Key result
Neural network predicts VT an hour prior with 0.93 AUC using heart and respiratory rate variability.
Why the study?
Does an artificial neural network model using heart rate and respiratory rate variability parameters accurately predict ventricular tachycardia one hour before occurrence in cardiovascular ICU patients?
Population
104 recordings from patients admitted to the cardiovascular intensive care unit at Asan Medical Center…
Design
Case-control
Authors
Loading...
May support ANN-based VT alerts in CVICU; hypothesis-generating and requires prospective validation before clinical use.
Case-Control (n=104)
No
Does an artificial neural network model using heart rate and respiratory rate variability parameters accurately predict ventricular tachycardia one hour before occurrence in cardiovascular ICU patients?
Effect estimate: AUC 0.93
An artificial neural network using heart rate and respiratory rate variability parameters demonstrated high accuracy in predicting ventricular tachycardia one hour before its onset in cardiovascular ICU patients.
Lee et al. (2016) conducted a case-control in Ventricular tachycardia (n=104). Artificial neural network (ANN) prediction model vs. Control recordings was evaluated on Prediction of ventricular tachycardia one hour before onset (AUC 0.93). An artificial neural network using heart rate and respiratory rate variability predicted ventricular tachycardia one hour before onset with 0.88 sensitivity, 0.82 specificity, and an AUC of 0.93.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: