Key result
A classification and regression tree model using pump speed waveform indices detected suction with a peak sensitivity of 99.11% and specificity of 98.76%.
Why the study?
Can a classification and regression tree model using noninvasive pump speed waveforms accurately detect left ventricular collapse in patients with implantable rotary blood pumps?
Population
10 human recipients of implantable rotary blood pumps
Comparison
Classification and regression tree model using… vs Expert opinion aided by transesophageal…
Authors
Loading...
May support automated LVAD suction prevention; leaves open prospective validation before clinical use.
Observational (n=10)
Can a classification and regression tree model using noninvasive pump speed waveforms accurately detect left ventricular collapse in patients with implantable rotary blood pumps?
A noninvasive algorithm using pump speed waveforms can highly accurately detect left ventricular collapse in patients with implantable rotary blood pumps, facilitating better automated control strategies.
Karantonis et al. (2007) conducted an observational in Implantable rotary blood pump recipients (n=10). Classification and regression tree model using pump speed waveform indices vs. Expert opinion aided by transesophageal echocardiographic images was evaluated on Detection of suction (ventricular collapse). A classification and regression tree model using pump speed waveform indices detected suction with a peak sensitivity of 99.11% and specificity of 98.76%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: