The aim of the planned study is to conduct a systematic artificial intelligence (AI)-based analysis of an anonymised dataset using data routinely documented in the patient data management system of the Emergency Department (PDMS, COPRA), together with ICD-10 discharge diagnoses, including primary and secondary diagnoses, recorded in the hospital information system (HIS, MEDICO), and to validate a corresponding algorithm.
Conditions
Interventions
Group 1: Inclusion criteria (AI geneation)
The inclusion criterion is treatment as a patient in the Emergency Department of University Hospital Düsseldorf during the period from 1 January 2022 to 31 D
Sponsors
Universitätsklinkum Düsseldorf
Eligibility
Sex/Gender
All
Age
18 Years to No maximum
Inclusion criteria
Inclusion criteria: The inclusion criterion is treatment as a patient in the Emergency Department of University Hospital Düsseldorf during the period from 1 January 2022 to 28 February 2025. Retrospectively, all patients assigned to the non-traumatological departmental codes INNA, INER, INGI, INHO, INKP, INNR, INRH, and INSE will be included.
Exclusion criteria
Exclusion criteria: Data loss, e.g. due to missing documentation.
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Agreement between the primary admission diagnosis proposed by the trained AI algorithm and the actual hospital discharge diagnosis. | — |
Secondary
| Measure | Time frame |
|---|---|
| Agreement between the radiological imaging studies proposed by the algorithm — including conventional radiography and computed tomography (CT) — and the imaging studies actually performed as well as those recommended by clinical guidelines. Agreement between the laboratory parameters proposed by the AI algorithm and the laboratory parameters actually obtained as well as those recommended by clinical guidelines. | — |
Countries
Germany
Contacts
Public ContactHans-Michael Kauerz
Universitätsklinikum Düsseldorf
Outcome results
None listed