METHODS FOR DETERMINING WHETHER PATIENT MONITOR ALARMS ARE TRUE OR FALSE BASED ON A MULTI RESOLUTION WAVELET TRANSFORM AND INTER-LEADS VARIABILITY

摘要

Methods for automatically determining whether a patient monitor alarm will sound from a true or false signal, in particular from ventricular tachycardia (VT) and suppressing false alarms without eliminating any true alarms are presented. A multiresolution wavelet is extracted from a raw ECG waveform. Features are then extracted from the wavelets that account for summary statistics, noise, areas under the curve and summary statistics of the KL-divergence of the power spectra density between every two ECG leads. A classifier can be then be trained and its performance measured.

主权项

1. A method for determining whether a pathophysiological signal is true or false, the method comprising:
receiving physiological waveform data from a patient monitor, said patient monitor configured to collect multiple waveform data and provide notification to an operator when it detects a pathophysiological signal; extracting at least one multiresolution wavelet transform from the physiological waveform data of said multiple waveform data; extracting at least one feature from said multiresolution wavelet transform; analyzing variations among said at least one extracted feature for said multiple waveform data to determine whether the pathophysiological signal is true or false; training a classifier by presenting said at least one extracted feature to said classifier; and suppressing said notification when it is determined that the pathophysiological signal is false.