Detection Of Myocardial Ischemia Research Articles

ApoJ-Glyc, an early marker of myocardial ischaemia, rapidly maps improved myocardial perfusion in STEMI patients undergoing successful primary PCI

Abstract Background Previous studies using experimental models and clinical retrospective samples have pointed to a potential role of glycosylated apolipoprotein J (ApoJ-Glyc) as a marker for the early detection of myocardial ischaemia. Ischaemia induces intracellular accumulation of non-glycosylated ApoJ that mirrors the reduction in ApoJ-Glyc serum levels in patients presenting with ST-segment elevation myocardial infarction (STEMI). Purpose The EDICA (Early Detection of Myocardial Ischaemia in Suspected Acute Coronary Syndromes by Apo J-Glyc as a Novel Pathologically based Ischaemia Biomarker) clinical trial assessed the performance of ApoJ-Glyc as a biomarker for the early detection of myocardial ischaemia in patients attending the A&E department with chest pain suggestive of acute coronary syndrome. Here, we report the observed changes in ApoJ-Glyc concentration in STEMI patients at baseline and after primary percutaneous coronary intervention (PPCI). Methods The EDICA trial, a multi-centre (10 sites), international, in vitro diagnostic study, assessed 404 patients attending the A&E department with suspected ACS. Of these, 291 patients had a final diagnosis of “non-ischaemic” event and 113 of “ischaemic” event. The main inclusion criterion was chest pain of suspected cardiac origin. Blood samples were obtained for the simultaneous assessment of high sensitivity-troponin and ApoJ-Glyc on admission (time 0) and at 1h and 3h thereafter. Two different glycosylated variants of ApoJ (ApoJ-GlycA2 and ApoJ-GlycA6) were analyzed with a novel ELISA in serum samples. Of the “ischaemic” patients, 33 had STEMI, of whom 85% underwent PPCI. Results As expected, in the presence of myocardial ischaemia, time 0 ApoJ-GlycA2 and ApoJ-GlycA6 serum levels decreased by 34% and 48%, respectively in STEMI patients, compared with non-ischaemic patients, i.e. ApoJ-GlycA2 in STEMI: 66 [52–95] μg/ml vs. non-ischaemic: 100 [72–131] μg/ml; P=0.0002; ApoJ-GlycA6 STEMI: 38 [34–67] vs. non-ischaemic: 73 [56–95] μg/ml; P<0.0001. ApoJ-GlycA6 showed a discriminating ability for the presence of STEMI with a 67% sensitivity and a 83% specificity (AUC=0.747, cut-off of 50μg/ml). In STEMI patients in whom PPCI successfully restored TIMI 3 flow, ApoJ-Glyc levels increased rapidly and significantly compared with time 0 levels (ApoJ-GlycA2: P=0.02 and P=0.003 for 1h and 3h; ApoJ-GlycA6: P=0.02 and P=0.002 for 1h and 3h) and compared to patients in whom PPCI was not performed (Table 1). Conclusions ApoJ-Glyc concentrations are reduced in STEMI patients on admission and increase rapidly after improved perfusion with PPCI, pointing to a potential role of this biomarker in the early detection of reversible ischaemia and the mapping of reversible changes. The mechanisms whereby ApoJ-Glyc levels rapidly and markedly increase after PPCI are speculative at present and deserve further investigation, together with the potential prognostic value of ApoJ-Glyc in this setting. Funding Acknowledgement Type of funding sources: Public grant(s) – EU funding. Main funding source(s): European Commission 2020-EIC-SMEInstrument Phase 2; Spanish Ministry of Science, Innovation and Universities

Early detection of myocardial ischemia in 12‐lead ECG using deterministic learning and ensemble learning

Background and objective: Early detection of myocardial ischemia is a necessary but difficult problem in cardiovascular diseases. Approaches that exclusively rely on classical ST and T wave changes on the standard 12-lead electrocardiogram (ECG) lack sufficient accuracy in detecting myocardial ischemia. This study aims to construct generalizable models for the detection of myocardial ischemia in patients with subtle ECG waveform changes (namely non-diagnostic ECG) using ensemble learning to integrate ECG dynamic features acquired via deterministic learning. Methods: First, cardiodynamicsgram (CDG), a noninvasive spatiotemporal electrocardiographic method, is generated through dynamic modeling of ECG signals using the deterministic learning algorithm. Then, the spectral fitting exponent, Lyapunov exponent, and Lempel-Ziv complexity are extracted from CDG. Subsequently, the bagging-based heterogeneous ensemble algorithm is applied on CDG features to generate diverse base classifiers and aggregate them with weighted voting to obtain an ensemble model for myocardial ischemia detection. Finally, we train and test the proposed heterogeneous ensemble model on a real-world clinical dataset. This dataset consists of 499 non-diagnostic 12-lead ECG records from 499 patients collected from three independent medical centers, including 383 patients with myocardial ischemia and 116 patients without ischemia. Results: With 10-times 5-fold cross-validation technology, our proposed method achieves an average accuracy of 89.10%, sensitivity of 91.72%, and specificity of 82.69% using the heterogeneous ensemble algorithm on the real-world clinical dataset. On three independent medical centers, our ensemble model also achieves accuracy performance over 82% for patients with non-diagnostic ECG. Furthermore, our ensemble model trained with real-world clinical data yields promising results of 91.11% accuracy, 90.49% sensitivity, and 92.88% specificity on the external test set of the public PTB dataset. Conclusion: The experimental results demonstrate that the proposed model combining ensemble learning and deterministic learning presents excellent diagnostic accuracy and generalization in clinical practice, and could be implemented as a complement to the standard ECG in the clinical diagnosis of myocardial ischemia.

Algorithm for real-time analysis of intracoronary electrocardiogram

IntroductionSince its first implementation in 1985, intracoronary (ic) electrocardiogram (ECG) has shown ample evidence for its diagnostic value given the higher sensitivity for myocardial ischemia detection in comparison to surface ECG. However, a lack of online systems to quantitatively analyze icECG in real-time prevents its routine use. The present study aimed to develop and validate an autonomous icECG analyzing algorithm.Materials and methodsThis is a retrospective observational study in 100 patients with chronic coronary syndrome. From each patient, a non-ischemic as well as ischemic icECG at the end of a 1-min proximal coronary balloon occlusion was available. An ECG expert as well as the newly developed algorithm for autonomous icECG analysis measured the icECG ST-segment shift in mV for each icECG tracing.ResultsIntraclass correlation coefficient (ICC) demonstrated low variability between the two methods (ICC = 0.968). Using the time point of icECG recording as allocation reference for absent or present myocardial ischemia, ROC-analysis for ischemia detection by the manually determined icECG ST-segment shift showed an area under the curve (AUC) of 0.968 ± 0.021 (p < 0.0001). AUC for the algorithm analysis was 0.967 ± 0.023 (p < 0.0001; p = 0.925 for the difference between the ROC curve AUCs). Time to complete analysis was below 1,000 ms for the autonomous icECG analysis and above 5 min for manual analysis.ConclusionA newly developed autonomous icECG analysing algorithm detects myocardial ischemia with equal accuracy as manual ST-segment shift assessment. The algorithm provides the technical fundament for an analysing system to quantitatively obtain icECG in real-time.

Emerging ECG methods for acute coronary syndrome detection: Recommendations & future opportunities

Despite being the mainstay for the initial noninvasive assessment of patients with symptomatic coronary artery disease, the 12‑lead ECG remains a suboptimal diagnostic tool for myocardial ischemia detection with only acceptable sensitivity and specificity scores. Although myocardial ischemia affects the configuration of the QRS complex and the STT waveform, current guidelines primarily focus on ST segment amplitude, which constitutes a missed opportunity and may explain the suboptimal diagnostic performance of the ECG. This possible opportunity and the low cost and ease of use of the ECG provide compelling motivation to enhance the diagnostic accuracy of the ECG to ischemia detection. This paper describes numerous computational ECG methods and approaches that have been shown to dramatically increase ECG sensitivity to ischemia detection. Briefly, these emerging approaches can be conceptually grouped into one of the following four approaches: (1) leveraging novel ECG waveform features and signatures indicative of ischemic injury other than the classical ST-T amplitude measures; (2) applying body surface potentials mapping (BSPM)-based approaches to enhance the spatial coverage of the surface ECG to detecting ischemia; (3) developing an inverse ECG solution to reconstruct anatomical models of activation and recovery pathways to detect and localize injury currents; and (4) exploring artificial intelligence (AI)-based techniques to harvest ECG waveform signatures of ischemia. We present recent advances, shortcomings, and future opportunities for each of these emerging ECG methods. Future research should focus on the prospective clinical testing of these approaches to establish clinical utility and to expedite potential translation into clinical practice.

Visualizing activation and recovery pathways as a novel approach for myocardial ischemia detection on prehospital 12-lead ECGs

Visualizing activation and recovery pathways as a novel approach for myocardial ischemia detection on prehospital 12-lead ECGs

Reliable Detection of Myocardial Ischemia Using Machine Learning Based on Temporal-Spatial Characteristics of Electrocardiogram and Vectorcardiogram.

Background: Myocardial ischemia is a common early symptom of cardiovascular disease (CVD). Reliable detection of myocardial ischemia using computer-aided analysis of electrocardiograms (ECG) provides an important reference for early diagnosis of CVD. The vectorcardiogram (VCG) could improve the performance of ECG-based myocardial ischemia detection by affording temporal-spatial characteristics related to myocardial ischemia and capturing subtle changes in ST-T segment in continuous cardiac cycles. We aim to investigate if the combination of ECG and VCG could improve the performance of machine learning algorithms in automatic myocardial ischemia detection. Methods: The ST-T segments of 20-second, 12-lead ECGs, and VCGs were extracted from 377 patients with myocardial ischemia and 52 healthy controls. Then, sample entropy (SampEn, of 12 ECG leads and of three VCG leads), spatial heterogeneity index (SHI, of VCG) and temporal heterogeneity index (THI, of VCG) are calculated. Using a grid search, four SampEn and two features are selected as input signal features for ECG-only and VCG-only models based on support vector machine (SVM), respectively. Similarly, three features (S I , THI, and SHI, where S I is the SampEn of lead I) are further selected for the ECG + VCG model. 5-fold cross validation was used to assess the performance of ECG-only, VCG-only, and ECG + VCG models. To fully evaluate the algorithmic generalization ability, the model with the best performance was selected and tested on a third independent dataset of 148 patients with myocardial ischemia and 52 healthy controls. Results: The ECG + VCG model with three features (S I ,THI, and SHI) yields better classifying results than ECG-only and VCG-only models with the average accuracy of 0.903, sensitivity of 0.903, specificity of 0.905, F1 score of 0.942, and AUC of 0.904, which shows better performance with fewer features compared with existing works. On the third independent dataset, the testing showed an AUC of 0.814. Conclusion: The SVM algorithm based on the ECG + VCG model could reliably detect myocardial ischemia, providing a potential tool to assist cardiologists in the early diagnosis of CVD in routine screening during primary care services.

Cross-granularity multi-task network for ischemia diagnosis and defect detection in the myocardial perfusion imaging

Myocardial perfusion imaging has been considered the reference standard for detection of myocardial ischemia in coronary heart disease. In clinical practice, doctors typically estimate the individual ischemic scores for 17 myocardial segments and then diagnose myocardial ischemia based on the scores for all segments considered together. However, prior works are generally limited to the diagnosis of myocardial ischemia and ignore the correlation between myocardial ischemia and the myocardial segment showing the defect. In this paper, we explore intra- and inter-granularity relationships between myocardial perfusion imaging tasks of different granularities and construct a multi-task learning framework to jointly learn these tasks. To this end, we propose a cross-granularity multi-task network, namely CGMT-Net. We present a task-specific module based on the attention mechanism to make the feature map task-specific. To explore the intra- and inter-granularity relationships among tasks, we propose a cross-granularity fusion module for the integration and transmission of task-specific information. We present a large dataset containing 1098 myocardial perfusion imaging sets paired with their diagnostic reports. Extensive experiments on the dataset demonstrate the superiority of our CGMT-Net over other methods. Furthermore, we performed ablation experiments that show the rationality and effectiveness of our network architecture.

Study on the Mechanism and Oxidative Stress of Compound Danshen on the Degradation of Cx43 and Improvement of Myocardial Apoptosis in ICM Rats.

In order to investigate the mechanism by which Salvia miltiorrhiza degrades connexin 43 (Cx43) and improves myocardial cell apoptosis and oxidative stress in rats with myocardial ischemia (ICM), male SD rats of pure grade are selected (32 rats), adaptively bred for 1 week, and then bred in SPF medium. They are randomly divided into a normal group, a model group, a low-dose Danshen group, and a high-dose group, with 8 rats in each group. HE staining and immunohistochemistry are performed. Serum samples are detected using kits according to instructions, including nitric oxide (NO) and endothelin-1 (ET-1); malondialdehyde (MDA), ELISA for superoxide dismutase (SOD), and vascular cell adhesion molecules (VCAM-1); western blot for detection of cardiac Cx43 protein expression; immunohistochemistry to detect Cx43 expression; and detection of myocardial ischemia. For ICM rats, the application of high-dose compound Salvia miltiorrhiza can effectively prevent the degradation of Cx43 protein, improve the apoptosis of myocardial cells in rats, and have a certain protective effect on ischemic myocardium in rats.

Stress echocardiography with regadenoson for the assessment of perioperative cardiovascular risk in non-cardiac surgery

Abstract Funding Acknowledgements Type of funding sources: None. Introduction The most commonly used drug in pharmacological stress echocardiography (SE) for perioperative cardiovascular (CV) risk assessment is dobutamine. Its arrhythmogenic potential and the unpredictable hypertensive response in patients with vascular pathology, makes us often resort to other less accessible and more expensive techniques such as Cardio-MRI or SPECT. Regadenoson is emerging as a safe drug in the detection of myocardial ischemia, although its use has not yet been validated in SE. Purpose The objective is to assess the short-medium term prognosis in patients undergoing high-risk noncardiac surgery who undergo SE with regadenoson. Methods A unicentric retrospective observational study. We included a subgroup of 58 patients referred for detection of ischemia prior to high-risk noncardiac surgery who underwent SE with regadenoson during the years 2017-2020. No patient has had cardiological symptoms. The test was considered positive if it presented at least one of the following: wall motion abnormalities, electrocardiographic and/or clinical changes compatible with ischemia. Patients were followed up in the immediate postoperative period (30 days), at 12 months and at 24 months, considering the presence of CV events such as admission for heart failure (HF), chest pain, acute myocardial infarction (AMI) or CV death. It was compared the group with negative (NG) and the group with positive (PG) results. Results 97% of the patients underwent vascular high-risk noncardiac surgery, 3% underwent other surgeries such as kidney transplantation or lung surgery considered high risk in the preanesthetic assessment. Twelve studies (21%) were positive and of these, only 2 patients underwent coronary artery bypass prior to surgery. The only CV event observed in this period was HF: in the NG 3 episodes were observed compared to 1 in the PG (p = 0.82), only in one of the events for HF was coronary angiography done that did not show coronary artery disease. The time to the NG event was a median of 90 [3-600] days versus 180 days in the PG. The cumulative incidence (CI) of events in the NG in the immediate postoperative period (30 days post-surgery) was 2%, annual 4% and biannual 7%. Conclusions A SE test with negative regadenoson prior to high-risk noncardiac surgery presents a low CI of events in the immediate postoperative period and in the short-medium term. Abstract Figure.

Regadenoson stress echocardiography: a road ahead

Abstract Funding Acknowledgements Type of funding sources: None. Introduction Drugs use in stress echocardiography (SE) have important limitations due to side effect and contraindications. Regadenoson (R) is emerging as a selective coronary vasodilator for pharmacological stress tests. Several studies have analyzed its diagnostic accuracy, but its prognostic value has not yet been studied. Purpose The objective is to assess safety and short-medium term prognosis in patients (p) who underwent SE with R. Methods Retrospective observational study. 126 patients were included from 2017 to 2020 and SE to study the detection of myocardial ischemia with R were performed. A positive SE test were consider if presented at least one of the follow: segmental changes in myocardial contractility, electrocardiography ischaemic changes or ischaemic symtomps. Adverse events (AE) were collected. To assess prognosis, we evaluated cardiovascular events (CV) with a median follow-up of 23 months, considering heart failure, angina, myocardial infarction (AMI) o cardiovascular death. We compare negative result SE test group (NG) with group of positive results (PG). Results Sixteen (13%) patients, presented AE, generally mild, with nausea in 4 patients. Two patients (1.6%) required the use of aminophylline for severe AE type bronchospasm. Nineteen studies (15%) were positive: 17 (89%) showed echocardiographically positive results, 5 of them also had clinical or electrocardiographic positivity, one (5%) was considered positive only by electrocardiographic criteria and another by clinical criteria. There were no CV deaths at follow-up. In the NG, 6 events were observed versus 2 in the PG (6 vs 11%). Time to event of the NG was a median of 90 [3-600] days versus 110 [40-180] days in the PG. The most frequent event was HF (4 NG vs 1 PG), coronary angiography was performed in only 2 patients with HF of the NG and did not show significant lesions. In the NG there were 2 IAM (2 vs 0), one had severe stenosis in the right coronary artery and the other several moderate diffuse stenosis. There was no events for angina in the NG (0 vs 1). The annual cumulative incidence was 11% in the PG compared to 4% in the NG. Conclusions Stress echocardiography with regadenoson is a safe test with a low serious adverse events rate. As concern as prognosis, In our sample, NG presented a lower proportion of events with a lower annual cumulative incidence than PG and also in a 23-month follow-up. Abstract Figure.

Dynamic computed tomography perfusion imaging for detection of cardiac allograft rejection and myocardial ischemia in a heart transplant recipient

Dynamic computed tomography perfusion imaging for detection of cardiac allograft rejection and myocardial ischemia in a heart transplant recipient

Increased deformation of the left ventricle during exercise test measured by global longitudinal strain can rule out significant coronary artery disease in patients with suspected unstable angina pectoris.

Noninvasive identification of significant coronary artery disease (CAD) in patients with unstable angina pectoris (UAP) is challenging. Exercise stress testing has been used for years in patients with suspected CAD but has low diagnostic accuracy. The use of Global longitudinal strain (GLS) by speckle tracking echocardiography is a highly sensitive and reproducible parameter for detection of myocardial ischemia. Our aim was to study if identification of normal or ischemic myocardium by measurement of GLS immediately after an ordinary bicycle exercise stress testing in patients with suspected UAP could identify or rule out significant CAD. Seventy-eight patients referred for coronary angiography from outpatient clinics and the emergency department with chest pain, inconclusive ECG and normal values of Troponin-T was included. All patients underwent echocardiographic examination at rest and immediately after maximum stress by exercise on a stationary bicycle. Significant CAD was defined by diameter stenosis>90% by coronary angiography. In patients with coronary stenosis between 50-90%, fractional flow reserve (FFR) was measured and defined abnormal<.80. Analysis of echocardiographic data were performed blinded for angiographic data. Patients were discharged diagnosed with CAD (n=34) or non-coronary chest pain (NCCP, n=44). In patients with NCCP, GLS at rest was -21.1 ± 1.7% and -25.5 ± 2.6% at maximum stress (P<.01). In patients with CAD, GLS at rest was -16.8 ± 4.0% and remained unchanged at maximum stress (-16.6 ± 4.6%, P=.69). In patients with NCCP, LVEF was 56.1%±6.0 and increased to 61.8% 5.2, P<.01. In CAD patients, LVEF at rest was 54.7%±8.6 and increased to 58.2%±9.5 during stress, P=.16. In NCCP patients, Wall Motion Score index decreased .02 ± .07, P=.03 during stress and was without significant changes in patients with CAD. Area under the curve (AUC) for distinguishing CAD for was .97 (.95-1.00), .63 (.49-.76), and .71 (.59-.83) for GLS, LVEF, and WMSi, respectively. In patients with suspected UAP, increased deformation of the left ventricle measured by GLS immediately after exercise stress testing identified normal myocardium without CAD. Reduced LV contractile function by GLS without increase after exercise identified significant CAD.

Association between T wave morphology parameters and abnormal cardiac SPECT imaging

BackgroundT-wave morphology dispersion (TMD) described the electrocardiographic T-wave heterogeneity during a single cardiac cycle. Total cosine R-to-T (TCRT) is the average of the cosines of the angles between the QRS and T vectors on the ECG. We examine the predictive value of TMD and TCRT calculation to assess abnormal myocardial perfusion. MethodsRetrospective single center cohort study including all patients referred for evaluation of ischemia by myocardial SPECT scanning with no known history of ischemic heart disease, from 1 January 2019 to 31 December 2019. Study endpoint was the correlation between the calculated TMD and TCRT values and detection of myocardial injury or ischemia by myocardial SPECT. ResultsAmong 606 patients, calculated TCRT was 0.401 ± 0.53 for the normal group and 0.283 ± 0.62 for the abnormal group (p = 0.007). Measured TMD was 22.9 ± 16.6 degrees (p < 0.001) in the normal group, compared to 31.5 ± 22.8 degrees (p < 0.001) for the abnormal group. ConclusionsThe results demonstrate a correlation between the decreased TCRT values and increase TMD and myocardial ischemia seen in SPECT results. The TCRT and TMD can be used as simple and non-invasive markers to predict abnormal SPECT results and ischemic heart disease in patients with no known cardiac history.

Repeated Structuring & Learning Procedure for Detection of Myocardial Ischemia: a Robustness Analysis.

Myocardial ischemia, consisting in a reduction of blood flow to the heart, may cause sudden cardiac death by myocardial infarction or trigger serious abnormal rhythms. Thus, its timely identification is crucial. The Repeated Structuring and Learning Procedure (RS&LP), an innovative constructive algorithm able to dynamically create neural networks (NN) alternating structuring and learning phases, was previously found potentially useful for myocardial ischemia detection. However, performance of created NN depends on three parameters, the values of which need to be set a priori by the user: maximal number of layers (NL), maximal number of initializations (NI) and maximal number of confirmations (NC). A robustness analysis of RS&LP to varying values of NL, NI and NC is fundamental for clinical applications concerning myocardial ischemia detection but was never performed before; thus, it was the aim the present study. Thirteen serial ECG features were extracted by pairs of ECGs belonging to 84 cases (patients with induced myocardial ischemia) and 398 controls (patients with no myocardial ischemia) and used as inputs to learn (50% of population) and test (50% of population) NNs with varying values of NL (1,2,3,4,10), NI (50,250,500,1000,1500) and NC (2,5,10,20,50). Performance of obtained NNs was compared in terms of area under the curve (AUC) of the receiver operating characteristics. Overall, 13 NNs were considered; 12 (92%) were characterized by AUC≥80% and 4 (31%) by AUC≥85%. Thus, RS&LP proved to be robust when creating NNs for detecting of myocardial ischemia.

Cover Image

The cover image is based on the Review Article Spectrum of clinical applications of interlead ECG heterogeneity assessment: From myocardial ischemia detection to sudden cardiac death risk stratification by Richard L. Verrier, Bruce D. Nearing, and Andre D'Avila., https://doi.org/10.1111/anec.12894.

Stress Myocardial Perfusion Imaging Interpretation From the Viewpoint of Fractional Flow Reserve.

Myocardial perfusion imaging (MPI) and fractional flow reserve (FFR) are established approaches to the assessment of myocardial ischemia. Recently, various FFR cutoff values were proposed, but the diagnostic accuracy of MPI in identifying positive FFR using various cutoff values is not well established.Methods and Results:We retrospectively studied 273 patients who underwent stress MPI and FFR within a 3-month period. Results for FFR were obtained from 218 left anterior descending artery (LAD) lesions and 207 non-LAD lesions. Stress MPI and FFR demonstrated a good correlation in the detection of myocardial ischemia. However, the positive predictive value (PPV) of FFR for detecting MPI-positive lesions at the optimal FFR thresholds was insufficient (44% for LAD and 65% for non-LAD lesions). This was caused by a sharp drop in PPV at an FFR threshold of 0.7 or more. Notably, 41% of the lesions with normal MPI demonstrated FFRs <0.80. However, MPI-negative lesions had an extremely low lesion rate with FFR <0.65 (6%). Conversely, 78% and 41% of MPI-positive lesions had FFR <0.80 and <0.65, respectively. The data confirmed that decisions based on MPI are reasonable because MPI-negative patients have an extremely low rate of lesions with a FFR below the cutoff point for a hard event, and MPI-positive lesions include many lesions with FFR <0.65.

Research Progress of ECG Monitoring Equipment and Algorithms Based on Polymer Materials.

Heart diseases such as myocardial ischemia (MI) are the main causes of human death. The prediction of MI and arrhythmia is an effective method for the early detection, diagnosis, and treatment of heart disease. For the rapid detection of arrhythmia and myocardial ischemia, the electrocardiogram (ECG) is widely used in clinical diagnosis, and its detection equipment and algorithm are constantly optimized. This paper introduces the current progress of portable ECG monitoring equipment, including the use of polymer material sensors and the use of deep learning algorithms. First, it introduces the latest portable ECG monitoring equipment and the polymer material sensor it uses and then focuses on reviewing the progress of detection algorithms. We mainly introduce the basic structure of existing deep learning methods and enumerate the internationally recognized ECG datasets. This paper outlines the deep learning algorithms used for ECG diagnosis, compares the prediction results of different classifiers, and summarizes two existing problems of ECG detection technology: imbalance of categories and high computational overhead. Finally, we put forward the development direction of using generative adversarial networks (GAN) to improve the quality of the ECG database and lightweight ECG diagnosis algorithm to adapt to portable ECG monitoring equipment.

Detection of myocardial ischemia by intracoronary ECG using convolutional neural networks

Abstract Introduction The electrocardiogram (ECG) is a valuable tool for the diagnosis of myocardial ischemia as it presents distinctive ischemic patterns. Deep learning methods such as convolutional neural networks (CNN) are employed to extract data-derived features and to recognize natural patterns. This study aimed to determine the optimal ischemic parameter as obtained from the highly susceptible intracoronary ECG (icECG) using pre-trained CNN. Method This was a retrospective observational study in 228 patients with chronic coronary syndrome. Each patient had participated in clinical trials with icECG recording and ST-segment shift measurement at the beginning (i.e.,non-ischemic) and the end (i.e.,ischemic) of a one-minute proximal coronary artery balloon occlusion establishing the reference. Using these data (893icECGs in total), two pre-trained, open-access CNN (GoogLeNet/ResNet101) were trained to recognize ischemia. The best performing CNN during training were compared with the icECG ST-segment shift for diagnostic accuracy in the detection of artificially induced myocardial ischemia. Results Using coronary patency or occlusion as reference for absent or present myocardial ischemia, receiver-operating-characteristics (ROC)-analysis of manually obtained icECG ST-segment shift (mV) showed an area under the ROC-curve (AUC) of 0.903±0.043 (p&amp;lt;0.0001, sensitivity 80%, specificity 92% at a cut-off of 0.279mV). The best performing CNN showed an AUC of 0.924 (sensitivity 93%, specificity 92%). DeLong-Test of the ROC-curves showed no significant difference between the AUCs. The underlying morphology responsible for the network prediction differed between the trained networks but was focused on the ST-segment and the T-wave for myocardial ischemia detection. Conclusions When tested in an experimental setting with artificially induced coronary artery occlusion, quantitative icECG ST-segment shift and CNN using pathophysiologic prediction criteria detect myocardial ischemia with similarly high accuracy. Funding Acknowledgement Type of funding sources: None.

Spectrum of clinical applications of interlead ECG heterogeneity assessment: From myocardial ischemia detection to sudden cardiac death risk stratification.

Heterogeneity in depolarization and repolarization among regions of cardiac cells has long been recognized as a major factor in cardiac arrhythmogenesis. This fundamental principle has motivated development of noninvasive techniques for quantification of heterogeneity using the surface electrocardiogram (ECG). The initial approaches focused on interval analysis such as interlead QT dispersion and Tpeak–Tend difference. However, because of inherent difficulties in measuring the termination point of the T wave and commonly encountered irregularities in the apex of the T wave, additional techniques have been pursued. The newer methods incorporate assessment of the entire morphology of the T wave and in some cases of the R wave as well. This goal has been accomplished using a number of promising vectorial approaches with the resting 12‐lead ECG. An important limitation of vectorcardiographic analyses is that they require exquisite stability of the recordings and are not inherently suitable for use in exercise tolerance testing (ETT) and/or ambulatory ECG monitoring for provocative stress testing or evaluation of the influence of daily activities on cardiac electrical instability. The objectives of the present review are to describe a technique that has been under clinical evaluation for nearly a decade, termed “interlead ECG heterogeneity.” Preclinical testing data will be briefly reviewed. We will discuss the main clinical findings with regard to sudden cardiac death risk stratification, heart failure evaluation, and myocardial ischemia detection using standard recording platforms including resting 12‐lead ECG, ambulatory ECG monitoring, ETT, and pharmacologic stress testing in conjunction with single‐photon emission computed tomography myocardial perfusion imaging.

Dynamic Myocardial Perfusion CT for the Detection of Hemodynamically Significant Coronary Artery Disease

ObjectivesIn this international, multicenter study, using third-generation dual-source computed tomography (CT), we investigated the diagnostic performance of dynamic stress CT myocardial perfusion imaging (CT-MPI) in addition to coronary CT angiography (CTA) compared to invasive coronary angiography (ICA) and invasive fractional flow reserve (FFR). BackgroundCT-MPI combined with coronary CTA integrates coronary artery anatomy with inducible myocardial ischemia, showing promising results for the diagnosis of hemodynamically significant coronary artery disease in single-center studies. MethodsAt 9 centers in Europe, Japan, and the United States, 132 patients scheduled for ICA were enrolled; 114 patients successfully completed coronary CTA, adenosine-stress dynamic CT-MPI, and ICA. Invasive FFR was performed in vessels with 25% to 90% stenosis. Data were analyzed by independent core laboratories. For the primary analysis, for each coronary artery the presence of hemodynamically significant obstruction was interpreted by coronary CTA with CT-MPI compared to coronary CTA alone, using an FFR of ≤0.80 and angiographic severity as reference. Territorial absolute myocardial blood flow (MBF) and relative MBF were compared using C-statistics. ResultsICA and FFR identified hemodynamically significant stenoses in 74 of 289 coronary vessels (26%). Coronary CTA with ≥50% stenosis demonstrated a per-vessel sensitivity, specificity, and accuracy for the detection of hemodynamically significant stenosis of 96% (95% CI: 91%-100%), 72% (95% CI: 66%-78%), and 78% (95% CI: 73%-83%), respectively. Coronary CTA with CT-MPI showed a lower sensitivity (84%; 95% CI: 75%-92%) but higher specificity (89%; 95% CI: 85%-93%) and accuracy (88%; 95% CI: 84%-92%). The areas under the receiver-operating characteristic curve of absolute MBF and relative MBF were 0.79 (95% CI: 0.71-0.86) and 0.82 (95% CI: 0.74-0.88), respectively. The median dose-length product of CT-MPI and coronary CTA were 313 mGy·cm and 138 mGy·cm, respectively. ConclusionsDynamic CT-MPI offers incremental diagnostic value over coronary CTA alone for the identification of hemodynamically significant coronary artery disease. Generalized results from this multicenter study encourage broader consideration of dynamic CT-MPI in clinical practice. (Dynamic Stress Perfusion CT for Detection of Inducible Myocardial Ischemia [SPECIFIC]; NCT02810795)