Perioperative medicine & outcomes
Defining Postinduction Hemodynamic Instability With an Automated Classification Model
Authors' conclusion
Based on the high sensitivity and specificity, the developed model is able to differentiate between clinically relevant hemodynamic instability and hemodynamic stable patients.
Study context
- Population
- Adult elective noncardiac surgery patients, noninvasive BP measured from 5 min before to 15 min after first induction agent
- Participants
- 375 patients
- Exposure
- Hemodynamically unstable vs stable patients after induction
- Hemodynamic instabilityn = 78
- Hemodynamic stablen = 279reference
- Outcome
- Performance of automated classification model for clinically relevant hemodynamic instability vs expert labels
Methodological detailsautomated classification model development, random forest classifier
- Automated classification model development
- Random forest classifier
Main finding
As reported in the abstract
Random forest classifier performance
Area under the receiver operating curve (AUROC)
0.96
Sensitivity
0.84
Specificity
0.94
Observational data: associations, not effects.
Further findings
SAP before induction
- SAP before induction: P < .001
Interrater agreement between experts
- Interrater agreement
- 0.92 (95% CI 0.89-0.94)
Age
- Hemodynamically unstable patients significantly older, years
- 7 (95% CI 4-11, P < .001)
Chronic obstructive pulmonary disease (COPD) prevalence
- Higher COPD prevalence in hemodynamically unstable patients, % higher
- 3 (95% CI 1-8, P = .036)
Original publication
Defining Postinduction Hemodynamic Instability With an Automated Classification Model. Anesth Analg. Published 25 October 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →