Saadat SHOOKA User Manual page 32

Electroshock
Table of Contents

Advertisement

Performance Report is provided in accordance with AHA recommendations
2
requirements
for reporting performance data for a rhythm recognition detector.
A. Acquisition and Annotation Methodology
This section includes recording methods, rhythm source, rhythm selection criteria, annotation
methods, and annotation criteria for the databases.
PhysioNet Test Set
The PhysioNet Test Set includes 5891 ECG segments gathered from a variety of sources. Each
ECG segment is 8 seconds in duration. Sources for the ECGs include:
• Creighton University Ventricular Tachyarrhythmia Database (CUDB):
This database includes 35 eight-minute ECG recordings of human subjects who
experienced episodes of sustained ventricular tachycardia, ventricular flutter, and
ventricular fibrillation. Records was obtained from a long-term ECG (Holter) recording
and from patient monitors. Five records were from paced patients. The reference
annotation files supplied for this database have been included to aid users in locating
VF segments.
• MIT-BIH Malignant Ventricular Ectopy Database (VFDB):
This database includes 22 half-hour ECG recordings of subjects who experienced
episodes of sustained ventricular tachycardia, ventricular flutter, and ventricular
fibrillation. The reference annotation contains rhythm labels including atrial fibrillation,
asystole, ventricular bigeminy, first degree heart block, high grade ventricular ectopic
activity, normal sinus rhythm, nodal rhythm, noise, pacemaker (paced rhythm), sinus
bradycardia, supraventricular tachyarrhythmia, ventricular escape rhythm, ventricular
fibrillation, ventricular flutter and ventricular tachycardia.
• MIT-BIH Arrhythmia Database (MITDB):
The MIT-BIH Arrhythmia Database contains 48 half-hour excerpts of two-channel
ambulatory ECG recordings, obtained from 47 subjects. Two or more cardiologists
independently annotated each record.
• AHA Ventricular Arrhythmia Database (AHADB):
AHA database consisted of 80 two-channel excerpts of analog ambulatory ECG
recordings. These 80 recordings are divided into eight classes of ten recordings each,
according to the highest level of ventricular ectopy present. In this case, we use part 8
(ventricular flutter/fibrillation) of AHA database.
Simulator Test Set
The Simulator Test Set include 52 ECG segments gathered from the Fluke Impulse 7000DP
Defibrillator Analyzer. Each ECG segment is 10 seconds in duration and including Ventricular
1
Kerber RE, et al, "Automatic External Defibrillators for Public Access Defibrillation: Recommendations for Specifying and Reporting Arrhythmia
Analysis Algorithm Performance, Incorporating New Waveforms, and Enhancing Safety: A Statement for Health Professionals from the American
Heart Association Task Force on Automatic External Defibrillation", Subcommittee on AED Safety and Efficacy. Circulation, 1997: Vol. 95: 1677-
1682.
2
Clause 201.7.9.3.103, "Essential Performance data of the Rhythm Recognition Detector," International Electrotechnical Association, IEC 60601-
2-4, Medical Electrical Equipment – Part 2-4: Particular Requirements for the Basic Safety and Essential Performance of Cardiac Defibrillators:
2018.
1
and IEC
32

Advertisement

Table of Contents
loading

Table of Contents