Abstract 15924: Identification of Gender- and Age-specific Top Predictors of Hospitalization Due to Heart Failure Using Machine Learning in TOPCAT

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Gauri Dandi ◽  
Nuha Gani ◽  
Zyannah Mallick ◽  
Avantika Banerjee ◽  
Ian Atkinson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Diabetic Complications ◽  
Age Groups ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Age Group ◽  
Ventricular Ejection Fraction ◽  
Gender And Age ◽  
Liver Markers

Background: NHLBI supported Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist trial (TOPCAT) (NCT00094302) investigated whether treatment with spironolactone reduces hospitalization due to heart failure (hHF) in 3,445 adults with prior heart failure and a left ventricular ejection fraction over 45%. We reused publicly available individual patient-level data from NHLBI Data Repository (BioLINCC) to perform hypothesis-generating secondary analyses by machine learning (ML) on the American TOPCAT cohort (n=1767) to identify gender and age groups specific baseline (bl) predictors of hHF. Methods: The subjects were stratified into subgroups based on gender (male and female) and age (50-59, 60-69, 70-79, 80-90). Random Survival Forest (RSF), a non-parametric ML approach, evaluated 172 bl variables as predictors of hHF. Top 10 predictors were subsequently included in a multivariate Cox proportional hazards model. Results: The top 10 predictors of hHF are shown in Figure 1. Overall, renal and hematological biomarkers appeared prominently in the top 10 predictors for these patients. While liver markers were among top predictors for hHF in males, diabetes treatment and diabetic complications were top predictors for females. Also, diabetic treatment was a top predictor among age group 50-59, diabetic complications were top predictors among age groups 50-59 and 70-79, liver markers were top predictors among age groups 70-79, and race and years of smoking were top predictors among age group 60-69. Importantly, the use of potassium sparing diuretic at bl was the top predictor among age group 80-90. Conclusion: Using ML, we uncovered in an unbiased fashion, otherwise overlooked bl predictors of hHF in a large, international, multi-center trial like TOPCAT. Thus, ML can help to identify similarities and differences of disease and treatment outcomes among gender, race, ethnicity, and age specific subgroups and advance precision medicine.

scholarly journals Machine learning for prediction of sudden cardiac death in heart failure patients with low left ventricular ejection fraction: study protocol for a retroprospective multicentre registry in China

BMJ Open ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. e023724 ◽  
Author(s):  
Fanqi Meng ◽  
Zhihua Zhang ◽  
Xiaofeng Hou ◽  
Zhiyong Qian ◽  
Yao Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Sudden Cardiac Death ◽  
Left Ventricular Ejection Fraction ◽  
Ejection Fraction ◽  
Study Protocol ◽  
Cardiac Death ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction

IntroductionLeft ventricular ejection fraction (LVEF) ≤35%, as current significant implantable cardioverter-defibrillator (ICD) indication for primary prevention of sudden cardiac death (SCD) in heart failure (HF) patients, has been widely recognised to be inefficient. Improvement of patient selection for low LVEF (≤35%) is needed to optimise deployment of ICD. Most of the existing prediction models are not appropriate to identify ICD candidates at high risk of SCD in HF patients with low LVEF. Compared with traditional statistical analysis, machine learning (ML) can employ computer algorithms to identify patterns in large datasets, analyse rules automatically and build both linear and non-linear models in order to make data-driven predictions. This study is aimed to develop and validate new models using ML to improve the prediction of SCD in HF patients with low LVEF.Methods and analysisWe will conduct a retroprospective, multicentre, observational registry of Chinese HF patients with low LVEF. The HF patients with LVEF ≤35% after optimised medication at least 3 months will be enrolled in this study. The primary endpoints are all-cause death and SCD. The secondary endpoints are malignant arrhythmia, sudden cardiac arrest, cardiopulmonary resuscitation and rehospitalisation due to HF. The baseline demographic, clinical, biological, electrophysiological, social and psychological variables will be collected. Both ML and traditional multivariable Cox proportional hazards regression models will be developed and compared in the prediction of SCD. Moreover, the ML model will be validated in a prospective study.Ethics and disseminationThe study protocol has been approved by the Ethics Committee of the First Affiliated Hospital of Nanjing Medical University (2017-SR-06). All results of this study will be published in international peer-reviewed journals and presented at relevant conferences.Trial registration numberChiCTR-POC-17011842; Pre-results.

scholarly journals Machine-learning facilitates selection of a novel diagnostic panel of metabolites for the detection of heart failure

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
M. Marcinkiewicz-Siemion ◽  
M. Kaminski ◽  
M. Ciborowski ◽  
K. Ptaszynska-Kopczynska ◽  
A. Szpakowicz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Ejection Fraction ◽  
Current Knowledge ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Metabolic Derangement ◽  
Ventricular Ejection Fraction ◽  
Diagnostic Panel ◽  
Selection Of

AbstractThe metabolic derangement is common in heart failure with reduced ejection fraction (HFrEF). The aim of the study was to check feasibility of the combined approach of untargeted metabolomics and machine learning to create a simple and potentially clinically useful diagnostic panel for HFrEF. The study included 67 chronic HFrEF patients (left ventricular ejection fraction-LVEF 24.3 ± 5.9%) and 39 controls without the disease. Fasting serum samples were fingerprinted by liquid chromatography-mass spectrometry. Feature selection based on random-forest models fitted to resampled data and followed by linear modelling, resulted in selection of eight metabolites (uric acid, two isomers of LPC 18:2, LPC 20:1, deoxycholic acid, docosahexaenoic acid and one unknown metabolite), demonstrating their predictive value in HFrEF. The accuracy of a model based on metabolites panel was comparable to BNP (0.85 vs 0.82), as verified on the test set. Selected metabolites correlated with clinical, echocardiographic and functional parameters. The combination of two innovative tools (metabolomics and machine-learning methods), both unrestrained by the gaps in the current knowledge, enables identification of a novel diagnostic panel. Its diagnostic value seems to be comparable to BNP. Large scale, multi-center studies using validated targeted methods are crucial to confirm clinical utility of proposed markers.

Efficacy of Vitamin D on Chronic Heart Failure Among Adults

2020 ◽  
Vol 90 (1-2) ◽  
pp. 49-58 ◽  
Author(s):  
Wang Chunbin ◽  
Wang Han ◽  
Cai Lin
Keyword(s):  
Heart Failure ◽  
Vitamin D ◽  
Chronic Heart Failure ◽  
Left Ventricular Ejection Fraction ◽  
Confidence Interval ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Controlled Trials ◽  
Ventricular Ejection Fraction ◽  
Randomized Controlled

Abstract. Vitamin D deficiency commonly occurs in chronic heart failure. Whether additional vitamin D supplementation can be beneficial to adults with chronic heart failure remains unclear. We conducted a meta-analysis to derive a more precise estimation. PubMed, Embase, and Cochrane databases were searched on September 8, 2016. Seven randomized controlled trials that investigated the effects of vitamin D on cardiovascular outcomes in adults with chronic heart failure, and comprised 592 patients, were included in the analysis. Compared to placebo, vitamin D, at doses ranging from 2,000 IU/day to 50,000 IU/week, could not improve left ventricular ejection fraction (Weighted mean difference, WMD = 3.31, 95% confidence interval, CL = −0.93 to 7.55, P < 0.001, I2 = 92.1%); it also exerts no beneficial effects on the 6 minute walk distance (WMD = 18.84, 95% CL = −24.85 to 62.52, P = 0.276, I2 = 22.4%) and natriuretic peptide (Standardized mean difference, SMD = −0.39, 95% confidence interval CL = −0.48 to 0.69, P < 0.001, I2 = 92.4%). However, a dose-response analysis from two studies demonstrated an improved left ventricular ejection fraction with vitamin D at a dose of 4,000 IU/day (WMD = 6.58, 95% confidence interval CL = −4.04 to 9.13, P = 0.134, I2 = 55.4%). The results showed that high dose vitamin D treatment could potentially benefit adults with chronic heart failure, but more randomized controlled trials are required to confirm this result.

Emerging Cardiac Resynchronisation Therapy Indications

2011 ◽  
Vol 7 (1) ◽  
pp. 29
Author(s):  
Charlotte Eitel ◽  
Gerhard Hindricks ◽  
Christopher Piorkowski ◽  
◽  
◽  
...  
Keyword(s):  
Heart Failure ◽  
Systolic Heart Failure ◽  
Cardiac Resynchronisation Therapy ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Current Evidence ◽  
Class Iii ◽  
Ventricular Ejection Fraction ◽  
Cardiac Resynchronisation ◽  
Resynchronisation Therapy

Cardiac resynchronisation therapy (CRT) is an efficacious and cost-effective therapy in patients with highly symptomatic systolic heart failure and delayed ventricular conduction. Current guidelines recommend CRT as a class I indication for patients with sinus rhythm, New York Heart Association (NYHA) functional class III or ambulatory class IV, a QRS duration ≥120ms, and left ventricular ejection fraction (LVEF) ≤35%, despite optimal pharmacological therapy. Recent trials resulted in an extension of current recommendations to patients with mild heart failure, patients with atrial fibrillation, and patients with an indication for permanent right ventricular pacing with the aim of morbidity reduction. The effectiveness of CRT in patients with narrow QRS, patients with end-stage heart failure and cardiogenic shock, and patients with an LVEF >35% still needs to be proved. This article reviews current evidence and clinical applications of CRT in heart failure and provides an outlook on future developments.

Heart Failure with Preserved Ejection Fraction – A Review

2012 ◽  
Vol 9 (1) ◽  
pp. 90-95 ◽  
Author(s):  
Otto A Smiseth ◽  
Anders Opdahl ◽  
Espen Boe ◽  
Helge Skulstad
Keyword(s):  
Heart Failure ◽  
Ejection Fraction ◽  
Diastolic Heart Failure ◽  
The Elderly ◽  
Left Ventricular ◽  
Filling Pressure ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
Reduced Ejection Fraction ◽  
Objective Evidence

Heart failure with preserved left ventricular ejection fraction (HF-PEF), sometimes named diastolic heart failure, is a common condition most frequently seen in the elderly and is associated with arterial hypertension and left ventricular (LV) hypertrophy. Symptoms are attributed to a stiff left ventricle with compensatory elevation of filling pressure and reduced ability to increase stroke volume by the Frank-Starling mechanism. LV interaction with stiff arteries aggravates these problems. Prognosis is almost as severe as for heart failure with reduced ejection fraction (HF-REF), in part reflecting co-morbidities. Before the diagnosis of HF-PEF is made, non-cardiac etiologies must be excluded. Due to the non-specific nature of heart failure symptoms, it is essential to search for objective evidence of diastolic dysfunction which, in the absence of invasive data, is done by echocardiography and demonstration of signs of elevated LV filling pressure, impaired LV relaxation, or increased LV diastolic stiffness. Antihypertensive treatment can effectively prevent HF-PEF. Treatment of HF-PEF is symptomatic, with similar drugs as in HF-REF.

A translational model of chronic heart failure in rats

2018 ◽  
pp. 136-148
Author(s):  
С.А. Крыжановский ◽  
И.Б. Цорин ◽  
Е.О. Ионова ◽  
В.Н. Столярук ◽  
М.Б. Вититнова ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Heart Failure ◽  
Chronic Heart Failure ◽  
Left Ventricular ◽  
Compensatory Hypertrophy ◽  
Experimental Myocardial Infarction ◽  
Left Ventricular Ejection ◽  
Translational Model ◽  
Innovative Drug ◽  
Ventricular Ejection Fraction

Цель исследования - разработка трансляционной модели хронической сердечной недостаточности (ХСН) у крыс, позволяющей, с одной стороны, изучить тонкие механизмы, лежащие в основе данной патологии, а с другой стороны, выявить новые биомишени для поиска и изучения механизма действия инновационных лекарственных средств. Методика. Использован комплекс эхокардиографических, морфологических, биохимических и молекулярно-биологических исследований, позволяющий оценивать и дифференцировать этапы формирования ХСН. Результаты. Динамические эхокардиографические исследования показали, что ХСН формируется через 90 дней после воспроизведения переднего трансмурального инфаркта миокарда. К этому времени у животных основной группы отмечается статистически значимое по сравнению со 2-ми сут. после воспроизведения экспериментального инфаркта миокарда снижение ФВ левого желудочка сердца (соответственно 55,9 ± 1,4 и 63,9 ± 1,6%, р = 0,0008). Снижение насосной функции сердца (на 13% по сравнению со 2-ми сут. после операции и на ~40% по сравнению с интактными животными) сопровождается увеличением КСР и КДР (соответственно с 2,49 ± 0,08 до 3,91 ± 0,17 мм, р = 0,0002, и с 3,56 ± 0,11 до 5,20 ± 0,19 мм, р = 0,0001), то есть к этому сроку развивается сердечная недостаточность. Результаты эхокардиографических исследований подтверждены данными морфометрии миокарда, продемонстрировавшими дилатацию правого и левого желудочков сердца. Параллельно проведенные гистологические исследования свидетельствуют о наличии патогномоничных для данной патологии изменений миокарда (постинфарктный кардиосклероз, компенсаторная гипертрофия кардиомиоцитов, очаги исчезновения поперечной исчерченности мышечных волокон и т.д.) и признаков венозного застоя в легких и печени. Биохимические исследования выявили значимое увеличение концентрации в плазме крови биохимического маркера ХСН - мозгового натрийуретического пептида. Данные молекулярно-биологических исследований позволяют говорить о наличии гиперактивности ренин-ангиотензин-альдостероновой и симпатоадреналовой систем, играющих ключевую роль в патогенезе ХСН. Заключение. Разработана трансляционная модель ХСН у крыс, воспроизводящая основные клинико-диагностические критерии этого заболевания. Показано наличие корреляции между морфометрическими, гистологическими, биохимическими и молекулярными маркерами прогрессирующей ХСН и эхокардиографическими диагностическими признаками, что позволяет использовать неинвазивный метод эхокардиографии, характеризующий состояние внутрисердечной гемодинамики, в качестве основного критерия оценки наличия/отсутствия данной патологии. Aim. Development of a translational model for chronic heart failure (CHF) in rats to identify new biotargets for finding and studying mechanisms of innovative drug effect in this disease. Methods. A set of echocardiographic, morphological, biochemical, and molecular methods was used to evaluate and differentiate stages of CHF development. Results. Dynamic echocardiographic studies showed that CHF developed in 90 days after anterior transmural myocardial infarction. By that time, left ventricular ejection fraction was significantly decreased in animals of the main group compared with rats studied on day 2 after experimental myocardial infarction (55.9 ± 1.4% vs . 63.9 ± 1.6%, respectively, p<0.0008). The decrease in heart’s pumping function (by 13% compared with day 2 after infarction and by approximately 40% compared to intact animals) was associated with increased ESD and EDD (from 2.49 ± 0.08 to 3.91 ± 0.17 mm, p = 0.0002, and from 3.56 ± 0.11 to 5.20 ± 0.19 mm, respectively, p = 0.0001); therefore, heart failure developed by that time. The results of echocardiographic studies were confirmed by myocardial morphometry, which demonstrated dilatation of both right and left ventricles. Paralleled histological studies indicated presence of the changes pathognomonic for this myocardial pathology (postinfarction cardiosclerosis, compensatory hypertrophy of cardiomyocytes, foci of disappeared transverse striation of muscle fibers, etc.) and signs of venous congestion in lungs and liver. Biochemical studies demonstrated a significant increase in plasma concentration of brain natriuretic peptide, a biochemical marker of CHF. Results of molecular studies suggested hyperactivity of the renin-angiotensin-aldosterone and sympathoadrenal systems, which play a key role in the pathogenesis of CHF. Conclusions. A translational model of CHF in rats was developed, which reproduced major clinical and diagnostic criteria for this disease. Morphometric, histological, biochemical, and molecular markers for progressive CHF were correlated with echocardiographic diagnostic signs, which allows using this echocardiographic, noninvasive method characterizing the intracardiac hemodynamics as a major criterion for the presence / absence of this pathology.

Sign in / Sign up

Export Citation Format

Share Document