Data processing pipeline for cardiogenic shock prediction using machine learning.

Introduction: Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS. Methods: We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction. Results: We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization. Conclusion: We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.

Plasmatic apelin shows a promising potential as a screening biomarker for atrial fibrillation.

OBJECTIVES: Purpose of this study was to evaluate properties of apelin, a peptide detectable in peripheral blood, for atrial fibrillation (AF) detection in a diverse population of patients covering a broad spectrum from healthy to polymorbid patients. BACKGROUND: AF is the most common cardiac arrhythmia with constantly increasing incidence and prevalence. Currently available diagnostic tools do not provide sufficient detection rate. Large proportion of patients with AF remains undiagnosed and the possibility of screening at-risk groups would be significantly beneficial. METHODS: We designed this study as a multi-centre retrospective study. Study population included 183 patients. 64 in non-AF and 119 in AF group. RESULTS: Apelin plasma concentration was significantly lower in AF group compared to non-AF group (p < 0.001). Receiver operating characteristic analysis of apelin as a predictor of AF scored area under the curve of 0.79, sensitivity = 0.941 and specificity = 0.578. Multivariate analysis using logistic regression adjusted for age, BMI, apelin, dilated LV, dilated LA, arterial hypertension, and gender showed only apelin and age to be statistically significant contributors for AF. CONCLUSION: Apelin might be a promising biomarker for detecting AF in our study population. These results suggest promising potential of apelin as a screening biomarker for AF (Tab. 2, Fig. 1, Ref. 46). Text in PDF www.elis.sk Keywords: biomarker, apelin, arrhythmia, atrial fibrillation.

Left Ventricular Hypertrophy and Ventricular Tachyarrhythmia: The Role of Biomarkers.

Left ventricular hypertrophy (LVH) refers to a complex rebuilding of the left ventricle that can gradually lead to serious complications-heart failure and life-threatening ventricular arrhythmias. LVH is defined as an increase in the size of the left ventricle (i.e., anatomically), therefore the basic diagnosis detecting the increase in the LV size is the domain of imaging methods such as echocardiography and cardiac magnetic resonance. However, to evaluate the functional status indicating the gradual deterioration of the left ventricular myocardium, additional methods are available approaching the complex process of hypertrophic remodeling. The novel molecular and genetic biomarkers provide insights on the underlying processes, representing a potential basis for targeted therapy. This review summarizes the spectrum of the main biomarkers employed in the LVH valuation.

Risk of bleeding after ground-level falls in elderly patients with atrial fibrillation and warfarin therapy.

OBJECTIVES: The aim of this study was to investigate bleeding risk in patients treated with VKAs after ground-level falls, considering the type and severity of bleeding. METHODS: The study was designed as a retrospective cohort study and included a total of 204 elderly patients aged > 65 years treated for AF continuously with warfarin for more than 3 years. Data were obtained from hospital registries in Bratislava, Slovakia. A 5-year assessment of death/survival was performed to determine mortality. RESULTS: There was no statistically significant difference in severe bleeding (2.13 % with falls vs 2.55 % without, p = 1) and 5-year mortality (45 % and 38 % respectively, p = 0.3987) based on the presence of falls. Multivariate analysis, after adjustment for age, CHA2DS2VASc, HASBLED, stroke history, labile INR and number of falls showed that only HASBLED score was a statistically significant contributor (CI: 1.0245 - 1.0919, p = 0.0007) to severe bleeding. There was statistically significant difference in severe bleeding (18 % vs 0 %, p = 0.0132) between patients suffering from spontaneous and bleeding after falls and also when comparing individual bleeding episodes (12 % vs 1 %, p < 0.0001). There was no statistically significant difference in 5-year mortality between the two groups (43 % vs 42 % respectively, p = 0.3931). CONCLUSIONS: Our results show that occurrence of falls in AF patients treated with VKAs have no significant impact on the incidence of severe bleeding and 5-year mortality and that spontaneous bleeding was associated with a significantly higher risk of severe bleeding compared to bleeding after falling (Tab. 4, Ref. 30).

Advanced glycation end products predict long-term outcome of catheter ablation in paroxysmal atrial fibrillation.

PURPOSE: Oxidative stress is an important contributor to the etiology of atrial fibrillation (AF). Our aim was to study oxidative stress biomarkers in patients undergoing pulmonary vein isolation (PVI) for paroxysmal AF with radiofrequency catheter ablation and to assess its prognostic value in predicting long-term PVI outcome. METHODS: In this prospective cohort study, we included 62 patients (mean age 55±8 years, 12 females and 50 males) with paroxysmal AF and implanted ECG loop recorders who underwent PVI. Plasmatic concentrations of advanced glycation end-products (AGEs), fructosamine, advanced oxidation protein products, and thiobarbituric-acid reacting substances were measured before PVI. AF burden (percentage of time spent in AF) was continually assessed during the follow-up period (1063±271 days). RESULTS: Nineteen patients (31%) were defined as optimal responders (oR) with AF burden < 0.5% after PVI. Remaining 43 patients (69%) were defined as sub-optimal responders. Concentration of AGEs was significantly lower in oR by 3.7 g/g (CI: -6.5 to -1.7; P=0.0003). After adjustment for age, sex, BMI, left atrial size, arterial hypertension, and AF burden before PVI, only low concentration of AGEs remained significantly associated with oR (odds ratio: 1.3; P=0.04). AGEs concentration achieved area under the curve of 0.78 for predicting optimal long-term PVI response. CONCLUSIONS: AGEs concentration before PVI was associated with long-term PVI outcome in patients with paroxysmal AF. Further research will show if this biomarker could contribute to optimal patient selection for catheter ablation.

Association between dose of catecholamines and markers of organ injury early after out-of-hospital cardiac arrest.

BACKGROUND: Catecholamines are recommended as first-line drugs to treat hemodynamic instability after out-of-hospital cardiac arrest (OHCA). The benefit-to-risk ratio of catecholamines is dose dependent, however, their effect on metabolism and organ function early after OHCA has not been investigated. METHODS: The Post-Cardiac Arrest Syndrome (PCAS) pilot study was a prospective, observational, multicenter study. The primary outcomes of this analysis were association between norepinephrine/cumulative catecholamines doses and neuron specific enolase (NSE)/lactate concentration over the first 72 hours after resuscitation. The association was adjusted for proven OHCA mortality predictors and verified with propensity score matching (PSM). RESULTS: Overall 148 consecutive OHCA patients; aged 18-91 (62.9 ± 15.27), 41 (27.7%) being female, were included. Increasing norepinephrine and cumulative catecholamines doses were significantly associated with higher NSE concentration on admission (r = 0.477, p < 0.001; r = 0.418, p < 0.001) and at 24 hours after OHCA (r = 0.339, p < 0.01; r = 0.441, p < 0.001) as well as with higher lactate concentration on admission (r = 0.404, p < 0.001; r = 0.280, p < 0.01), at 24 hours (r = 0.476, p < 0.00; r = 0.487, p < 0.001) and 48 hours (r = 0.433, p < 0.01; r = 0.318, p = 0.01) after OHCA. The associations remained significant up to 48 hours in non-survivors after PSM. CONCLUSIONS: Increasing the dose of catecholamines is associated with higher lactate and NSE concentration, which may suggest their importance for tissue oxygen delivery, anaerobic metabolism, and organ function early after OHCA.

Association Between Apelin and Atrial Fibrillation in Patients With High Risk of Ischemic Stroke.

Background: Atrial fibrillation (AF) is associated with high risk of stroke preventable by timely initiation of anticoagulation. Currently available screening tools based on ECG are not optimal due to inconvenience and high costs. Aim of this study was to study the diagnostic value of apelin for AF in patients with high risk of stroke. Methods: We designed a multicenter, matched-cohort study. The population consisted of three study groups: a healthy control group (34 patients) and two matched groups of 60 patients with high risk of stroke (AF and non-AF group). Apelin levels were examined from peripheral blood. Results: Apelin was significantly lower in AF group compared to non-AF group (0.694 ± 0.148 vs. 0.975 ± 0.458 ng/ml, p = 0.001) and control group (0.982 ± 0.060 ng/ml, p < 0.001), respectively. Receiver operating characteristic (ROC) analysis of apelin as a predictor of AF scored area under the curve (AUC) of 0.658. Apelin's concentration of 0.969 [ng/ml] had sensitivity = 0.966 and specificity = 0.467. Logistic regression based on manual feature selection showed that only apelin and NT-proBNP were independent predictors of AF. Logistic regression based on selection from bivariate analysis showed that only apelin was an independent predictor of AF. A logistic regression model using repeated stratified K-Fold cross-validation strategy scored an AUC of 0.725 ± 0.131. Conclusions: Our results suggest that apelin might be used to rule out AF in patients with high risk of stroke.

Regional differences in presentation characteristics, use of treatments and outcome of patients with cardiogenic shock: Results from multicenter, international registry.

BACKGROUND: Concurrent evidence about cardiogenic shock (CS) characteristics, treatment and outcome does not represent a global spectrum of patients and is therefore limited. The aim of this study was to investigate these regional differences. METHODS: To investigate regional differences in presentation characteristics, treatments and outcomes of patients treated with all types of cardiogenic shock (CS) in a single calendar year on a multi-national level. Consecutive patients from 19 tertiary care hospitals in 13 countries with CS who were treated between January 1, 2018 and December 31, 2018 were enrolled in this study. RESULTS: In total, 699 cardiogenic shock patients were included in this study. Of these patients, 440 patients (63%) were treated in European hospitals and 259 (37%) were treated in Non-European hospitals. Female patients (P<0.01) and patients with a previous myocardial infarction (P=0.02) were more likely to present at Non-European hospitals; whereas older patients (P=0.01) and patients with cardiogenic shock due to acute heart failure (P<0.01) were more likely to present at European hospitals. Vasopressor use was more likely in Non-European hospitals (P=0.04), whereas use of mechanical circulatory support (MCS) was more likely in European hospitals (P<0.01). Despite adjustment for relevant confounders, 30-day in-hospital mortality risk was comparably high in CS patients treated in European vs. Non-European hospitals (hazard ratio 1.08, 95% CI 0.84-1.39, P=0.56). CONCLUSION: Despite marked heterogeneity in characteristics and treatment of CS patients, including fewer use of MCS but more frequent use of vasopressors in Non-European hospitals, 30-day in-hospital mortality did not differ between regions.

No Association Between T-peak to T-end Interval on the Resting ECG and Long-Term Incidence of Ventricular Arrhythmias Triggering ICD Interventions.

BACKGROUND AND OBJECTIVES: Potential of using the T-peak to T-end (TpTe) interval as an electrocardiographic parameter reflecting the transmural dispersion of ventricular repolarization (TDR) to identify patients (pts.) with higher risk of malignant ventricular arrhythmias (MVA) for better selection of candidates for implantable cardioverter-defibrillator (ICD) in primary prevention (PP) of sudden cardiac death (SCD) remains controversial. The primary objective of this study was to investigate the relationship between the TpTe interval in patient's preimplantation resting 12-lead electrocardiogram (ECG) and the incidence of MVA resulting in appropriate ICD intervention (AI). The secondary objective was to assess its relationship to overall mortality. METHODS: A total of 243 consecutive pts. with severe left ventricular (LV) systolic dysfunction after myocardial infarction (MI) with a single-chamber ICD for PP of SCD from one implantation center were included. Excluded were all pts. with any other disease that could interfere with the indication of ICD implantation. Primarily investigated intervals were measured manually in accordance with accepted methodology. Data on ICD interventions were acquired from device interrogation during regular outpatient visits. Survival data were collected from the databases of health insurance and regulatory authorities. RESULTS: We did not find a significant relationship between the duration of the TpTe interval and the incidence of MVA (71.5 ms in pts. with MVA vs. 70 ms in pts. without MVA; p = 0.408). Similar results were obtained for the corrected TpTe interval (TpTec) and the ratio of TpTe to QT interval (76.3 ms vs. 76.5 ms; p = 0.539 and 0.178 vs. 0.181; p = 0.547, respectively). There was also no significant difference between the duration of TpTe, TpTec and TpTe/QT ratio in pts. groups by overall mortality (71.5 ms in the deceased group vs. 70 ms in the survivors group; HR 1.01; 95% CI, 0.99-1.02; p = 0.715, 76.3 ms vs. 76.5 ms; HR 1.01; 95% CI, 0.99-1.02; p = 0.208 and 0.178 vs. 0.186; p = 0.116, respectively). CONCLUSION: This study suggests no significant association of overall or MVA-free survival with ECG parameters reflecting TDR (TpTe, TpTec) in patients with systolic dysfunction after MI and ICD implanted for primary prevention.

The three-dimensional speckle tracking echocardiography in distinguishing between ischaemic and non-ischaemic aetiology of heart failure.

AIMS: The aim of this pilot study was to compare selected three-dimensional speckle tracking echocardiography (3D STE) parameters in patients with ischaemic and non-ischaemic aetiology of heart failure (HF) and to identify indices that can differentiate the two pathologies. METHODS AND RESULTS: Forty patients with left ventricular ejection fraction (LVEF) ≤ 40% were included to the study: 20 patients (age 63 ± 9.0 years, LVEF 29.0 ± 11.3%) with ischaemic cardiomyopathy and 20 patients (age 64.0 ± 11.0 years, LVEF 27.3 ± 7.5%) with non-ischaemic cardiomyopathy. All patients underwent two-dimensional (2D) and three-dimensional (3D) transthoracic echocardiography. Standard echocardiographic parameters, global longitudinal strain, and rotational parameters of left ventricle (LV) were assessed using 3D speckle tracking (3D STE). There were no differences in standard and STE parameters between the two groups. Among rotational parameters, the LV apical rotation (4.9 ± 3.5° vs. 2.3 ± 2.4°, P = 0.0022) was significantly higher in patients with ischaemic HF. Among all echocardiographic parameters, a cut-off value of 3.28° (area under the curve 0.78; 95% confidence interval, 0.62 to 0.93) was able to distinguish the ischaemic and non-ischaemic aetiology of HF with a sensitivity of 80% and specificity of 75%. CONCLUSIONS: This is the first study that compares 3D STE parameters between patients with ischaemic and non-ischaemic cardiomyopathy. It was proved that the apical rotation was significantly higher in patients with ischaemic cardiomyopathy. Our findings suggest that 3D STE might be useful in non-invasive differentiation between ischaemic and non-ischaemic aetiology of HF.

Molecular Mechanisms, Diagnostic Aspects and Therapeutic Opportunities of Micro Ribonucleic Acids in Atrial Fibrillation.

Micro ribonucleic acids (miRNAs) are short non-coding RNA molecules responsible for regulation of gene expression. They are involved in many pathophysiological processes of a wide spectrum of diseases. Recent studies showed their involvement in atrial fibrillation. They seem to become potential screening biomarkers for atrial fibrillation and even treatment targets for this arrhythmia. The aim of this review article was to summarize the latest knowledge about miRNA and their molecular relation to the pathophysiology, diagnosis and treatment of atrial fibrillation.

Social media in cardiovascular medicine: a contemporary review.

Social media increasingly impact both the private and professional lives of the majority of the population, including individuals engaged in cardiovascular healthcare and research. Healthcare providers across the world use social media platforms such as Twitter or Facebook to find medical and scientific information, to follow scientific meetings, to discuss individual clinical cases with colleagues, and to engage with patients. While social media provide a means for fast, interactive and accessible communication without geographic boundaries, their use to obtain and disseminate information has limitations and the potential threats are not always clearly understood. Governance concerns include a lack of rigorous quality control, bias due to the pre-selection of presented content by filter algorithms, and the risk of inadvertent breach of patient confidentiality. This article provides information and guidance regarding the role and use of social media platforms in cardiovascular medicine, with an emphasis on the new opportunities for the dissemination of scientific information and continuing education that arise from their responsible use.