Cardiothoracic & vascular anesthesia
Effect of a Machine Learning-Derived Early Warning Tool With Treatment Protocol on Hypotension During Cardiac Surgery and ICU Stay: The Hypotension Prediction 2 (HYPE-2) Randomized Clinical Trial
Primary resultResult — go to the resultMedian of differences −0.40 mm Hg 95% CI −0.65 to −0.27Authors' conclusion
Using HPI combined with diagnostic guidance on top of standard care significantly decreased hypotension severity in elective cardiac surgery patients compared with standard care.
Study context
- Population
- Adults undergoing elective on-pump CABG, with or without single heart valve surgery, with mean arterial pressure (MAP) target ≥65 mm Hg during off-pump phases and ICU stay; academic hospital, the Netherlands130 in primary analysis
- Participants
- 142 adults
- Comparison
- Hypotension Prediction Index (HPI) with diagnostic guidance plus standard care vs standard care alone
- HPIn = 72
- Standard caren = 70reference
- Primary endpoint
- Severity of hypotension: time-weighted average (TWA) of MAP <65 mm Hg
Methodological detailssingle-centre
- Single-centre
Primary result
As reported in the abstract
Median of differences
−0.40 mm Hg
95% CI −0.65 to −0.27
P < 0.001
HPI vs Standard care
median of differences −0.40 mm Hg (95% CI −0.65 to −0.27); P < 0.001
Secondary outcomes
Time in hypotension · less time in hypotension · per-group values are measurement duration
median (minutes) 28 (17–44)
Hypertension severity, treatment choice, fluid, vasopressor and inotrope amounts
- No significant differences
Original publication
Effect of a Machine Learning-Derived Early Warning Tool With Treatment Protocol on Hypotension During Cardiac Surgery and ICU Stay: The Hypotension Prediction 2 (HYPE-2) Randomized Clinical Trial. Crit Care Med. Published 22 November 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →