Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Identifying Premature Ventricular Complexes from Outflow Tracts Based on PVC Configuration: A Machine Learning Approach
Ist Teil von
Journal of clinical medicine, 2023-08, Vol.12 (17), p.5558
Ort / Verlag
MDPI AG
Erscheinungsjahr
2023
Link zum Volltext
Quelle
EZB Electronic Journals Library
Beschreibungen/Notizen
Background: Current inferences about the site of origin (SOO) of premature ventricular complexes (PVC) from the surface ECG have not been subjected to newer data analytic techniques that identify signals that are not recognized by visual inspection. Aims: The objective of this study was to apply data analytics to PVC characteristics. Methods: PVCs from 12-lead ECGs of a consecutive series of 338 individuals were examined by unsupervised machine learning cluster analysis, and indexes were compared to a composite criterion for SOO. Results: Data analytics found that V1S plus V2S ≤ 9.25 of the PVC had a LVOT origin (sensitivity 95.4%; specificity 97.5%). V1R + V2R + V3R > 15.0 (a RBBB configuration) likely had a LVOT origin. PVCs with V1S plus V2S > 12.75 (LBBB configuration) likely had a RVOT origin. PVC with V1S plus V2S > 14.25 (LBBB configuration) and all inferior leads positive likely had a RVOT origin. Conclusion: Newer data analytic techniques provide a non-invasive approach to identifying PVC SOO, which should be useful for the clinician evaluating a 12-lead ECG.