Detection of myocardial ischemia by intracoronary ECG using convolutional neural networks

Intracoronary electrocardiogram detects coronary microvascular dysfunction and ischemia in patients with no obstructive coronary arteries disease

BACKGROUND

Coronary microvascular dysfunction (CMD) is the leading cause of ischemia with no obstructive coronary arteries disease (INOCA) disease. Diagnosis of CMD relies on surrogate physiological indices without objective proof of ischemia.

OBJECTIVES

Intracoronary electrocardiogram (icECG) derived hyperemic indices may accurately and objectively detect CMD and reversible ischemia in related territory.

METHODS

INOCA patients with proven ischemia by myocardial perfusion scan (MPS) and completely normal coronary arteries underwent simultaneous intracoronary electrophysiological (icECG) and physiological (intracoronary Doppler) assessment in all 3 coronary arteries during rest and under adenosine induced hyperemia.

RESULTS

Sixty vessels in 21 patients were included in the final analysis. All patients had at least one vessel with abnormal CFR. 41 vessels had CMD (CFR < 2.5), of which 26 had increased microvascular resistance (structural CMD, HMR > 1.9 mmHg.cm-1.s) and 15 vessels had CMD (CFR < 2.5) with normal microvascular resistance (functional CMD, HMR <= 1.9 mmHg.cm-1.s). Only one-third of the patients (n = 7) had impaired CFR < 2.5 in all 3 epicardial arteries. Absolute ST shift between hyperemia and rest (∆ST) has shown the best diagnostic performance for ischemia (cut-off 0.10 mV, sensitivity: 95%, specificity: 72%, accuracy: 80%, AUC: 0.860) outperforming physiological indices (CFR: 0.623 and HMR: 0.653 DeLong's test P = .0002).

CONCLUSIONS

In INOCA patients, CMD involves coronary artery territories heterogeneously. icECG can accurately detect CMD causing perfusion abnormalities in patients with INOCA outperforming physiological CMD markers, by demonstrating actual ischemia instead of predicting the likelihood of inducible ischemia based on violated surrogate thresholds of blunted flow reserve or increased minimum microvascular resistance.

CONDENSED ABSTRACT

In 21 INOCA patients with coronary microvascular dysfunction (CMD) and myocardial perfusion scan proved ischemia, hyperemic indices of intracoronary electrocardiogram (icECG) have accurately detected vessel-specific CMD and resulting perfusion abnormalities & ischemia, outperforming invasive hemodynamic indices. Absolute ST shift between hyperemia and rest (∆ST) has shown the best classification performance for ischemia in no Obstructive Coronary Arteries (AUC: 0.860) outperforming Doppler derived CMD indices (CFR: 0.623 and HMR: 0.653 DeLong's test P = .0002).icECG can be used to diagnose CMD causing perfusion defects by demonstrating actual reversible ischemia at vessel-level during the initial CAG session, obviating the need for further costly ischemia tests.

CLINICALTRIALS

GOV: NCT05471739.

Machine learning based hybrid anomaly detection technique for automatic diagnosis of cardiovascular diseases using cardiac sympathetic nerve activity and electrocardiogram

OBJECTIVES

Coronary artery diseases (CADs) are the leading cause of death worldwide and early diagnosis is crucial for timely treatment. To address this, our study presents a novel automated Artificial Intelligence (AI)-based Hybrid Anomaly Detection (AIHAD) technique that combines various signal processing, feature extraction, supervised, and unsupervised machine learning methods. By jointly and simultaneously analyzing 12-lead cardiac sympathetic nerve activity (CSNA) and electrocardiogram (ECG) data, the automated AIHAD technique performs fast, early, and accurate diagnosis of CADs.

METHODS

In order to develop and evaluate the proposed automated AIHAD technique, we utilized the fully labeled STAFF III and PTBD databases, which contain the 12-lead wideband raw recordings non-invasively acquired from 260 subjects. Using these wideband raw recordings, we developed a signal processing technique that simultaneously detects the 12-lead CSNA and ECG signals of all subjects. Using the pre-processed 12-lead CSNA and ECG signals, we developed a time-domain feature extraction technique that extracts the statistical CSNA and ECG features critical for the reliable diagnosis of CADs. Using the extracted discriminative features, we developed a supervised classification technique based on Artificial Neural Networks (ANNs) that simultaneously detects anomalies in the 12-lead CSNA and ECG data. Furthermore, we developed an unsupervised clustering technique based on Gaussian mixture models (GMMs) and Neyman-Pearson criterion, which robustly detects outliers corresponding to CADs.

RESULTS

Using the automated AIHAD technique, we have, for the first time, demonstrated a significant association between the increase in CSNA signals and anomalies in ECG signals during CADs. The AIHAD technique achieved highly reliable detection of CADs with a sensitivity of 98.48 %, specificity of 97.73 %, accuracy of 98.11 %, positive predictive value of 97.74 %, negative predictive value of 98.47 %, and F1-score of 98.11 %. Hence, the automated AIHAD technique demonstrates superior performance compared to the gold standard diagnostic test ECG in the diagnosis of CADs. Additionally, it outperforms other techniques developed in this study that separately utilize either only CSNA data or only ECG data. Therefore, it significantly increases the detection performance of CADs by taking advantage of the diversity in different data types and leveraging their strengths. Furthermore, its performance is comparatively better than that of most previously proposed machine and deep learning methods that exclusively used ECG data to diagnose or classify CADs. Additionally, it has a very low implementation time, which is highly desirable for real-time detection of CADs.

CONCLUSIONS

The proposed automated AIHAD technique may serve as an efficient decision-support system to increase physicians' success in fast, early, and accurate diagnosis of CADs. It may be highly beneficial and valuable, particularly for asymptomatic patients, for whom the diagnostic information provided by ECG alone is not sufficient to reliably diagnose the disease. Hence, it may significantly improve patient outcomes by enabling timely treatments and considerably reducing the mortality of cardiovascular diseases (CVDs).

Primary versus iatrogenic (post-PCI) coronary microvascular dysfunction: a wire-based multimodal comparison

BACKGROUND

Although there are studies examining each one separately, there are no data in the literature comparing the magnitudes of the iatrogenic, percutaneous coronary intervention (PCI)-induced, microvascular dysfunction (Type-4 CMD) and coronary microvascular dysfunction (CMD) in the setting of ischaemia in non-obstructed coronary arteries (INOCA) (Type-1 CMD).

OBJECTIVES

We aimed to compare the characteristics of Type-1 and Type-4 CMD subtypes using coronary haemodynamic (resistance and flow-related parameters), thermodynamic (wave energy-related parameters) and hyperemic ECG changes.

METHODS

Coronary flow reserve (CFR) value of <2.5 was defined as CMD in both groups. Wire-based multimodal perfusion markers were comparatively analysed in 35 patients (21 INOCA/CMD and 14 CCS/PCI) enrolled in NCT05471739 study.

RESULTS

Both groups had comparably blunted CFR values per definition (2.03±0.22 vs 2.11±0.37; p: 0.518) and similar hyperemic ST shift in intracoronary ECG (0.16±0.09 vs 0.18±0.07 mV; p: 0.537). While the Type-1 CMD was characterised with impaired hyperemic blood flow acceleration (46.52+12.83 vs 68.20+28.63 cm/s; p: 0.017) and attenuated diastolic microvascular decompression wave magnitudes (p=0.042) with higher hyperemic microvascular resistance (p<0.001), Type-4 CMD had blunted CFR mainly due to higher baseline flow velocity due to post-occlusive reactive hyperemia (33.6±13.7 vs 22.24±5.3 cm/s; p=0.003).

CONCLUSIONS

The perturbations in the microvascular milieu seen in CMD in INOCA setting (Type-1 CMD) seem to be more prominent than that of seen following elective PCI (Type-4 CMD), although resulting reversible ischaemia is equally severe in the downstream myocardium.

Prognostic and diagnostic accuracy of intracoronary electrocardiogram recorded during percutaneous coronary intervention: a meta-analysis

OBJECTIVE

Intracoronary ECG (IC-ECG) recording has been shown to be sensitive and reliable for detecting myocardial viability and local myocardial ischaemia in some studies. But IC-ECG is neither widely used during percutaneous coronary intervention (PCI) nor recommended in guidelines. This up-to-date meta-analysis of published studies was conducted to evaluate the prognostic and diagnostic accuracy of IC-ECG recorded during PCI.

METHODS

Relevant studies were identified by searches of MEDLINE until 19 June 2021. Observational and diagnostic studies which reported the prognostic or diagnostic accuracy of IC-ECG were included. Data were extracted independently by two authors. Summary estimates of clinical outcomes were obtained using a random effects model. Summary diagnostic accuracy was obtained by using a Bayesian bivariate random effects model.

RESULTS

Of the 12 included studies, 7 studies reported the clinical outcomes (821 patients) and 6 studies reported the diagnostic accuracy (485 patients) of IC-ECG. The pooled ORs with 95% CIs of ST-segment elevation recorded by IC-ECG were 4.65 (1.69 to 12.77), 5.08 (1.10 to 23.44), 4.53 (0.79 to 25.90) and 1.83 (0.93 to 3.62) for major adverse cardiac events, myocardial infarction, cardiac death and revascularisation, respectively. The weighted mean difference were 6.49 (95% CIs 3.84 to 9.14) for ejection fraction when ST-segment resolution was recorded, and 0.86 (95% CIs -8.55 to 10.26) when ST-segment elevation was recorded. The pooled sensitivity and specificity of ST-segment elevation were 0.78 (95% credibility intervals 0.64 to 0.89) and 0.87 (95% credibility intervals 0.75 to 0.94), respectively.

CONCLUSIONS

These findings provide quantitative data supporting that IC-ECG had promising diagnostic ability for local myocardial injury, and could predict clinical outcomes.

Meta-Analysis of Dynamic Electrocardiography in the Diagnosis of Myocardial Ischemic Attack of Coronary Heart Disease

Background and Aims

Patients with coronary artery disease (CHD) are prone to early myocardial ischemia; early diagnosis of myocardial ischemia is of great significance in judging disease progression and guiding clinical intervention. However, reports on the accuracy of dynamic electrocardiogram (ECG) in the diagnosis of myocardial ischemia in patients with CHD are inconsistent. The purpose of the current meta-analysis was to analyze the efficacy of ECG in the diagnosis of myocardial ischemia attack in CHD.

Methods

Chinese database (Wanfang, VIP, and CNKI) and English database (PubMed, Web of Science, Embase, SinoMed, and Cochrane Library) were searched. A study on the collection of dynamic ECG in the diagnosis of myocardial ischemic attack of coronary heart disease to extract data and calculate sensitivity (Sen), specificity (Spe), positive likelihood ratio (+LR), negative likelihood ratio (- LR), and diagnostic odds ratio (DOR). Draw summary receiver operating characteristic curves (SROC), and calculate area under curve (AUC). Stata 15 software was used for meta-analysis.

Results

Twenty-seven literatures were included in this study. Meta-analysis results showed that Sen = 0.78 (95% CI: 0.73~0.82), Spe = 0.76 (95% CI: 0.68~0.82), +LR = 2.79 (95% CI: 2.17~3.59), −LR = 0.33 (95% CI: 0.27~0.40), AUC = 0.84 (95% CI: 0.80~0.87), and DOR = 9.66 (95% CI: 6.13~15.21). Subgroup analysis showed that the sensitivity of 12-lead ECG was higher than that of 3-lead ECG. The sensitivity and specificity of ST segment and QTc interphase changes were higher than those of ST segment changes alone (P < 0.05).

Conclusion

Dynamic ECG has high application value in the diagnosis of myocardial ischemia attack of coronary heart disease. But it is difficult to achieve a satisfactory level of use alone. ST segment combined with QTc interval observation can improve the diagnostic accuracy. Synchronous observation of ST segment and QTc interval can improve the diagnostic efficiency.