Perioperative medicine & outcomes
Forecasting intraoperative hypotension during hepatobiliary surgery
Authors' conclusion
We present a novel ML model to predict IOH with a distinctive "dial" on sensitivity and specificity to predict first IOH episode during liver resection surgeries.
Study context
- Population
- Adults undergoing hepatobiliary surgery
- Comparison
- Multivariate random forest (RF) model vs univariate MAP-only model
- Outcome
- Prediction of IOH (AUC)
- Follow-up
- Up to 8 min before a possible IOH event
Methodological detailsmachine learning, multivariate random forest, multi-model voting
- Machine learning
- Multivariate random forest
- Multi-model voting
Main finding
As reported in the abstract
IOH prediction, static context
| Group | Average AUC |
|---|---|
| Multivariate model | 0.97 |
| MAP-only | 0.83 |
Average AUC
Multivariate model0.97
MAP-only0.83
Further findings
| Outcome | MMV model |
|---|---|
| IOH prediction, dynamic sliding window · across 40 min prior to a possible IOH event | |
| AUC | 0.96 |
| PPV | 0.89 |
| NPV | 0.98 |
Cohort characteristics
- Subjects with at least one intraoperative hypotension (IOH) event
- 85%
- Males
- 70%
- Median age (years)
- 55.8
- Median BMI
- 27.7
Original publication
Forecasting intraoperative hypotension during hepatobiliary surgery. J Clin Monit Comput. Published 24 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →