Natural language processing to classify electrocardiograms in patients with syncope: A preliminary study

Table 1 Syncope high-risk ECG criteria from risk stratification studies QTc > 470 LBBB QRS > 100 PR < 120 ms Any AV (Type I, II, III) Left axis deviation Non-sinus rhythm (including paced) multiple PVC's Sinus bradycardia < 40 Q waves ST segment changes Note: Based on decision rules...

Full description

Saved in:
Bibliographic Details
Published inHealth science reports Vol. 5; no. 6; pp. e904 - n/a
Main Authors Quinn, James, Kim, David, Rice, Brian Travis, Hao, Wei David
Format Journal Article
LanguageEnglish
Published United States John Wiley & Sons, Inc 01.11.2022
John Wiley and Sons Inc
Wiley
Subjects
Accuracy
Algorithms
Automation
Cardiac arrhythmia
Classification
electrocardiograms
Electrocardiography
Emergency medical care
Natural language processing
Physicians
Research Letter
Review boards
Sinuses
syncope
Writing
electrocardiograms
syncope
natural language processing
classification
Online AccessGet full text
ISSN2398-8835
2398-8835
DOI10.1002/hsr2.904

Cover

More Information
Summary:Table 1 Syncope high-risk ECG criteria from risk stratification studies QTc > 470 LBBB QRS > 100 PR < 120 ms Any AV (Type I, II, III) Left axis deviation Non-sinus rhythm (including paced) multiple PVC's Sinus bradycardia < 40 Q waves ST segment changes Note: Based on decision rules and consensus groups for “high-risk” ECG abnormalities. 1,5–11 Abbreviation: ECG, electrocardiogram. The protocol was approved by researchers a t and the protocol was approved by the Stanford University Institutional Review Board with an exemption from informed consent. ETHICS STATEMENT The Stanford University Institutional Review Board with an exemption from informed consent under the policies of the US Federal Policy for the Protection of Human Subjects Research.
Bibliography:Abstract presented at the Annual Meeting of the Society of Academic Emergency Medicine, New Orleans, LA USA, May 2022.
SourceType-Scholarly Journals-1
ObjectType-Correspondence-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:2398-8835
2398-8835
DOI:10.1002/hsr2.904