Acute cardiac care & 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. Potential applications include using eye movement quantification to evaluate associations with recovery.
Study context
- Population
- Post-CA patients who underwent standard-of-care EEG/electrooculography (EOG) monitoring in the intensive care unit from 2020 to 2023training group 48 · test group 24
- Participants
- 72 eligible patients
- Exposure
- Training group vs test group
- Training groupn = 48
- Test groupn = 24
- Outcome
- Eye movement identification by final algorithm
Main finding
As reported in the abstract
| Group | Sensitivity | Specificity | AUC |
|---|---|---|---|
| Test group | 94.0% | 82.0% | 94.2% |
Test group
Sensitivity94.0%
Specificity82.0%
AUC94.2%
Observational data: associations, not effects.
Further findings
| Outcome | Training group | Test group |
|---|---|---|
| Survival and command following | ||
| Survived | 35 (72.9%) | 16 (66.7%) |
| Followed commands | 32 (66.7%) | 7 (29.2%) |
Baseline characteristics
- Average age
- 56.9 years
- Female
- 46 (63.9%)
Original publication
Eye movement detection using electrooculography and machine learning in cardiac arrest patients. Resuscitation. Published 24 March 2025. doi:10.
Summarised from the published abstract; every number is checked against it