RESUMO
BACKGROUND: Atrial fibrillation (AF) can be maintained by localized intramural reentrant drivers. However, AF driver detection by clinical surface-only multielectrode mapping (MEM) has relied on subjective interpretation of activation maps. We hypothesized that application of machine learning to electrogram frequency spectra may accurately automate driver detection by MEM and add some objectivity to the interpretation of MEM findings. METHODS: Temporally and spatially stable single AF drivers were mapped simultaneously in explanted human atria (n=11) by subsurface near-infrared optical mapping (NIOM; 0.3 mm2 resolution) and 64-electrode MEM (higher density or lower density with 3 and 9 mm2 resolution, respectively). Unipolar MEM and NIOM recordings were processed by Fourier transform analysis into 28 407 total Fourier spectra. Thirty-five features for machine learning were extracted from each Fourier spectrum. RESULTS: Targeted driver ablation and NIOM activation maps efficiently defined the center and periphery of AF driver preferential tracks and provided validated annotations for driver versus nondriver electrodes in MEM arrays. Compared with analysis of single electrogram frequency features, averaging the features from each of the 8 neighboring electrodes, significantly improved classification of AF driver electrograms. The classification metrics increased when less strict annotation, including driver periphery electrodes, were added to driver center annotation. Notably, f1-score for the binary classification of higher-density catheter data set was significantly higher than that of lower-density catheter (0.81±0.02 versus 0.66±0.04, P<0.05). The trained algorithm correctly highlighted 86% of driver regions with higher density but only 80% with lower-density MEM arrays (81% for lower-density+higher-density arrays together). CONCLUSIONS: The machine learning model pretrained on Fourier spectrum features allows efficient classification of electrograms recordings as AF driver or nondriver compared with the NIOM gold-standard. Future application of NIOM-validated machine learning approach may improve the accuracy of AF driver detection for targeted ablation treatment in patients.
Assuntos
Potenciais de Ação , Fibrilação Atrial/diagnóstico , Técnicas Eletrofisiológicas Cardíacas , Análise de Fourier , Frequência Cardíaca , Aprendizado de Máquina , Imagens com Corantes Sensíveis à Voltagem , Fibrilação Atrial/fisiopatologia , Humanos , Valor Preditivo dos Testes , Reprodutibilidade dos Testes , Espectroscopia de Luz Próxima ao Infravermelho , Fatores de TempoAssuntos
Doenças Cardiovasculares/terapia , Terapias Complementares/métodos , Mitocôndrias/metabolismo , Plaquetas/efeitos dos fármacos , Plaquetas/patologia , Doenças Cardiovasculares/genética , Doenças Cardiovasculares/patologia , Epigênese Genética/efeitos dos fármacos , Produtos Finais de Glicação Avançada/metabolismo , Humanos , Mitocôndrias/efeitos dos fármacos , Compostos Fitoquímicos/uso terapêutico , Fitoterapia/métodos , Inibidores da Agregação Plaquetária/uso terapêutico , Receptor para Produtos Finais de Glicação Avançada/metabolismoRESUMO
BACKGROUND: Atherosclerosis remains a major problem in the modern society being a cause of life-threatening cardiovascular diseases. Subclinical atherosclerosis can be present for years before the symptoms become obvious, and first manifestations of the disease in a form of acute ischemia of organs are often fatal. The development of atherosclerosis is characterized by lipid accumulation in the aortic wall and formation of foam cells overloaded with large amounts of lipid inclusions in the cytoplasm. Current therapy of atherosclerosis is aimed mostly at the normalization of the blood lipid profile, and has no direct activity on the atherosclerotic plaque development. It is therefore necessary to continue the search for substances that possess a direct anti-atherosclerotic effect, preventing the cholesterol deposition in the arterial wall cells and reducing the existing plaques. PURPOSE: Medicinal plants with potential anti-atherosclerotic activity are especially interesting in that regard, as plant-based medications are often characterized by good tolerability and are suitable for long-term therapy. The evaluation of novel active substances requires the establishment of reliable models of atherogenesis. In this review we discuss cellular models based on cultured human aortic cells. We also discuss several examples of successful application of these models for evaluation of anti-atherosclerotic activity of natural products of botanical origin based on measurable parameters, such as intracellular cholesterol accumulation. CHAPTERS: We describe several examples of successful screening and clinical studies evaluating natural products that can be beneficial for prevention and treatment of atherosclerosis, including the subclinical (asymptomatic) forms. CONCLUSION: Several substances of botanical origin have been demonstrated to be active for treatment and prevention of atherosclerosis. The obtained results encourage future studies of naturally occurring anti-atherosclerotic agents.