SmartAlert: Machine learning-based patient-ventilator asynchrony detection system in intensive care units
We developed and internally validated SmartAlert, an automated system that detects PVAs, classifies severity, and alerts clinicians in real time. Its potential to reduce alarm fatigue, optimize ventilator settings, and improve patient outcomes remains to be tested in clinical trials.
Authors
- Miroslav Macík (ORCID: https://orcid.org/0000-0001-6312-747X)
- Jan Kubr
- Eliška Niebauerová
- Jaroslav Pažout
- Václav Zvoníček
- Petr Waldauf (ORCID: https://orcid.org/0000-0003-4668-5837)
- Jan Jirman
- Jaromír Mikeš (ORCID: https://orcid.org/0000-0002-9941-7855)
- František Duška (ORCID: https://orcid.org/0000-0003-1559-4078)
- Jakub Vaněk (ORCID: https://orcid.org/0000-0003-2833-1736)
- Milan Němý (ORCID: https://orcid.org/0000-0002-4870-1354)
- Robert Babuška (ORCID: https://orcid.org/0000-0001-9578-8598)
- Lenka Vysloužilová (ORCID: https://orcid.org/0000-0002-5722-6671)
- Michal Štajnrt
- Michal Pech
Institutions
- Charles University (CZ)
- Institute of Endocrinology (CZ)
- University Hospital Kralovske Vinohrady (CZ)
- Czech Technical University in Prague (CZ)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2025-06-21
- DOI
- https://doi.org/10.1016/j.cmpb.2025.108927
- Citations
- 1
- Primary Topic
- Healthcare Technology and Patient Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 2.01
Funders
- European Commission
- Ministerstvo Školství, Mládeže a Tělovýchovy
- Ministerstvo Zdravotnictví Ceské Republiky
- Research Center for Informatics, Czech Technical University in Prague