Cardiac arrest & resuscitation
Eye movement detection using electrooculography and machine learning in cardiac arrest patients
Authors' conclusion
Automated eye movement detection from EOG is highly sensitive in CA patients.
Study context
- Population
- Post-CA patients with standard-of-care EEG/electrooculography (EOG) monitoring in the ICU, 2020 to 2023
- Participants
- 72 eligible patients
- Exposure
- Training vs Test
- Trainingn = 48
- Testn = 24
- Outcome
- Performance of a machine learning algorithm detecting eye movement from EOG (AUC, sensitivity, specificity) on the test set
Methodological detailssingle-centre, machine learning algorithm development, Mean age 56.9 years; 46 (63.9%) female
- Single-centre
- Machine learning algorithm development
- Mean age 56.9 years; 46 (63.9%) female
Main finding
As reported in the abstract
Eye movement detection from EOG
| Group | Sensitivity | Specificity | AUC |
|---|---|---|---|
| Final algorithm | 94.0% | 82.0% | 94.2% |
Final algorithm
Sensitivity94.0%
Specificity82.0%
AUC94.2%
Observational data: associations, not effects.
Further findings
Survival and command following
- Training: survived
- 35 (72.9%)
- Training: followed commands
- 32 (66.7%)
- Test: survived
- 16 (66.7%)
- Test: followed commands
- 7 (29.2%)
Original publication
Eye movement detection using electrooculography and machine learning in cardiac arrest patients. Resuscitation. Published 24 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →