Pediatric anesthesia & critical care
Validation of Automated Data Extraction From the Electronic Medical Record to Provide a Pediatric Risk Assessment Score
Authors' conclusion
Development of an electronically derived, automated PRAm score that maintains good discrimination for 30-day mortality in neonates, infants, and children after noncardiac surgery is feasible.
Study context
- Population
- Children <18 years who underwent noncardiac surgery from 2017 through 2021 at Boston Children's Hospital
- Participants
- 6,014 / 6,014 / 5,267
- Exposure
- Automated vs NSQIP-derived vs manual physician-entered Pediatric Risk Assessment (PRAm) score
- Automatedn = 6,014
- NSQIPn = 6,014reference
- Manualn = 5,267
- Outcome
- Agreement and correlation among PRAm scores obtained via automation, NSQIP data and manual physician entry
Methodological detailssingle-centre
- Single-centre
Main finding
As reported in the abstract
Agreement and correlation with NSQIP score
- Automated
- Spearman rho 0.78 (95% CI 0.76–0.79); P < 0.001
- Automated
- Intraclass correlation coefficient (ICC) 0.80 (95% CI 0.79–0.81)
- Automated
- Fleiss kappa 0.66 (95% CI 0.65–0.67)
- Manual
- Spearman rho 0.73 (95% CI 0.71–0.74); P < 0.001
- Manual
- ICC 0.78 (95% CI 0.77–0.79)
- Manual
- Fleiss kappa 0.56 (95% CI 0.54–0.57)
Observational data: associations, not effects.
Secondary outcomes
| Outcome | Automated | NSQIP | Manual |
|---|---|---|---|
| Discrimination for 30-day mortality (ROC AUC) | |||
| AUC | 0.880 | 0.904 | 0.976 |
| 95% CI | 0.769-0.999 | 0.792-0.999 | 0.959,0.993 |
- Discrimination for 30-day mortality (ROC AUC) — 30-day mortality rate
- 0.18% (n = 11)
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Validation of Automated Data Extraction From the Electronic Medical Record to Provide a Pediatric Risk Assessment Score. Anesth Analg. Published 10 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →