Hemodynamics, fluids & transfusion
Diastolic Versus Systolic or Mean Intraoperative Hypotension as Predictive of Perioperative Myocardial Injury in a White-Box Machine-Learning Model
Authors' conclusion
We found that an absolute, not relative, IOH threshold based on diastolic arterial pressure, and not systolic or mean arterial pressure, or tachycardia, was most predictive of PMI.
Study context
- Population
- Patients undergoing vascular surgery
- Participants
- 498 patients
- Exposure
- Absolute and relative thresholds of systolic, mean and diastolic intraoperative hypotension, and tachycardia, as predictors of perioperative myocardial injury (PMI)
- Outcome
- Perioperative myocardial injury (PMI; high-sensitivity cardiac troponin T measured preoperatively and at 4, 24 and 48 h)
Methodological detailssingle-centre, decision tree machine-learning (white-box) model
- Single-centre
- Decision tree machine-learning (white-box) model
Main finding
As reported in the abstract
PMI and its prediction by IOH and tachycardia thresholds
PMI incidence
99
20%
Most predictive threshold: absolute diastolic arterial pressure (mm Hg)
<44
Model with diastolic <44 mm Hg: macro average F1 score
0.67
Model with diastolic <44 mm Hg: weighted average F1 score
0.76
Observational data: associations, not effects.
Original publication
Diastolic Versus Systolic or Mean Intraoperative Hypotension as Predictive of Perioperative Myocardial Injury in a White-Box Machine-Learning Model. Anesth Analg. Published 20 February 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →