Early Diagnosis Of Heart Failure Research Articles

Prognostic and diagnostic implications of impaired rest and exercise-stress left atrial compliance in heart failure with preserved ejection fraction: Insights from the HFpEF Stress Trial

Abstract Background With emerging therapies, early diagnosis of heart failure with preserved ejection fraction (HFpEF) comes to the fore. Whilst the reference standard of exercise-stress right heart catheterisation is well established, the clinical routine struggles between feasibility of exercise-stress and diagnostic accuracy of available tests. Methods The HFpEF Stress Trial (DZHK-17) prospectively enrolled 75 patients with exertional dyspnoea and echocardiographic signs of diastolic dysfunction (E/e’>8) who underwent simultaneous rest and exercise-stress echocardiography and RHC. HFpEF was defined according to pulmonary capillary wedge pressure (HFpEF: PCWP rest: ≥15mmHg stress: ≥25mmHg). Patients were classified as non-cardiac dyspnoea (NCD) in the absence of HFpEF and cardiovascular disease. LA compliance was defined as reservoir strain (Es)/(E/e’). Follow-up was conducted after 4 years to evaluate cardiovascular hospitalisation (CVH). Results The final study population included 68 patients (HFpEF n=34 and NCD n=34) of which 23 reached the clinical endpoint, 1 Patient was lost to follow-up. Patients with HFpEF according to the HFA-PEFF score (≥5 points) had significantly lower LA compliance at rest (p<0.001) compared to patients with a score ≤4. LA compliance at rest outperformed E/e’ (AUC 0.78 vs 0.87, p=0.024) and showed a statistical trend to outperform Es (AUC 0.79 vs 0.87, p=0.090) for the diagnosis of HFpEF. LA compliance at rest predicted CVH (HR 2.83, 95% CI 1.70-4.74, p<0.001) irrespective of concomitant atrial fibrillation. Conclusions LA compliance at rest can be obtained from clinical routine imaging and bears strong diagnostic and prognostic accuracy. Addition of LA compliance can improve the role of echocardiography as the primary test and gatekeeper.

Explainable Machine Learning Based Prediction of Severity of Heart Failure Using Primary Electronic Health Records.

Heart Failure (HF) is a life-threatening condition. It affects more than 64 million people worldwide. Early diagnosis of HF is extremely crucial. In this study, we propose utilization of machine learning (ML) models to predict severity of HF from primary Electronic Health Records (EHRs). We used a public dataset of 2008 HF patients for the study. Gaussian Naive Bayes, Random Forest and CatBoost methods were used for prediction. The study shows that CatBoost works best for the goal. In addition to that, the largest contributors for tree-based models harmonize well with clinically important parameters, which exhibits the trustworthiness of these models. Hence, we conclude that utilization of ML methods on primary EHRs is a promising step for time-efficient diagnosis of HF patients.

The Effects of Different Blood Sample and Anticoagulant Types on Quantitative Tests of B-Type Natriuretic Peptide.

BNP is a sensitive and widely used biomarker for an early diagnosis of heart failure. Currently, most commercial BNP detection products use EDTA plasma samples. The aim of this study was to evaluate the clinical performance of the BNP test by using whole blood samples compared to plasma samples, and to evaluate the effect of the anticoagulant type on the BNP test result. In total, 106 patients with different BNP levels from the Dahua Hospital volunteered for this study. Clinically homogenous samples, including EDTA anticoagulant plasma, EDTA whole blood, and heparin anticoagulant plasma, were collected and analyzed by using i-Reader S automatic immuno-analyzer and its supporting reagent kits. Pearson's correlation and weighted least squares linear regression analysis, Bland-Altman plotting, and Kappa test were used for statistical analysis. Correlation analysis showed that BNP concentrations, measured from EDTA anticoagulated plasma samples, had a good linear regression relationship with BNP from whole blood samples, with a slope of 0.9477, r = 0.9978, p < 0.05. A similar correlation was observed between EDTA anticoagulated plasma samples and heparin anticoagulant plasma, with a slope of 0.8413, r = 0.9793, p < 0.05. The BNP concentration measured from the heparin plasma samples were lower than of the EDTA plasma samples. Bland-Altman analysis for assessing BNP concentration agreement showed there was no outlier ratio between EDTA whole blood and EDTA plasma within the range of the detection system, as well as no outlier between EDTA anticoagulated and heparin anticoagulant plasma. Kappa coefficient of BNP concentration between homologous EDTA anticoagulated and heparin anticoagulant plasma was 0.8553 (p < 0.001), and for EDTA anticoagulated plasma and homologous whole blood it was 0.8941 (p < 0.001). The diagnostic performance of EDTA anticoagulated whole blood samples did not differ significantly from EDTA anticoagulated plasma samples for the BNP test. This study showed no big significant difference between EDTA anticoagulated and heparin anticoagulated plasma measurements within 2 hours. The type of anticoagulant should be carefully chosen when performing the BNP test if BNP samples were in vitro for a long time.

Construction of a Near-Infrared Fluorescent Probe for Dynamic Monitoring and Early Diagnosis of Heart Failure.

Cardiac hypertrophy characterized by abnormal cardiomyocyte viscosity is a typical sign of heart failure (HF) with vital importance for early diagnosis. However, current biochemical and imaging diagnostic methods are unable to detect this subclinical manifestation. In this work, we developed a series of NIR-I fluorescence probes for detecting myocardial viscosity based on the pyridazinone scaffold. The probes showed weak fluorescence due to free intramolecular rotation under low-viscosity conditions, while they displayed strong fluorescence with limited intramolecular rotation in response to a high-viscosity environment. Among them, CarVis2 exhibited higher stability and photobleaching resistance than commercial dyes. Its specific response to viscosity was not influenced by the pH and biological species. Furthermore, CarVis2 showed rapid and accurate responses to the viscosity of isoproterenol (ISO)-treated H9C2 cardiomyocytes with good biocompatibility. More importantly, CarVis2 demonstrated excellent sensitivity in monitoring myocardial viscosity variation in HF mice in vivo, potentially enabling earlier noninvasive identification of myocardial abnormalities compared to traditional clinical imaging and biomarkers. These findings revealed that CarVis2 can serve as a powerful tool to monitor myocardial viscosity, providing the potential to advance insights into a pathophysiological mechanism and offering a new reference strategy for early visual diagnosis of HF.

Chapter 1: The Burden of Heart Failure

Heart failure (HF) affects an estimated 6 million American adults, and the prevalence continues to increase, driven in part by the aging of the population and by increases in the prevalence of diabetes. In recent decades, improvements in the survival of patients with HF have resulted in a growing number of individuals living longer with HF. HF and its comorbidities are associated with substantial impairments in physical functioning, emotional well-being, and quality of life, and also with markedly increased rates of morbidity and mortality. As a result, the management of patients with HF has a substantial economic impact on the health care system, with most costs arising from hospitalization. Clinicians have an important role in helping to reduce the burden of HF through timely diagnosis of HF as well as increasing access to effective treatments to minimize symptoms, delay progression, and reduce hospital admissions. Prevention and early diagnosis of HF will play a fundamental role in efforts to reduce the large and growing burden of HF. Recent advances in pharmacotherapies for HF have the potential to radically change the management of HF, offering the possibility of improved survival and quality of life for patients.

Discovery and Validation of Potential Serum Biomarkers for Heart Failure by Untargeted Metabolomics

Detection of biomarkers was extremely important for the early diagnosis, prognosis, and therapy optimization of diseases. The purpose of this study was to investigate the differences in serum metabolites between patients with heart failure (HF) and healthy control (HC) and to diagnose HF qualitatively. In this study, serum samples from 83 patients with HF and 35 HCs were used as the research subjects for untargeted metabolomic analysis using ultraperformance liquid chromatography combined with quadrupole‐time of flight mass spectrometry (UPLC‐QTOF/MS) technology. Potential biomarkers were screened and validated using the orthogonal partial least squares discriminant analysis (OPLS‐DA), random forest (RF), binary logistic regression (BLR), and receiver operating characteristic (ROC) analysis. The results indicated that a total of 43 metabolites were considered as differentially expressed metabolites (DEMs). Among these DEMs, glycodeoxycholate was identified as a specific biomarker of HF. A ROC curve analysis for HC versus HF discrimination showed an area under the ROC curve (AUC) of 0.9853 (95% CI: 0.9859–1.0000), a sensitivity of 95%, and a specificity of 100%. Hence, glycodeoxycholate might serve as a potential biomarker for HF. Furthermore, the amino acid metabolism was screened as the most significantly altered pathway in patients with HF. By identifying serum biomarkers and analyzing metabolic pathways, our study provided opportunities to enhance the understanding of the pathogenesis and early diagnosis of HF.

The 'peptide for life' initiative in the emergency department study.

Natriuretic peptide (NP) uptake varies in Emergency Departments (EDs) across Europe. The 'Peptide for Life' (P4L) initiative, led by Heart Failure Association, aims to enhance NP utilization for early diagnosis of heart failure (HF). We tested the hypothesis that implementing an educational campaign in Western Balkan countries would significantly increase NP adoption rates in the ED. This registry examined NP adoption before and after implementing the P4L-ED study across 10 centres in five countries: Bosnia and Herzegovina, Croatia, Montenegro, North Macedonia, and Serbia. A train-the-trainer programme was implemented to enhance awareness of NP testing in the ED, and centres without access received point-of-care instruments. Differences in NP testing between the pre-P4L-ED and post-P4L-ED phases were evaluated. A total of 2519 patients were enrolled in the study: 1224 (48.6%) in the pre-P4L-ED phase and 1295 (51.4%) in the post-P4L-ED phase. NP testing was performed in the ED on 684 patients (55.9%) during the pre-P4L-ED phase and on 1039 patients (80.3%) during the post-P4L-ED phase, indicating a significant absolute difference of 24.4% (95% CI: 20.8% to 27.9%, P<0.001). The use of both NPs and echocardiography significantly increased from 37.7% in the pre-P4L-ED phase to 61.3% in the post-P4L-ED phase. There was an increased prescription of diuretics and SGLT2 inhibitors during the post-P4L-ED phase. By increasing awareness and providing resources, the utilization of NPs increased in the ED, leading to improved diagnostic accuracy and enhanced patient care.

Abstract 14527: AI-ECG is a Cost-Effective Early Screening Tool for Heart Failure With Reduced Ejection Fraction

Background: Early diagnosis of heart failure with reduced ejection fraction (HFrEF) can lead to reduced healthcare costs and improved outcomes. In this study, we evaluated the economic effectiveness of an AI algorithm for detecting low ejection fraction using 12-lead ECG data. Aims: The primary aim was to estimate the health economic impact of the AI-ECG algorithm intervention to detect low ejection fraction. Methods: The study population consisted of 113,719 individuals without a prior history of HFrEF who visited a multistate health system between 2010-2018 with 12-lead ECG data and an echocardiogram within 1 year. The AI-ECG algorithm was run retrospectively, and projected costs were estimated assuming each patient incurred the average cost based on their age group and AI-detected heart failure stage. Hospitalization costs were estimated using Medicare reimbursement rates, and economic benefits from increased survival were estimated using a willingness to pay of $50,000 per quality-adjusted life year (QALY) gained. Results: At the optimal model threshold, the total cost savings per patient (including benefits from QALYs gained) for the AI-ECG algorithm vs. standard-of-care on the overall study population were projected to be $79.11 (95% CI: [$53.77, $104.44]) and $124.93 (95% CI: [$83.99, $165.88]) for the 2 and 4 year periods, respectively. For patients over 50 years old, the projected total cost savings were $85.56 (95% CI: [$56.35, $114.78]) and $135.28 (95% CI: [$88.18, $182.38]) per patient for the 2 and 4 year periods, respectively. See Figure. Conclusions: The AI-ECG algorithm to detect low ejection fraction is a cost-effective early screening tool for HFrEF.

Abstract 12847: The Heart Bus: A Mobile Patient-Centered Approach to Improve Early Diagnosis of Heart Failure in the Community

Introduction: Heart failure with preserved ejection fraction (HFpEF) is associated with poor quality of life and considerable morbidity and mortality risk. Early diagnosis is expected to improve clinical outcomes, but requires imaging and laboratory analyses with frequent hospital visits. We developed a mobile care unit, the Heart Bus, to improve early diagnosis of HF. Methods: The Heart Bus was a 70 m 2 trailer with examination rooms, cardiac ultrasound, exercise testing equipment, a clinical laboratory, and 4 staff. During 2020-2022, the Heart Bus team reached out to the population in local newspapers, via HF patient digital platforms, and visited locations in the West Coast of Sweden. Eligible participants had suspected signs or symptoms of HF. Participants underwent echocardiography and tests for cardiopulmonary exercise, vascular function, adenosine-stress coronary flow reserve, and routine biochemistry and haematology. Molecular and physiological deep phenotyping were also performed in the Heart Bus to facilitate future patient stratification and precision medicine (data to be presented Nov 2023). Results: Of 218 participants screened over 18 months (12/month), 200 were included. Most participants actively reached out to take part. Twenty three participants (11.5%) had HFrEF, 54 (27.0%) had HFmrEF, and 62 (31.0%) had HFpEF; 70 (35.0%) had a previous HF diagnosis. Of the remaining patients, 60 (30.0%) had intermediate risk of HFpEF. The phenotypes of the EF-stratified HF subgroups were similar. However, participants in the HFpEF cohort had more women ( p &lt; 0.001), lower lung volume ( p &lt; 0.01), higher pulse wave velocity ( p &lt; 0.01) and poorer kidney function ( p &lt; 0.05) than those with HFrEF. Conclusions: The Heart Bus mobile clinic identified large numbers of patients with HF and may represent a cost-effective way to early HF diagnosis also for underserved communities, those located remotely, or have other thresholds for admittance to HF clinics.

Neopterin as a Potential Biomarker for the Early Diagnosis of Heart Failure: A Systematic Review and Meta-analysis.

Neopterin (NEO) is an inflammatory biomarker with proposed diagnostic value in cardiovascular diseases. Some correlations have been discovered between NEO levels and the incidence, severity, and adverse outcomes of heart failure (HF). However, there are discrepancies in the results reported in the literature. We conducted a systematic review and meta-analysis of studies comparing urinary and blood NEO concentrations between individuals with HF, cardiac insufficiency, or dilated cardiomyopathy (DCM) with control groups or those monitoring the role of NEO concentrations as a predictive marker of adverse outcomes in HF patients. A total of 24 studies that met the inclusion criteria were reviewed. The studies demonstrated the alteration of NEO in blood or urine samples in subjects with HF, cardiac insufficiency, or DCM compared with control groups. Also, reviewing the studies suggested a link between reduced ejection fraction, higher NYHA classes, and a higher risk of adverse cardiac outcomes with increased NEO levels. The meta-analysis of three studies revealed a significant increase in serum NEO levels in HF cases compared to that in healthy controls with an effect size of 3.72 (95 % CI 0.16 to 7.28; p = 0.04). Meta-analysis demonstrated a significant difference between serum NEO levels of HF cases and healthy subjects. This evidence implies the potential of serum NEO as a valuable diagnostic biomarker in HF patients. Also, the review of the studies revealed the prognostic potential of NEO. Further research is required to assess the usefulness of NEO as a diagnostic/prognostic biomarker for HF.

Practical algorithms for early diagnosis of heart failure and heart stress using NT-proBNP: A clinical consensus statement from the Heart Failure Association of the ESC.

Diagnosing heart failure is often difficult due to the non-specific nature of symptoms, which can be caused by a range of medical conditions. Natriuretic peptides (NPs) have been recognized as important biomarkers for diagnosing heart failure. This document from the Heart Failure Association examines the practical uses of N-terminal pro-B-type natriuretic peptide (NT-proBNP) in various clinical scenarios. The concentrations of NT-proBNP vary according to the patient profile and the clinical scenario, therefore values should be interpreted with caution to ensure appropriate diagnosis. Validated cut-points are provided to rule in or rule out acute heart failure in the emergency department and to diagnose de novo heart failure in the outpatient setting. We also coin the concept of 'heart stress' when NT-proBNP levels are elevated in an asymptomatic patient with risk factors for heart failure (i.e. diabetes, hypertension, coronary artery disease), underlying the development of cardiac dysfunction and further increased risk. We propose a simple acronym for healthcare professionals and patients, FIND-HF, which serves as a prompt to consider heart failure: Fatigue, Increased water accumulation, Natriuretic peptide testing, and Dyspnoea. Use of this acronym would enable the early diagnosis of heart failure. Overall, understanding and utilizing NT-proBNP levels will lead to earlier and more accurate diagnoses of heart failure ultimately improving patient outcomes and reducing healthcare costs.

Scoping Meta-Review of Methods Used to Assess Artificial Intelligence-Based Medical Devices for Heart Failure.

Artificial intelligence and machine learning (AI/ML) are playing increasingly important roles, permeating the field of medical devices (MDs). This rapid progress has not yet been matched by the Health Technology Assessment (HTA) process, which still needs to define a common methodology for assessing AI/ML-based MDs. To collect existing evidence from the literature about the methods used to assess AI-based MDs, with a specific focus on those used for the management of heart failure (HF), the International Federation of Medical and Biological Engineering (IFMBE) conducted a scoping meta-review. This manuscript presents the results of this search, which covered the period from January 1974 to October 2022. After careful independent screening, 21 reviews, mainly conducted in North America and Europe, were retained and included. Among the findings were that deep learning is the most commonly utilised method and that electronic health records and registries are among the most prevalent sources of data for AI/ML algorithms. Out of the 21 included reviews, 19 focused on risk prediction and/or the early diagnosis of HF. Furthermore, 10 reviews provided evidence of the impact on the incidence/progression of HF, and 13 on the length of stay. From an HTA perspective, the main areas requiring improvement are the quality assessment of studies on AI/ML (included in 11 out of 21 reviews) and their data sources, as well as the definition of the criteria used to assess the selection of the most appropriate AI/ML algorithm.

СРАВНЕНИЕ ИНФОРМАТИВНОСТИ ОПРЕДЕЛЕНИЯ NT-PROBNP ПОЛУКОЛИЧЕСТВЕННЫМ И КОЛИЧЕСТВЕННЫМ МЕТОДАМИ ДЛЯ РАННЕЙ ДИАГНОСТИКИ ХРОНИЧЕСКОЙ СЕРДЕЧНОЙ НЕДОСТАТОЧНОСТИ

Вackground. Heart failure (HF) is one of the main causes of morbidity and mortality worldwide. Since it is important to diagnose CH early and quickly, at the outpatient appointment, there is a need to create and introduce into practice a portable highly sensitive method for the determination of BNP, NT-proBNP. Purpose of the study. To determine the possibility of using reagents for semi-quantitative determination of N-terminal brain natriuretic peptide antigen for early detection of heart failure. Methods of statistical analysis. Microsoft Office Excel 2019 program was used. Patient Characterization and Research Methods. An open cross-sectional non-randomized cohort study included 50 patients (mean age 63.5 years) who applied on an outpatient basis for consultation to a cardiologist. In addition to standard clinical, biochemical and instrumental examinations, the concentration of N-terminal brain natriuretic peptide (NT-proBNP) was determined by quantitative and semi-quantitative immunochromatographic method (LLC NPO "BioTest", Novosibirsk). The diagnosis of chronic heart failure (CHF) was established in accordance with national and European recommendations. Methods of statistical analysis. Microsoft Office Excel 2019 program was used. Results and conclusion. In the course of the study, it was found that semi-quantitative method is highly sensitive for detection of small NT-proBNP elevations, which is important for early diagnosis of heart failure, including subclinical forms. Semi-quantitative method also allows to distinguish a group of patients with high NT-proBNP values. The relationship of NT-proBNP level with the course and prognosis of CHF requires further study.

Does nurse-led point-of-care ultrasound (POCUS) improve the triage of elderly community patients with suspected heart failure? A feasibility study

Abstract Funding Acknowledgements Type of funding sources: Public Institution(s). Main funding source(s): Research and Development of Swansea Bay University Health Board (Pathway to Portfolio) Background/Introduction In elderly people, the early diagnosis of heart failure (HF) in community settings can be challenging. The presence of multiple chronic conditions in this age group often limits the diagnostic accuracy of both the clinical examination and point-of-care tests such as electrocardiogram (ECG) and brain natriuretic peptide (BNP) blood test; low diagnostic confidence can negatively impact management and outcomes. There is evidence that point-of-care ultrasound (POCUS), used as an extension to the clinical examination, can improve diagnostic decision-making. However, it is unclear whether adding POCUS to the existing HF pathway for older people is feasible and where it offers improved accuracy compared with the ECG and BNP. Objectives This small feasibility study assessed whether: 1) community nurses could add POCUS to their current clinical assessment of patients with suspected HF in residential settings, 2) nurses could accurately and reliably detect left ventricular systolic dysfunction (LVSD), 3) adding POCUS to the pathway could improve the time to diagnosis and effectiveness of management decisions. Methods Single-arm, single-centre, prospective feasibility study in patients aged over 60yrs referred to a community-based acute clinical team with suspected HF. Four nurses completed a dedicated POCUS training programme prior to patient enrolment. Nurses completed the existing clinical pathway, recording working diagnosis and management plan before adding POCUS (focused heart and lung protocol), and recording whether the findings would hypothetically alter their diagnosis and plan. All images were reviewed and reported by an accredited specialist, blind to nurse results (reference test). Results N=32 (mean age 81 ± 9yrs). POCUS was performed in 100% and LVSD could be evaluated in 94%. Nurses could accurately and reliably detect LVSD (sensitivity 0.94, specificity 0.88, reliability 0.81 [Cohen’s kappa]). The standard care pathway (including ECG and BNP) provided confirmation of LVSD in 0% and exclusion of LVSD in 19% within 24hrs. Specialist echocardiography referral was requested in 81% (38% inappropriate). In contrast, POCUS allowed nurses to confirm or exclude LVSD at the bedside in 94% of patients. POCUS would have impacted the medication decision in 38% and led to referral for specialist echocardiography in 53% (12% inappropriate). Conclusion Adding POCUS to the current diagnostic community pathway appears to be feasible and reliable, leading to shorter time-to-diagnosis (and therefore initiation of treatment), and more effective triage. These preliminary data need to be confirmed in a larger effectiveness-implementation study which we have designed and which we will recruit to in 2023.

A Comparative Study of Plasma N-Terminal Pro- Brain Natriuretic Peptide to Assess Asymptomatic Cardiovascular Disease in Type 2 Diabetic Patients

Background: This study aimed to assess NT-pro BNP level in patients of T2DM without overt cardiovascular disease to determine presence of Asymptomatic Left Ventricular Dysfunction (ALVD) compared with matched control group. Methods: This study conducted at SMS Hospital, Jaipur by selecting 60 patients of type 2 diabetes mellitus and 60 control of non-diabetic population. Information regarding demographic data, clinical symptoms, past medical history, laboratory parameters, NT pro-BNP and 2D Echocardiography collected from selected sample population for comparative analysis among both groups. Results: Patients of T2DM have significantly higher value of NT pro-BNP, blood sugar and HbA1c with proportionally increased diastolic dysfunction as compared to matched non-diabetic population (P&lt;0.05). Absolute value of NT pro-BNP in patients of T2DM is directly correlated with age, duration of diabetes, Blood pressure, blood sugar level, HbA1c level, creatinine, total cholesterol and urine protein (positive correlation coefficient with P-value&lt;0.05). Left ventricular ejection fractions were found statistically similar among both groups. Conclusion: Heart failure in patients with T2DM is a most crucial diabetic complication for diagnosis as well as management. Level of NT-pro BNP in blood stream is an important tool for early diagnosis of heart failure especially HFpEF. This study suggests that the secretion of NT-pro BNP is increased in patients with T2DM compared with control subject without overt heart disease. Therefore, measurement of NT-pro BNP paired might be a simple screening tool to identify patients with diabetes at risk for ventricular dysfunction requiring further examination with echocardiography.

PO-04-174 AN ELECTROGRAPHIC DEEP LEARNING MODEL FOR LONG-TERM MORTALITY OF THE PATIENTS SURVIVING AFTER ACUTE MYOCARDIAL INFARCTION

The diagnosis of acute myocardial infarction (AMI) initially depends on a patient’s history and the 12-lead ECG. Significant changes of the ST segment on ECG are one of the diagnostic markers of AMI and are associated with higher short-term or long-term mortality of patients. However, scoring systems or predictors for long-term risk stratification are still lacking for patients with AMI. Recently deep learning (DL) model built based on 12-lead ECG showed its great potential for early diagnosis of heart failure and atrial fibrillation. We aimed to develop a prognosis model for the long-term mortality of AMI patients based on 12-lead ECG using DL. Twelve-lead ECGs of patients during AMI were retrieved retrospectively between 2011 to 2017, and a convolutional neural network (CNN) using 12-lead ECG and patient’s age has been built to predict all-cause death within one year. The patients’ ECG recordings were split into training, validation, and testing set at a ratio of 5:2:3 and the patients were not overlapped among different datasets. Survival analysis was conducted using the Kaplan-Meier method with available follow-up data in a testing set stratified by the built model. Furthermore, Cox proportional hazard model was performed to get crude hazard ratio (HR) and covariate-adjusted HR for TIMI and GRACE score. 16827 ECGs from 2238 patients (77% male, age 64.8±13.8 years) with AMI were included. The AUC of the DL model is 0.80, with a sensitivity of 82%, and specificity of 66% using an optimal threshold on the testing set. In addition, we also found that the patients labeled as dead by DL model have a higher probability of death over a 6-year follow-up with the HR of 6.00 (95% confidence interval (CI) 3.92-9.20) while the HR of TIMI score is 1.38 (95% CI 0.97-1.97) and HR of GRACE score is 2.72 (95% CI 1.92-3.86). By applying multivariate adjustment, the DL model can be an independent predictor with the HR of 5.68 (95% CI 3.69-8.74) for the sex-adjusted model, 6.11 (95% CI 3.95-9.45) for the TIMI-socre-adjusted model and 5.22 (95% CI 3.38-8.06) for GRACE-score-adjusted model. (Figure 1) Our result showed that the DL model built based on 12-lead ECG can predict long-term mortality after AMI for up to 6 years. The DL model can provide an instant prognostic indicator using the 12-lead ECG complemented with TIMI or GRACE scores.

The Use of Brain Natriuretic Peptide in the Evaluation of Heart Failure in Geriatric Patients.

Heart failure is one of the main morbidity and mortality factors in the general population and especially in elderly patients. Thus, at the European level, the prevalence of heart failure is 1% in people under 55 years of age but increases to over 10% in people over 70 years of age. The particularities of the elderly patient, which make the management of heart failure difficult, are the presence of comorbidities, frailty, cognitive impairment and polypharmacy. However, elderly patients are under-represented in clinical trials on the diagnosis and treatment of heart failure. The need for complementary methods (biomarkers) for differential and early diagnosis of heart failure is becoming more and more evident, even in its subclinical stages. These methods need to have increased specificity and sensitivity and be widely available. Natriuretic peptides, in particular B-type natriuretic peptide (BNP) and its fraction NTproBNP, have gained an increasingly important role in the screening, diagnosis and treatment of heart failure in recent years.

Gamma-glutamyl transpeptidase is a promising biological marker of heart failure

Introduction. Currently, the search and study of new biological markers that can help early diagnosis of heart failure, serve as a laboratory tool for assessing the effectiveness of therapy, be a predictive marker of possible adverse clinical outcomes and a significant criterion for risk stratification is very relevant. While cardiospecific markers, including natriuretic peptides, their precursors, and highly sensitive troponins, are widely used in clinical practice, the need to use other markers does not have sufficient evidence. aspect of a biological marker of heart failure.Gamma-glutamyl transpeptidase is an enzyme localized on the outer side of cell membranes and involved in the metabolism of glutathione and cysteine. This enzyme is a dimeric glycoprotein (68 kDa), consisting of 2 subunits – a large and a small (46 and 22 kDa). Gamma-glutamyl transpeptidase is encoded by a multigene family consisting of at least 7 different genes located on chromosome 22; however, only 1 of these genes is involved in the formation of a functional enzyme. Gamma-glutamyl transpeptidase was found in all cells except erythrocytes. There is a significant variability in enzyme activity, which is especially high in tissues with a secretory and absorptive function, such as the kidneys, biliary tract, intestines, and epididymis.Purpose of the review is to present an overview of current publications devoted to the study of γ-glutamyl transpeptidase in the aspect of a biological marker of heart failure.Materials and methods. The analysis of literature sources (foreign and domestic articles) was carried out in the databases: PubMed, RSCI, MedLine, Google Scholar, Science Direct. The search was performed according to the following keywords: biological markers, heart failure, γ-glutamyl transpeptidase, biological markers, heart failure, γ-glutamyl transpeptidase.Results. In addition to its clinical use as a test for liver disease, biliary tract disease, and alcohol abuse, γ-glutamyl transpeptidase is of great interest because of its association with cardiovascular disease, diabetes, metabolic syndrome, and cancer. In the literature available to us, we found a small number of works devoted to the study of γ-glutamyl transpeptidase in patients with heart failure. In the review, we have presented data from experimental and clinical studies indicating a clear link between γ-glutamyl transpeptidase and heart failure. The pathogenetic mechanism of the possible relationship between γ-glutamyl transpeptidase and heart failure is not completely clear. The localization of this enzyme in tissues with a transport function has led to the assumption that it is involved in the transport of amino acids through the γ-glutamyl cycle.Conclusion. Further deeper understanding of the structure and function of the enzyme is needed, as well as future clinical studies to determine the diagnostic, prognostic and possibly therapeutic significance of this biological marker.

Role of Natriuretic Terminal Pro B-type Natriuretic Peptide (NT-Pro-BNP) in Diagnosis of Heart Failure in Acute Exacerbation of Chronic Obstructive Pulmonary Disease (COPD), Retrospective Cohort Study Conducted in Karachi, Pakistan

Introduction: COPD and heart failure effecting millions of people in the world where as combinedly becomes deadlier and affecting the major population of different regions of world, also increasing the rate of morbidity and mortality. Diagnosis of heart failure in COPD patients or COPD in heart failure patient is very difficult for cardiologist and pulmonologist. Objective: Acute exacerbation of COPD concomitant with Heart failure is among the diseases responsible for increasing the Mortality, morbidity, economic burden on patients, health care system and to see the impact on gender-based incidence Early use of NT-Pro-BNP is evaluated in COPD patients for diagnosis of heart failure in Pakistan due to socio-cultural and economical differences this study was conducted. Methods: The study was conducted in 7th Day Karachi Adventist hospital from Nov 2020 to Nov 2021, retrospective cohort study in admitted patients with acute exacerbation of COPD. Qualitative variables including gender, age groups, smoking status, symptoms and clinical finding were recorded. Data was entered and analyzed in statistical package for social sciences (SPSS) version 22. Quantitative variables including age in years, duration of COPD, NT-Pro-BNP level and ejection fraction was presented in mean and standard deviation. For the determination of association between qualitative variables chi-square test was used. Results: In our study heart failure was reported in 89 (85.5%) patients of AECOPD on the basis of Pro -BNP level with Heart Failure &amp; COPD without Heart Failure in 15 (14.4%) patients by using NT-Pro-BNP as a marker of heart Failure. independent sample was used for calculating mean difference (8042.2),95 %CI (1060.7-23.0) and P-value 0.02 *between patients of COPD with heart failure and without HF P-value shows significant difference between Pro BNP level of COPD with heart failure and without Heart failure. Gender of Patients with COPD was male in 61 (58.6%) patients and female in 43 (41.3%). Mean age of the patient with acute exacerbation of COPD was 70.0±11.2 (40-98) years. Age distribution of patients with acute exacerbation of COPD in male vs female was in age group &lt;50 years was 4 (3.8%) vs 1 (0.9%), in age group 50-75 years was 50 (48%) vs 22 (21.1%), and in age group &lt;75 years was 20 (19.2%) vs 7 (6.7%) shows male patients more suffering than women in all age groups. On history and clinical examination Symptoms of shortness of breathing and Coughing were more in male then female. Mean ejection fraction of patients with acute exacerbation of COPD without HF minimum E.F was 40% and maximum was 70% with mean 26%. COPD with HF minimum E.F was 20% and maximum was 70% with mean 52% ±16.6 (20-70%). Mean Pro-BNP level of patients with acute exacerbation of COPD was 7498 ±12221 (17-36000) pg/ml. Chi-square test value was 0.122 and P-value was 0.7. Conclusion: It was concluded from this study that the level of NT-Pro-BNP in patients with acute Exacerbation of COPD. diagnosed with Heart Failure was significantly high as compared to patient of acute exacerbation without Heart Failure especially high in males than females. Early diagnosis of heart failure in COPD patients will be helpful in early initiation of heart failure, medication, decreasing the hospital admissions, hospital stay and cost burden on patients and health care system of low socio-economical countries.

Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation.

The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are ideal clinical research environments for such development because they collect many clinical data and are highly computerized. Goal: We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. Methods: The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients' clinical notes with 5444 single lines of notes. There were 1941 positive cases (36% of total) and 3503 negative cases classified by two independent physicians using a standardized approach. Results: The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89% accuracy, 88% recall, and 89% precision. Conclusions: This study successfully applied learning representation and machine learning algorithms to detect heart failure in a single French institution from clinical natural language. Further work is needed to use the same methodology in other languages and institutions.