Perioperative medicine & outcomes
Robotic process automation to identify patients at high risk for perioperative myocardial infarction or injury: a prospective, blinded, paired reader-controlled single-centre study
Performance · True positive identificationsResult — go to the resultRelative true positive fraction 1.19 95% CI 1.08–1.32Authors' conclusion
RPA screening was superior to standard-of-care manual screening by experienced clinical staff in identifying patients at high risk for perioperative myocardial infarction or injury.
Study context
- Population
- Surgical patients screened for eligibility for active surveillance for perioperative MI/injury (high risk), by predefined criteria77 (12%) eligible
- Participants
- 660 patients
- Comparison
- Robotic process automation (RPA) screening vs Manual screening
- Outcome
- Relative true positive fraction vs reference standard classification (independent blinded clinician review of discrepancies)
Methodological detailsprospective, blinded, paired reader-controlled, single-centre
- Prospective
- Blinded
- Paired reader-controlled
- Single-centre
Performance
True positive identifications
Relative true positive fraction
1.19
95% CI 1.08–1.32
P = 0.004
Events by group
As reported in the abstract
- Number needed to screen to identify one additional true positive using RPA
- 6
Further findings
| Outcome | RPA screening | Manual screening |
|---|---|---|
| Sensitivity | ||
| Sensitivity | 0.97 (0.91-0.99) | — not stated in the abstract |
| Specificity | ||
| Specificity | 0.98 [0.97-0.99] | 1.0 [0.99-1.00] |
— not stated in the abstract
- Sensitivity: abstract prints a comparator sensitivity of 0.82 (0.72-0.89) without naming the group ("for.")
Specificity
- Both approaches had high specificity
Number needed to screen to identify one additional true positive with RPA screening
- Number needed to screen
- 6
Estimated annual cost
- RPA screening cost lower vs manual screening
- 81%
Original publication
Robotic process automation to identify patients at high risk for perioperative myocardial infarction or injury: a prospective, blinded, paired reader-controlled single-centre study. Br J Anaesth. Published 31 July 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →