Retrospective data processing of routine flexible endoscopic evaluation of swallowing (FEES) diagnostic data for the purpose of training an artificial intelligence for aspiration detection

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00026822

Enrollment

150

Registered

2022-02-04

Start date

2021-10-28

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

R13 T17

Interventions

Group 1: Video recordings of endoscopic swallowing examinations for training purposes of an artificial intelligence

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: presence of a FEES video with aspiration or without in saliva, porridge or liquids

Exclusion criteria

Exclusion criteria: Vocal cord carcinoma Base of tongue carcinoma anomalous anatomical conditions intubation damage

Design outcomes

Primary

Measure	Time frame
The aim of the study is to find out whether AI-driven detection of aspirations in FEES videos is possible (feasibility). The percentage of correctly classified aspirations and non-aspirations is determined. This is done using the metrics Precision and Recall.	—

Secondary

Measure	Time frame
Is there a difference in recognition by the AI between the different bolus types (saliva, liquid, pasty) in terms of the Precision and Recall metrics?	—

Countries

Germany

Contacts

Public ContactJürgen Konradi

Universitätsmedizin der Johannes-Gutenberg-Universität Mainz, Interprofessionelles Studienzentrum für Bewegungsforschung

juergen.konradi@unimedizin-mainz.de06131172362

Outcome results

None listed

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