Automated APACHE II and SOFA score calculation using real-world electronic medical record data in a single center
Authors' conclusion
A partially automated APACHE II score, calculated with real-world EMR data using an extraction script, is associated with in-hospital mortality risk.
Study context
- Population
- Adults admitted to one of three ICUs, July 1, 2019 to December 31, 2020
- Participants
- 4,794 ICU admissions
- Outcome
- Prediction of in-hospital mortality by automated electronic medical records (EMR)-based APACHE II score
Methodological detailssingle-centre
- Single-centre
Main finding
As reported in the abstract
In-hospital mortality discrimination, automated APACHE II
AUC (AU-ROC) of automated APACHE II for in-hospital mortality, 95% CI 0.81-0.85
0.83
In-hospital deaths (in-hospital mortality rate 10.9%)
522
Observational data: associations, not effects.
Further findings
ICU LOS per 10-unit increase in APACHE II score
- Mean increase in ICU LOS (days) per 10 units APACHE II, [1-1.2], p = < .0001
- 1.1
Daily SOFA score, survivors vs non-survivors
- SOFA score curves did not discriminate significantly between survivors and non-survivors
Original publication
Automated APACHE II and SOFA score calculation using real-world electronic medical record data in a single center. J Clin Monit Comput. Published 19 April 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →