ECG Score Research Articles

Multimodal Data Integration to Predict Atrial Fibrillation

Abstract Background Many studies have utilized data sources such as clinical variables, polygenic risk scores, ECG, and plasma proteins to predict the risk of atrial fibrillation (AF). However, few studies have integrated all four sources from a single study to comprehensively assess AF prediction. Methods We included 8374 (Visit 3, 1993-1995) and 3,730 (Visit 5, 2011-2013) participants from the Atherosclerosis Risk in Communities Study to predict incident AF and prevalent (but covert) AF. We constructed a 1) clinical risk score using CHARGE-AF clinical variables, 2) polygenic risk score using pre-determined weights, 3) protein risk score using penalized and regularized logistic regression, and 4) ECG risk score from convolutional neural network. Risk prediction performance was measured using regularized logistic regression. Results After a median follow up of 15.1 years, 1910 AF events occurred since Visit 3 and 229 participants had prevalent AF at Visit 5. The AUC improved from 0.660 to 0.752 (95% CI, 0.741-0.763) and from 0.737 to 0.854 (95% CI, 0.828-0.880) after addition of polygenic risk score to the CHARGE-AF clinical variables for predicting incident and prevalent AF, respectively. Further addition of ECG and protein risk scores improved the AUC to 0.763 (95% CI, 0.753-0.772) and 0.875 (95% CI, 0.851-0.899) for predicting incident and prevalent AF, respectively. Conclusions A combination of clinical and polygenic risk scores was the most effective and parsimonious approach to predicting AF. Further addition of an ECG risk score or protein risk score provided only modest incremental improvement for predicting AF.

The added value of deep learning to submaximal exercise electrocardiogram for the 10-year prediction of major adverse cardiovascular and cerebrovascular events

Abstract Background The added value of exercise ECG data to traditional risk factors in predicting cardiovascular events remains unclear. Deep learning of ECG signals has demonstrated state-of-the-art performance in detecting subtle abnormalities indicative of cardiovascular disease. We investigated whether deep learning analysis of exercise ECGs could improve the prediction of major cardiovascular and cerebrovascular events (MACCE) with respect to established risk models in a large population-based cohort. Purpose To assess the added value of submaximal exercise ECG measurements to established cardiovascular risk prediction models. Methods We obtained ECG recordings from 41,076 UK Biobank participants without cardiovascular disease (CVD) who underwent a submaximal exercise ECG test. We obtained ECG recordings from 41,076 UK Biobank participants without cardiovascular disease (CVD) who underwent a submaximal exercise ECG test. We created two deep neural network ECG risk scores: one derived from conventional ECG parameters, measured at rest, peak exercise and late-stage recovery, and another based on the complete ECG (Q-ECG). We assessed the added value of conventional ECG parameters and Q-ECG risk scores to the UK's current prediction algorithm (QRISK3). We estimate the association between ECG parameters and MACCE, using Cox Proportional hazard models, following adjustment for traditional risk factors. All models were internally validated via 5-fold cross-validation and 1000 bootstrap iterations. Predictive performance was evaluated using Harrel's C-index, Net Reclassification Index (NRI) and net benefit. Findings: Incident MACCE was reported in 4,082 (9.9%) individuals in the study population and 3,463(9.7%) individuals with valid ECG parameters over a median follow-up period of 12.5 years. We found combined conventional ECG and Q-ECG scores were independently associated with MACCE, following adjustment for multiple testing: adjusted hazard ratio [HZ] = 1.76 (95% CI:1.63-1.91); HZ = 1.14 (95% CI:1.10-1.18), respectively, per standard deviation increase. Both conventional ECG parameters and Q-ECG were predictive of MACCE, independent of clinical risk factors, C-index = 0.64 (95%CI 0.63-0.65); net benefit = 0.09(95% CI 0.07 - 0.11) and C-index = 0.56 (95% CI 0.55-0.57); net benefit = 0.07(95% CI 0.05 - 0.09). ECG measurement's modestly improved model discrimination over the bassline QRISK3 risk score when combined with QRISK3 risk factors for conventional markers and Q-ECG score, respectively; ΔC-index 0.03 (95% CI: 0.02 – 0.04) and ΔC-index 0.03 (95% CI: 0.02 – 0.03); However, we observed no significant improvements in classification at the current recommended threshold of 10%. Conclusion In individuals without a history of prior cardiovascular disease, ECG measures independently predict the risk of MACCE. When combined with QRISK3, neural-network-derived ECG risk scores marginally improve cardiovascular risk prediction over QRISK3.

Ion Channel Diseases as a Cause of Sudden Cardiac Death in Young People: Aspects of Their Diagnosis, Treatment, and Pathogenesis.

Sudden cardiac death (SCD) is the death of an apparently healthy person within one hour of the onset of symptoms, or within 24 hours of last being seen alive and well-with no evidence of an extra-cardiac cause. In autopsied cases, SCD is defined as the natural unexpected death of unknown or cardiac cause. The reported incidence figures for SCD vary widely. This review is based on clinical registry studies, meta-analyses, randomized controlled trials, systematic reviews, and current guidelines that were retrieved by a selective search in PubMed employing the key words "channelopathy," "Brugada syndrome," "long QT syndrome," "catecholaminergic polymorphic ventricular tachycardia," "short QT syndrome," and "early repolarization." Approximately 18% of cases of SCD in young persons are associated with cardiac channelopathy. The most common ion channel diseases affecting the heart are long QT syndrome and Brugada syndrome. The diagnosis is established by specific ECG abnormalities in the absence of structural heart disease. These can be unmasked by various maneuvers, e.g., the administration of sodium-channel blockers in Brugada syndrome. Imaging studies such as echocardiography, coronary angiography, and computed tomography are used to rule out structural heart disease and coronary artery disease. Long-term ECG and risk stratification scores can be useful aids to therapeutic decision-making. For some of these diseases, it is advisable for the patient to avoid particular triggers of ECG changes and cardiac arrhythmias in his or her everyday life. The near relatives of persons with congenital ion channel diseases should undergo clinical and genetic screening to protect them from SCD. The affected families should be investigated systematically so that appropriate diagnoses and treatments can be established.

External validation of the preHEART score and comparison with current clinical risk scores for prehospital risk assessment in patients with suspected NSTE-ACS

BackgroundEmergency Medical Services (EMS) studies have shown that prehospital risk stratification and triage decisions in patients with suspected non-ST-elevation acute coronary syndrome (NSTE-ACS) can be improved using clinical risk scores...

Acute pulmonary embolism pretest probability estimation by d-dimer test, our modified, new ECG score and clinical prediction rules

ObjectivesWe investigated whether a sufficiently sensitive D-dimer test could exclude acute pulmonary embolism (acPE) as a stand-alone diagnostic test and compared our previously published, modified ECG score with the Wells and Geneva scores in the estimation of acPE pretest probability. MethodsWe retrospectively evaluated 345 patients who underwent chest CT angiography (CTA) for the suspicion of acPE. The pretest probability of acPE was assessed in 120 D-dimer negative [DD (−)] and 225 D-dimer positive [DD (+)] patients. ResultsChest CTA verified acPE in 57/345 (16.5 %) patients and in 1/120 (0.8 %) DD (−) patient. In DD (−) patients the test accuracy (TA) and specificity (SP) of the ECG score (98 %, 99 %) were better than those of the Wells score (92.5 %, 92.4 %) (p = 0.063 and p < 0.05 respectively) and the Geneva score (76.7 %, 76.5 %) (p < 0.001 for both), the Wells score TA and SP were greater than those of the Geneva score (p < 0.001 for both). In DD (+) patients the SPs, TAs and positive predictive values (PPV) of the ECG score (94 %, 78.6 %, 69 %) and the Wells score (91.8 %, 75.1 %, 48 %) were greater than those of the Geneva score (71.3 %, 64.9 %, 38.2 %) (p < 0.001 for both SP and TA respectively, and p < 0.001 for PPV of the ECG score vs. the Geneva score and p < 0.05 for PPV of the Wells score vs. Geneva score), their sensitivities (SE) (36.4 %, 23.6 %) were less than that of the Geneva score (47.5 %) (p < 0.05 and p < 0.001 respectively). The ECG score's TA in a trend, its SE and PPV were significantly (p < 0.01 and p < 0.001) better than those of the Wells score. ConclusionIn contrast to the current guidelines, a stand-alone high sensitivity DD (−) test, without prediction rules, could reliably exclude acPE. Our ECG score slightly outperformed the Wells score, the ECG score and Wells score far outperformed the Geneva score in the estimation of acPE pretest probability. An acPE diagnosis with the ECG score, in addition to the supportive diagnosis with the clinical prediction rules, may further increase the chance of true DD positivity.

European Society of Cardiology 0/1-hour algorithm (high-sensitivity cardiac troponin T) performance across distinct age groups

BackgroundTo determine if the European Society of Cardiology 0/1-hour (ESC 0/1-h) algorithm with high-sensitivity cardiac troponin T (hs-cTnT) meets the ≥99% negative predictive value (NPV) safety threshold for 30-day cardiac...

Evaluation of the Relationship between QT Interval in ECG and GRACE Score Amount of Hospitalized Patients with NSTEMI.

Non-ST-elevation myocardial infarction (NSTEMI) is a significant component of acute coronary syndrome (ACS) and typically exhibits a relative incidence that is more than double that of ST-segment elevation myocardial infarction (STEMI). Data obtained from the International Long QT Syndrome Registry indicate that the risk of developing malignant arrhythmias in individuals with long QT syndrome is exponentially associated with the duration of the QTc interval. Therefore, the aim of this study was to assess the potential inclusion of prolonged QTc as a prognostic risk factor in NSTEMI patients. A cross-sectional study was conducted on patients with NSTEMI diagnosis admitted to the Bu-Ali Hospital of Qazvin between April 2021 and September 2021 by census method. The QT interval was measured in the electrocardiogram at admission. The documented grace score was calculated and its relationship with the corrected QTc interval was estimated using the Hodges formula. Finally, the relationship between QTc and GRACE score was investigated as a prognostic factor in ACS patients. Relationships were assessed by using both the T-test and the chi-square test. A total of 60 patients (31.7% females, 63.8% males) with a mean age of 63 ± 12.7 years were evaluated. Most of the patients (68.3%) were at low risk regarding the Grace score category. In evaluating the relationship between QTc in the electrocardiogram at admission with total GRACE score, the Pearson correlation results were significant and there was a positive relationship between these two factors (r = 0.497, P < 0.001). This study revealed a significant relationship between the QTc interval of patients and the GRACE Score. It was shown patients' QTc can be a predictive factor of patients' mortality.

Erratum: HCC EV ECG score: An extracellular vesicle-based protein assay for detection of early-stage hepatocellular carcinoma.

Erratum: HCC EV ECG score: An extracellular vesicle-based protein assay for detection of early-stage hepatocellular carcinoma.

Change in left ventricular function and outcomes following high-risk percutaneous coronary intervention with Impella-guided hemodynamic support.

High-risk percutaneous coronary interventions (HRPCI) are a potential treatment option for patients with reduced left ventricular ejection fraction (LVEF) and coronary artery disease. The extent to which such intervention is coupled with improvement in LVEF and associated with favorable outcomes is unknown. We aimed to characterize the incidence and correlates of LVEF improvement after Impella-guided HRPCI, and compare clinical outcomes in patients with versus without LVEF improvement. Data on consecutive patients undergoing Impella-guided HRPCI from a single center registry were analyzed. LVEF-improvement was defined as an absolute increase of LVEF of ≥10% measured at ≥30-days after intervention. The primary outcome was a composite of all-cause death, myocardial infarction or target vessel revascularization within 1-year. Out of 161 consecutive patients undergoing Impella-guided HRPCI from June 2008 to December 2017, 43% (n = 70) demonstrated LVEF-improvement (baseline LVEF of 25.09 ± 6.19 to 33.30 ± 11.98 post intervention). Patients without LVEF-improvement had higher frequency of previous MI (61.5% vs. 37.1%, p = 0.0021), Q-waves on ECG (17.6% vs. 5.7%, p = 0.024) and higher SYNTAX scores (30.8 ± 17.6 vs. 25.2 ± 12.2; p = 0.043). After correction of these confounders by multivariable analysis, no significant differences were found regarding the composite endpoint in patients with versus without LVEF-improvement (34.9% vs. 38.3%; p = 0.48). In this single-center retrospective analysis, we report the following findings. First, LVEF improvement of at least 10% was documented in over 40% of patients undergoing Impella supported high-risk PCI. Second, a history of MI, Q-waves on admission ECG, and higher baseline SYNTAX scores were independent correlates of no LVEF improvement. Third, one year rates of adverse CV events were substantial and did not vary by the presence or absence of LVEF improvement Prospective studies with longer follow-up are needed to elucidate the impact of LVEF improvement on clinical outcomes.

Identification of an effective and safe bolus dose and lockout time for patient-controlled sedation (PCS) using dexmedetomidine in dental treatments: a randomized clinical trial.

This study investigated a safe and effective bolus dose and lockout time for patient-controlled sedation (PCS) with dexmedetomidine for dental treatments. The depth of sedation, vital signs, and patient satisfaction were investigated to demonstrate safety. Thirty patients requiring dental scaling were enrolled and randomly divided into three groups based on bolus doses and lockout times: group 1 (low dose group, bolus dose 0.05 µg/kg, 1-minute lockout time), group 2 (middle dose group, 0.1 µg/kg, 1-minute), and group 3 (high dose group, 0.2 µg/kg, 3-minute) (n = 10 each). ECG, pulse, oxygen saturation, blood pressure, end-tidal CO2, respiratory rate, and bispectral index scores (BIS) were measured and recorded. The study was conducted in two stages: the first involved sedation without dental treatment and the second included sedation with dental scaling. Patients were instructed to press the drug demand button every 10 s, and the process of falling asleep and waking up was repeated 1-5 times. In the second stage, during dental scaling, patients were instructed to press the drug demand button. Loss of responsiveness (LOR) was defined as failure to respond to auditory stimuli six times, determining sleep onset. Patient and dentist satisfaction were assessed before and after experimentation. Thirty patients (22 males) participated in the study. Scaling was performed in 29 patients after excluding one who experienced dizziness during the first stage. The average number of drug administrations until first LOR was significantly lower in group 3 (2.8 times) than groups 1 and 2 (8.0 and 6.5 times, respectively). The time taken to reach the LOR showed no difference between groups. During the second stage, the average time required to reach the LOR during scaling was 583.4 seconds. The effect site concentrations (Ce) was significantly lower in group 1 than groups 2 and 3. In the participant survey on PCS, 8/10 in group 3 reported partial memory loss, whereas 17/20 in groups 1 and 2 recalled the procedure fully or partially. PCS with dexmedetomidine can provide a rapid onset of sedation, safe vital sign management, and minimal side effects, thus facilitating smooth dental sedation.

Echocardiography and Electrocardiography in Detecting Atrial Cardiomyopathy: A Promising Path to Predicting Cardioembolic Strokes and Atrial Fibrillation

(1) Background: Atrial cardiomyopathy constitutes an intrinsically prothrombotic atrial substrate that may promote atrial fibrillation and thromboembolic events, especially stroke, independently of the arrhythmia. Atrial reservoir strain is the echocardiography marker with the most robust evidence supporting its prognostic utility. The main aim of this study is to identify atrial cardiomyopathy by investigating the association between left atrial dysfunction in echocardiography and P-wave abnormalities in the surface electrocardiogram. (2) Methods: This is a community-based, multicenter, prospective cohort study. A randomized sample of 100 patients at a high risk of developing atrial fibrillation were evaluated using diverse echocardiography imaging techniques, and a standard electrocardiogram. (3) Results: Significant left atrial dysfunction, expressed by a left atrial reservoir strain &lt; 26%, showed a relationship with the dilation of the left atrium (p &lt; 0.001), the left atrial ejection fraction &lt; 50% (p &lt; 0.001), the presence of advanced interatrial block (p = 0.032), P-wave voltage in lead I &lt; 0.1 mV (p = 0.008), and MVP ECG score (p = 0.036). (4) Conclusions: A significant relationship was observed between left atrial dysfunction and the presence of left atrial enlargement and other electrocardiography markers; all of them are non-invasive biomarkers of atrial cardiomyopathy.

Early rule-out of major adverse cardiac events in acute chest pain patients using a risk score and self-reported computerised history taking

Abstract Introduction Risk scores, such as the History, ECG, Age, Risk factors, and Troponin (HEART) score, Emergency Department Assessment of Chest Pain Score Accelerated Diagnostic Protocol (EDACS-ADP), and Troponin-only Manchester Acute Coronary Syndrome (T-MACS), are recommended for the evaluation of acute chest pain patients. Obtaining a structured medical history by self-reported computerised history taking (CHT) may provide an automated and improved risk assessment in the emergency department (ED). Purpose We aimed to determine the diagnostic accuracy of three well-established acute chest pain risk scores using CHT to predict 30-day major adverse cardiovascular event (MACE). Methods Prospective cohort of clinically stable patients aged ≥18 years presenting with a chief complaint of chest pain and an ECG not indicating an acute coronary syndrome (ACS), at a tertiary hospital ED during 2017–2019. Medical histories were self-reported on a tablet using a CHT program (Clinical Expert Operating System, CLEOS), owned by a public university. With &amp;gt;17,000 decision nodes, CLEOS mimics a physician interview and tailors each interview depending on previous answers. Data acquired is in a binary structured format and can be used for input in clinical decision support systems. The HEART score, EDACS-ADP, and T-MACS were calculated from the CHT and the electronic health records (EHR). Relevant EHR data, including medical history, vital signs, and lab data, was extracted manually by the research staff in a predetermined standardised way. The EHR was subsequently reviewed for ACS and intervention procedure International Classification of Diseases (ICD) codes for any 30-day 3-point MACE. Results Of the 1,000 consecutive participants enrolled (mean age 55±17 years; 54% women), the HEART score, EDACS-ADP, and T-MACS could be calculated in 65%, 65% and 68%, respectively using only CHT acquired data. Main reasons for premature termination of the CHT were early discharge from ED or getting tired. A 30-day MACE occurred in 7.2% of the total population. The sensitivity, specificity, positive and negative predictive values of any 30-day MACE are presented in Table 1. The diagnostic accuracy for each risk score using CHT was similar to previous studies, where physician-collected data was used. Conclusions CHT can provide relevant risk scores in a majority of acute chest pain patients, and allow a safe and early rule-out of a 30-day MACE. The use of CHT may enable automation and improve the management of a large proportion of low-risk acute chest pain patients in the ED.Example of a question in the CHT program

Atrial and ventricular arrhythmia predictors with electrocardiographic parameters in myocardial infarction with non-obstructive coronary artery disease (MINOCA).

The clinical importance and recognition of myocardial infarction with non-obstructive coronary artery disease (MINOCA) is increasing. Nevertheless, no studies are investigating the risk of atrial fibrillation and ventricular arrhythmia in MINOCA patients. This study aimed to determine the risk of arrhythmia with electrocardiographic predictors in MINOCA patients. In this study, patients diagnosed with MINOCA and stable out-patients without significant lesions in their coronary arteries were compared. Morphology-voltage-Pwave duration electrocardiography (MPV ECG) score was used to determine atrial arrhythmia risk. QT interval and QT dispersion Tpeak-Tend time and Tpeak-Tend/QT interval were used to determine ventricular arrhythmia risk. A total of 155 patients were included in our study. Seventy-seven of these patients were in the MINOCA group. There was no statistically significant difference between the two groups in MPV ECG score (1.95 ± 1.03 vs 1.68 ± 1.14, p = 0.128). P-wave voltage, P-wave morphology and P-wave duration, which are components of the MPV ECG score, were not statistically significantly different. The QRS complex duration (90.21 ± 14.87 vs 82.99 ± 21.59 ms, p = 0.017), ST interval (271.95 ± 45.91 vs 302.31 ± 38.40 ms, p < 0.001), corrected QT interval (438.17 ± 43.80 vs 421.41 ± 28.39, p = 0.005) and QT dispersion (60.75 ± 22.77 vs 34.19 ± 12.95, p < 0.001) were statistically significantly higher in the MINOCA group. The Tpeak-Tend (89.53 ± 32.16 vs 65.22 ± 18.11, p < 0.001), Tpeak-Tend/QT interval (0.2306 ± 0.0813 vs 0.1676 ± 0.0470, p < 0.001) and Tpeak-Tend/corrected QT interval (0.2043 ± 0.6997 vs 0.1551 ± 0.4310, p < 0.001) ratios were also significantly higher in patients with MINOCA. In the MINOCA patients, there was no increase in the risk of atrial fibrillation based on ECG predictors. However, it was shown that there could be a significant increase in the risk of ventricular arrhythmia. We believe this study could be helpful for specific recommendations concerning duration of hospitalisation and follow up in MINOCA patients.

HEART versus GRACE Score in Predicting the Outcomes of Patients with Acute Coronary Syndrome; a Systematic Review and Meta-Analysis.

Several scoring systems have been proposed to predict the outcomes of patients with ischemic heart disease. Global Registry of Acute Coronary Events (GRACE) and History, ECG, Age, Risk Factors, and Troponin (HEART) scores are two of the more widely used risk prediction tools in patients with acute coronary syndrome (ACS). The present systematic review and meta-analysis aimed to compare the value of GRACE and HEART scores in the outcome prediction of ACS patient. The online databases of Medline, Embase, Web of Science, and Scopus were search until September 2022 for articles directly comparing GRACE and HEART scores value in prediction of outcome in patients with ACS. GRACE score cut-offs were categorized into two groups of less than and equal to 100 and more than 100, and HEART score cut-offs were categorized into three groups of less than 4, equal to 4, and more than 4. Investigated outcomes were major adverse cardiovascular events (MACE), acute myocardial infraction (AMI) and all-cause mortality. 25 articles were included. The sensitivity and specificity of the GRACE score for prediction of MACE were 0.96 and 0.26 for cut-offs of ≤ 100, and 0.58 and 0.69 for cut-offs of >100, respectively. The sensitivity and specificity of the HEART score for prediction of MACE were 0.99 and 0.16 for cut-offs less than 4, 0.93 and 0.47 for equal to 4, and 0.77 and 0.78 for cut-offs greater than 4. GRACE score was shown to be predictive of AMI with sensitivity and specificity of 0.95 and 0.29, respectively. The analysis for the value of HEART score in the prediction of AMI a sensitivity and specificity of 0.94 and 0.48, respectively. The risk scores were not found to be suitable predictors of all-cause mortality. The results demonstrated the low specificity of GRACE and HEART scores in predicting the MACE, AMI and all-cause mortality, irrespective of the utilized cut-off. Considering the acceptable sensitivity of two scores in predicting the MACE and AMI, these scores were more suitable to be used as a rule-out tool for identification of ACS patients with low risk of developing adverse outcomes.

Environment, Social and Governance Reporting and Firm Performance: Evidence from GCC Countries

The aim of this research is to investigate the impact of ESG reporting on firm performance, Environment, Social and Governance (ESG) are a triple-bottom-line approach that combines financial gains with adhering to social, governance and environmental norms. In addition, the study's objective is to determine the relationship between ESG disclosure and firm performance in Gulf Cooperation Council (GCC) listed companies. ESG scores and other samples for 91 firms from 6 GCC countries were collected for this purpose over a three-year period from 2019, 2020 and 2021. The sample comprised nine diverse industries. The dependent variables are Return on Assets (ROA) and market capitalization , experimental variables are environmental pillar score, social pillar score, governance pillar score and overall ESG score and the control variables: size, leverage. The study found that ESG scores and governance pillar scores have a positive impact on a firm’s market value but environmental and social pillar scores were not significant. In addition, there is a strong relationship between all ESG disclosures and ECG scores.

Abstract 11648: ECG-Derived Features Enable Prediction of Sudden Death in Ischemic Cardiomyopathy

Introduction: Low left ventricular ejection fraction (LVEF) is an imperfect predictor of sudden cardiac death (SCD) in patients with ischemic cardiomyopathy. Novel features identified via automated ECG analysis might improve the prediction of sudden cardiac death risk. Hypothesis: We hypothesized that machine learning of the ECG can be used to predict SCD. Methods: We studied 5603 ECG Lead V1 beats in 41 patients (64±10 Y) with coronary disease and LVEF≤40% in steady-state pacing. Patients were randomly allocated to independent training and test cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines were trained to predict mortality at 3Y from the top 20 features derived from these beats (Fig C). Patient-level predictions were made by computing an ECG score that indicates the proportion of test set beats in that patient computed by the beat-level model to predict SCD. Results: Fig A shows the data flow in the study. Beat-level predictions in the validation (n=1678 Lead I beats) cohorts yielded c-statistics of 0.78 for SCD (95% CI, 0.62-0.91). In multivariable models, c-statistic was 0.87 for SCD (95% CI, 0.76-0.98) (Fig B). Conclusions: Machine learning of the ECG reveals novel predictors of SCD risk in patients with ischemic cardiomyopathy. This tool may improve risk stratification and allocation for ICD therapy beyond LVEF alone.

Cardiovascular screening prior to stem cell transplantation in the United Kingdom.

Cardiovascular screening prior to stem cell transplantation in the United Kingdom.

HCC EV ECG score: An extracellular vesicle-based protein assay for detection of early-stage hepatocellular carcinoma.

The sensitivity of current surveillance methods for detecting early-stage hepatocellular carcinoma (HCC) is suboptimal. Extracellular vesicles (EVs) are promising circulating biomarkers for early cancer detection. In this study, we aim to develop an HCC EV-based surface protein assay for early detection of HCC. Tissue microarray was used to evaluate four potential HCC-associated protein markers. An HCC EV surface protein assay, composed of covalent chemistry-mediated HCC EV purification and real-time immuno-polymerase chain reaction readouts, was developed and optimized for quantifying subpopulations of EVs. An HCC EV ECG score, calculated from the readouts of three HCC EV subpopulations ( E pCAM + CD63 + , C D147 + CD63 + , and G PC3 + CD63 + HCC EVs), was established for detecting early-stage HCC. A phase 2 biomarker study was conducted to evaluate the performance of ECG score in a training cohort ( n =106) and an independent validation cohort ( n =72).Overall, 99.7% of tissue microarray stained positive for at least one of the four HCC-associated protein markers (EpCAM, CD147, GPC3, and ASGPR1) that were subsequently validated in HCC EVs. In the training cohort, HCC EV ECG score demonstrated an area under the receiver operating curve (AUROC) of 0.95 (95% confidence interval [CI], 0.90-0.99) for distinguishing early-stage HCC from cirrhosis with a sensitivity of 91% and a specificity of 90%. The AUROCs of the HCC EV ECG score remained excellent in the validation cohort (0.93; 95% CI,0.87-0.99) and in the subgroups by etiology (viral: 0.95; 95% CI,0.90-1.00; nonviral: 0.94; 95% CI,0.88-0.99). HCC EV ECG score demonstrated great potential for detecting early-stage HCC. It could augment current surveillance methods and improve patients' outcomes.

Machine-learned physiological signatures from the ECG predict sudden death in ischemic cardiomyopathy

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Institute of Health (NIH) Background Low left ventricular ejection fraction (LVEF) is an imperfect predictor of sudden cardiac death (SCD) in patients with ischemic cardiomyopathy. Novel features from the ECG might provide a readily available tool to better predict risk. Purpose We hypothesized that machine learning (ML) of the ECG can be used to predict SCD, and the ML-learned ECG features could be referenced to interpretable intracardiac signals (monophasic action potentials: MAP) to provide mechanistic insights. Methods We studied 5603 ECG Lead V1 beats in 41 patients (64±10 Y) with coronary disease and LVEF≤40% in steady-state pacing. Patients were randomly allocated to independent training and test cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines were trained to predict mortality at 3Y from the top 20 features derived from these beats. Patient-level predictions were made by computing an ECG score that indicates the proportion of test set beats in that patient computed by the beat-level model to predict death. Explainability analysis was performed using the arithmetic mean of MAP and ECG beats that predicted SCD versus those that predicted survival. Results Fig 1A. shows ECG lead V1 and MAP in a 79 Y man with LVEF 29%. Fig 1B shows the dataflow in the study. Predictive accuracies of ML models were 78 and 70% and optimal with 20 features for both ECG and MAP models respectively (Fig. 1C). Beat-level predictions in the validation (n=1678 Lead I beats) cohorts yielded c-statistics of 0.78 with the ECG (95% CI, 0.62–0.91) and 0.75 with MAPs (95% CI, 0.75-0.76) (data not shown). In multivariable patient-level models, c-statistic was 0.87 with ECGs (95% CI, 0.76-0.98) (Fig 1D) and 0.82 with MAPs. On explainability analysis, ECG beats that predicted SCD (Fig 2; red) had lower amplitude and more notched T-waves in lead V1 than beats that predicted no SCD (Fig 2; blue). MAP that predicted SCD had higher repolarization current at the same time points. Both QT duration (ECG) and action potential duration (MAP) did not differ (Fig 2). Conclusions Machine learning of the ECG reveals novel predictors of SCD risk in patients with ischemic cardiomyopathy analogous to those identified in intracardiac signals. This approach can be used as a point-of-care ECG risk tool to improve risk stratification and allocation for ICD therapy beyond LVEF alone and may shed insights into the pathophysiology of ventricular arrhythmias.

Computerized history taking improves HEART score determination in acute chest pain patients

Abstract Funding Acknowledgements Type of funding sources: Foundation. Main funding source(s): Robert Bosch Stiftung (Stuttgart, Germany) Region Stockholm (ALF project; Stockholm, Sweden) Introduction Chest pain is a common chief complaint in emergency departments (EDs). The Acute Cardiovascular Care Association recommends the use of History, ECG, Age, Risk factors, and Troponin (HEART) score for risk stratification. In hectic and overcrowded EDs computerized history taking (CHT) is one structured way for collecting the components of HEART score, which include medical history (H- and R-variables). Purpose To determine the proportion of acute chest pain patients where CHT can be used to calculate HEART score, and what interrater reliability the included variables have with physician acquired medical history. Methods Prospective cohort study with acute chest pain patients self-reporting medical histories using a CHT program (Clinical Expert Operating System, CLEOS) on a tablet. CLEOS, with &amp;gt;17,000 decision nodes, mimics a physician interview and tailors each interview continuously depending on previous answers. Clinically stable women and men aged &amp;gt;18 years with a chief complaint of chest pain and non-diagnostic ECG or serum markers for acute coronary syndrome were enrolled. Patients unable to carry out a CHT interview (e.g., severe impaired vision or confusion) were excluded. As recommended in regional guidelines a modified HEART score using the traditional classification of anginal symptoms, i.e. 1) central chest pain, 2) provoked by physical exertion and/or emotional stress, and 3) relieved by rest and/or nitrates, and traditional risk factors was used (see Table 1). Observations to each discrete H- and R-variable and medical history data were extracted from electronic health records (EHR) and the CHT database by the research staff. Cohen’s kappa statistics and interpretation according to Landis &amp; Koch was used to describe the interrater reliability. Results A total of 1,000 consecutive patients were enrolled in one tertiary university hospital ED during 2017–2019 (mean age 55±17 years; 54% women), comparable to the general chest pain population (mean age 58±19 years; 50% women). A complete HEART score could be calculated in 60% of patients (H-variable 91%; R-variable 60%). Registered observations from EHR and CHT and interrater reliability data are presented in Table 1. Interrater reliability for the H-variable (classical anginal symptoms) was slight to moderate (kappa 0.19-0.44) and the R-variable (traditional risk factors) was moderate to almost perfect (kappa 0.56-0.88). Conclusions HEART score could be calculated in a majority of acute chest pain patients by the use of CHT. Interrater reliability was high for traditional risk factors but low to moderate for classical anginal symptoms. Our ongoing studies assess whether CHT combined with a risk score such as HEART score in an acute setting can be useful for improved risk stratification and, more important, to improve clinical outcomes.