASR) (Almvik & Woods, 1999

Cutcliffe & Barker, 2004)). For evaluation, we want to include the following data from the electronic health records: anamnesis/interview on admission, psychopathology on admission, the admission and

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: psychiatric inpatients in the Department of Psychiatry and Psychotherapy, University Hoslital Mainz and Parkklinik Schlangenbad with elecronic health records

Exclusion criteria

Exclusion criteria: patients for maintanance ECT age under 18 years no electronic health record available

Design outcomes

Primary

Measure	Time frame
length of stay	—

Secondary

Measure	Time frame
critical / adverse events	—

Countries

Germany

Contacts

Public ContactXenia Kersting

Universitätsmedizin Mainz, Klinik für Psychiatrie und Psychotherapie

xenia.kersting@unimedizin-mainz.de+496131172520

Outcome results

None listed

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