Predicting Episodes of Hypovigilance in Intensive Care Units Using Routine Physiological Parameters and Artificial Intelligence: Derivation Study
All classifiers produced precision and recall values that show potential for further development, with slightly different yet comparable performances in classifying hypovigilant episodes. Machine learning algorithms designed to detect hypovigilance have the potential to support early detection of hypoactive delirium in patients in the ICU.
Authors
- Patrick Archambault (ORCID: https://orcid.org/0000-0002-5090-6439)
- Simon Duchesne (ORCID: https://orcid.org/0000-0002-6326-0745)
- Philippe Després (ORCID: https://orcid.org/0000-0002-4163-7353)
- Raphaëlle Giguère (ORCID: https://orcid.org/0009-0005-2390-6299)
- Tanya S. Paul (ORCID: https://orcid.org/0009-0004-0632-8231)
- Alexandre Marois (ORCID: https://orcid.org/0000-0002-4127-4134)
- William Witteman (ORCID: https://orcid.org/0009-0000-6116-1543)
- Monia Noël-Hunter (ORCID: https://orcid.org/0009-0007-9144-4852)
- Victor Niaussat (ORCID: https://orcid.org/0009-0006-8172-9515)
Institutions
- Thales (Canada) (CA)
- Centre intégré de santé et de services sociaux de Chaudière-Appalaches (CA)
- Université Laval (CA)
- École Centrale de Lille (FR)
Publication Details
- Journal
- JMIR AI
- Published
- 2025-05-23
- DOI
- https://doi.org/10.2196/60885
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00