Cardiac arrest & resuscitation
Development and validation of a prehospital termination of resuscitation (TOR) rule for out - of hospital cardiac arrest (out-of-hospital cardiac arrest (OHCA)) cases using general purpose artificial intelligence (AI)
Authors' conclusion
The accuracy of prediction models using AI software to determine outcomes in OHCA was excellent and the AI-TOR rule's variables from prediction model performed better than the Universal TOR rule.
Study context
- Population
- Adults (≥18 years) with OHCA of presumed cardiac etiology, All-Japan Utstein Registry, 2016–2019153,374 validation cases
- Participants
- 302,799 adults
- Comparison
- AI-TOR rule vs Universal TOR rule
- Outcome
- Prediction of neurologically favorable outcome (one-month survival)
- Follow-up
- one-month
Methodological detailsregistry-based, derivation and validation cohorts, AI software (Prediction One®)
- Registry-based
- Derivation and validation cohorts
- AI software (Prediction One®)
Performance
As reported in the abstract
Prediction of lack of neurologically favorable survival (validation dataset)
| Test or model | AUC | Specificity | PPV |
|---|---|---|---|
| AI-TOR rule | 0.952 (95%CI 0.949 −0.954) | 0.990 | 0.999 |
| Universal TOR | — not stated in the abstract | 0.959 | 0.998 |
AUC
AI-TOR rule0.952 (95%CI 0.949 −0.954)
Universal TOR— not stated in the abstract
Specificity
AI-TOR rule0.990
Universal TOR0.959
PPV
AI-TOR rule0.999
Universal TOR0.998
— not stated in the abstract
- 11-variable AI model AUC, validation dataset
- 0.965
- 11-variable AI model AUC, training dataset
- 0.969
- Neurologically favorable one-month survival among 80,198 meeting all four AI-TOR criteria
- 58 (0.07%)
Original publication
Development and validation of a prehospital termination of resuscitation (TOR) rule for out - of hospital cardiac arrest (OHCA) cases using general purpose artificial intelligence (AI). Resuscitation. Published 5 March 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →