RESUMEN
OBJECTIVE: Despite a long history of ECG-based monitoring of acute ischemia quantified by several widely used clinical markers, the diagnostic performance of these metrics is not yet satisfactory, motivating a data-driven approach to leverage underutilized information in the electrograms. This study introduces a novel metric for acute ischemia, created using a machine learning technique known as Laplacian eigenmaps (LE), and compares the diagnostic and temporal performance of the LE metric against traditional metrics. METHODS: The LE technique uses dimensionality reduction of simultaneously recorded time signals to map them into an abstract space in a manner that highlights the underlying signal behavior. To evaluate the performance of an electrogram-based LE metric compared to current standard approaches, we induced episodes of transient, acute ischemia in large animals and captured the electrocardiographic response using up to 600 electrodes within the intramural and epicardial domains. RESULTS: The LE metric generally detected ischemia earlier than all other approaches and with greater accuracy. Unlike other metrics derived from specific features of parts of the signals, the LE approach uses the entire signal and provides a data-driven strategy to identify features that reflect ischemia. CONCLUSION: The superior performance of the LE metric suggests there are underutilized features of electrograms that can be leveraged to detect the presence of acute myocardial ischemia earlier and more robustly than current methods. SIGNIFICANCE: The earlier detection capabilities of the LE metric on the epicardial surface provide compelling motivation to apply the same approach to ECGs recorded from the body surface.
Asunto(s)
Electrocardiografía , Isquemia Miocárdica , Animales , Isquemia , Aprendizaje Automático , Isquemia Miocárdica/diagnósticoRESUMEN
BACKGROUND: Coronary artery disease and myocardial ischemia cause substantial morbidity and mortality. While ischemia is traditionally diagnosed on the 12-lead electrocardiogram (ECG) by shifts in the ST segment, electrical changes are also produced within the QRS complex during depolarization of ischemic ventricular tissue, though these are often of small amplitude and can be missed in traditional ECG analysis. We explore the utility of an easily implemented spectral analysis method for detecting intra-QRS changes during episodes of myocardial ischemia, using Holter recordings from the European ST-T database. METHODS: Time-frequency distributions of QRS complexes from each recording were computed using the continuous wavelet transform. Indices corresponding to frequency content of four overlapping frequency bands were computed: F1 (24-35Hz), F2 (30-45Hz), F3 (40-60Hz), and F4 (50-80Hz). Values of these indices were compared during annotated episodes of ST change and during a baseline during the recording. RESULTS: Marked changes in intra-QRS frequency content were identified during ischemia, grouped by ECG lead analyzed. In lead III, a pronounced and statistically significant increase in the highest frequency sub-bands (F3 and F4) was consistently observed. Analysis of anterior precordial leads also showed significant increases in F4. CONCLUSIONS: Intra-QRS time-frequency analysis using the continuous wavelet transform can identify a spectral signature corresponding to myocardial ischemia in the range 24-80Hz. Intra-QRS spectral analysis has the potential for many clinical applications.
Asunto(s)
Algoritmos , Diagnóstico por Computador/métodos , Electrocardiografía/métodos , Isquemia Miocárdica/diagnóstico , Femenino , Humanos , Masculino , Persona de Mediana Edad , Reproducibilidad de los Resultados , Estudios Retrospectivos , Sensibilidad y EspecificidadRESUMEN
Over four decades of high frequency electrocardiography research have provided a body of knowledge about QRS changes during myocardial ischemia, and the techniques to measure and quantify them. High-frequency QRS (HFQRS) components, being closely related to the pattern of ventricular depolarization, carry valuable clinical information. Changes in HFQRS amplitude and morphology have been shown to be sensitive diagnostic markers of myocardial ischemia, often superior to measures of ST-T segment changes. Clinical studies in patients undergoing exercise testing have consistently demonstrated the incremental diagnostic value of HFQRS analysis in detection of demand ischemia. In 6 studies that evaluated the HyperQ™ technology, the average sensitivity and specificity of HFQRS analysis were 75%±6% and 80%±6%, respectively, compared to average sensitivity 48%±16% and average specificity 70%±15% of ST segment analysis. In patients with acute supply ischemia, recent studies characterized and quantified the ischemic HFQRS patterns. HFQRS morphology index was found to be higher in patients with acute coronary syndrome (ACS), compared to non-ischemic, with good sensitivity in patients without ST elevation. These research findings may be translated into commercially-available ECG systems and be used in clinical practice for improved diagnosis and monitoring of myocardial ischemia.
Asunto(s)
Síndrome Coronario Agudo/diagnóstico , Algoritmos , Diagnóstico por Computador/métodos , Electrocardiografía/métodos , Isquemia Miocárdica/diagnóstico , Humanos , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
Shortly following an occlusion of an epicardial coronary artery, changes in the surface electrocardiogram (ECG) can be detected. Initially, T waves in leads with their positive poles facing the ischemic zone become positive, tall and symmetrical. Later, ST segment elevation (STE) becomes apparent. If ischemia continues, changes in the terminal portion of the QRS may also be detected. The changes in the terminal portion of the QRS are believed to be caused by prolongation of the electrical conduction in the ischemic zone and reflect severe ischemia due to lack of protection by preconditioning or collateral circulation. Several groups have shown that patients with the QRS changes of grade 3 ischemia have higher mortality, higher incidence of reinfarction and heart failure than patients presenting with only the T and ST changes of grade 2 ischemia, despite equal success in recanalizing the epicardial coronary artery by either thrombolytic therapy or primary percutaneous coronary intervention. Grade 3 ischemia is associated with more rapid progression of necrosis and larger final infarct size. Further studies are needed to better understand the underlying mechanisms that determine the severity of ischemia and how we should use this method based on the standard 12 lead ECG to implement clinical therapeutic decisions.