Management Of Heart Failure Patients Research Articles

Predicting mortality and hospitalization in heart failure using machine learning: A systematic literature review.

The partnership between humans and machines can enhance clinical decisions accuracy, leading to improved patient outcomes. Despite this, the application of machine learning techniques in the healthcare sector, particularly in guiding heart failure patient management, remains unpopular. This systematic review aims to identify factors restricting the integration of machine learning derived risk scores into clinical practice when treating adults with acute and chronic heart failure. Four academic research databases and Google Scholar were searched to identify original research studies where heart failure patient data was used to build models predicting all-cause mortality, cardiac death, all-cause and heart failure-related hospitalization. Thirty studies met the inclusion criteria. The selected studies' sample size ranged between 71 and 716790 patients, and the median age was 72.1 (interquartile range: 61.1-76.8) years. The minimum and maximum area under the receiver operating characteristic curve (AUC) for models predicting mortality were 0.48 and 0.92, respectively. Models predicting hospitalization had an AUC of 0.47 to 0.84. Nineteen studies (63%) used logistic regression, 53% random forests, and 37% of studies used decision trees to build predictive models. None of the models were built or externally validated using data originating from Africa or the Middle-East. The variation in the aetiologies of heart failure, limited access to structured health data, distrust in machine learning techniques among clinicians and the modest accuracy of existing predictive models are some of the factors precluding the widespread use of machine learning derived risk calculators.

POS-290 MANAGEMENT OF HEART FAILURE IN PATIENTS WITH CHRONIC KIDNEY DISEASE: A RETROSPECTIVE ANALYSIS OF 1,861 ADMISSIONS TO ST GEORGE'S HOSPITAL, LONDON

Heart failure (HF) is increasingly prevalent among patients with chronic kidney disease (CKD) and is a leading cause of hospitalisation and mortality in this cohort of patients. Previous studies have shown prognostic benefits of using renin-angiotensin-aldosterone system inhibitors (RAASi) in patients with CKD and HF in terms of disease progression and overall-mortality. However, there can sometimes be a reluctance to prescribe these medications in patients with HF and CKD due to concerns about hyperkalaemia and nephrotoxicity. The extent to which actual HF management practices differ for patients with and without CKD is unclear. To address this, we conducted an audit to describe the current management of HF in patients with CKD presenting with HF at a large teaching hospital. We accessed the UK National Heart Failure audit data for our hospital. This database relates to patients who had an unscheduled admission from March 2013–May 2020 and a primary discharge diagnosis of heart failure. We included patients who had confirmed left ventricular systolic dysfunction on echocardiogram and survived to discharge. To define CKD stage, we linked this data to laboratory records to calculate the average estimated glomerular filtration rate (eGFR) in the year preceding admission, grouped according to KDIGO CKD classification. Rates of HF medications at discharge were compared across CKD stages via chi-square test. Odds ratios for being prescribed RAASi (ACE inhibitor or angiotensin II receptor blocker) at discharge were adjusted for age and HF severity (graded by brain natriuretic peptide level) in a logistic regression model. For sensitivity analysis, we analysed prescribed medication according to discharge eGFR and CKD diagnosis on the electronic health record preceding admission. 1861 admissions with HF were recorded, representing a cohort of 1380 patients. This cohort was predominantly male (65.99%), white (46.96%) and had a median age of 75.0 years. 43.62% of admissions (n=812) had an eligible baseline eGFR to define CKD stage. Of these admissions, 75% had evidence of at least stage 3a CKD (n=614), with 15% having evidence of CKD stage 4 or 5 (n=123). Significantly less RAASi were prescribed in patients with CKD3a or higher (55.04% in CKD group vs. 76.26% of patients without CKD, p<0.001, adjusted OR of being prescribed RAASi in CKD 0.46, 95% CI 0.31 – 0.68). There was a progressive reduction in the use of RAASi with increasing stage of CKD. Beta-blockade and loop diuretic prescribing was consistent across groups, apart from CKD 5 where less were prescribed (figure). Findings were robust to sensitivity analysis. CKD is very prevalent in patients presenting with acute HF. Patients with HF and CKD are prescribed similar rates of beta-blockers but lower rates of RAASi compared to the non-CKD population. The exact cause for such discrepancy is unclear but could be due to concerns about side-effects or polypharmacy. Given the benefits of RAASi in both HF and CKD, there is likely under-utilisation of RAASi in patients with CKD and HF. There is a need for more education and support around the initiation of RAASi in patients with HF and CKD. As with all retrospective studies, this data could be liable to confounding and missing data, particularly relating to outpatient medication changes, drug intolerances or contraindications.

The management of secondary mitral regurgitation in patients with heart failure: a joint position statement from the Heart Failure Association (HFA), European Association of Cardiovascular Imaging (EACVI), European Heart Rhythm Association (EHRA), and European Association of Percutaneous Cardiovascular Interventions (EAPCI) of the ESC.

Secondary (or functional) mitral regurgitation (SMR) occurs frequently in chronic heart failure (HF) with reduced left ventricular (LV) ejection fraction, resulting from LV remodelling that prevents coaptation of the valve leaflets. Secondary mitral regurgitation contributes to progression of the symptoms and signs of HF and confers worse prognosis. The management of HF patients with SMR is complex and requires timely referral to a multidisciplinary Heart Team. Optimization of pharmacological and device therapy according to guideline recommendations is crucial. Further management requires careful clinical and imaging assessment, addressing the anatomical and functional features of the mitral valve and left ventricle, overall HF status, and relevant comorbidities. Evidence concerning surgical correction of SMR is sparse and it is doubtful whether this approach improves prognosis. Transcatheter repair has emerged as a promising alternative, but the conflicting results of current randomized trials require careful interpretation. This collaborative position statement, developed by four key associations of the European Society of Cardiology—the Heart Failure Association (HFA), European Association of Percutaneous Cardiovascular Interventions (EAPCI), European Association of Cardiovascular Imaging (EACVI), and European Heart Rhythm Association (EHRA)—presents an updated practical approach to the evaluation and management of patients with HF and SMR based upon a Heart Team approach.

Advances in cardiac resynchronization and implantable cardioverter/defibrillator therapy: Medtronic Cobalt and Crome.

Cardiovascular implantable electronic devices have revolutionized the management of heart failure with reduced ejection fraction. New device generations tend to be launched every few years, with incremental improvements in performance and safety and with an expectation that these will improve patient management and outcomes while remaining cost-effective. As a result, today's cardiac resynchronization therapy (CRT) and implantable cardioverter defibrillator devices are quite different from the pioneering but often bulky devices of the late 20th century. This review discusses new and improved features developed to target specific needs in managing heart failure patients, some of which are especially pertinent to the current worldwide healthcare situation, with focus on the latest generation of CRTs with defibrillator (CRT-Ds) and implantable cardioverter defibrillators from Medtronic.

Characterizing the role of, and physical and emotional burden on caregivers of patients with heart failure: Results from a cross-sectional survey in Japan

The aim of this cross-sectional survey was to characterize the role of and burden on caregivers of heart failure (HF) patients in Japan, since such data are limited at present. Data from 126 caregivers whose average age was 63.5 years were analyzed. Helping to prepare meals/cooking was the most frequently reported activity (47% of caregivers); 24% found this the most burdensome. The most frequently reported physical consequence of caregiving was feeling physically tired (44%); emotionally worrying about the patient (62%) was the most frequent psychological consequence. Approximately half of the caregivers reported that caring for patients impacted their lifestyle. Although 40% of caregivers asked questions to physicians regarding diet or lifestyle modifications, 19% did not ask any. Caregivers play a crucial role in the management of HF patients in Japan but experience physical and emotional burden. Solutions are required to reduce the caregiver burden associated with HF.

Impact of telemedicine on the management of heart failure patients during coronavirus disease 2019 pandemic.

AimsChronic heart failure (HF) is a major comorbidity accounting for an increased severity and mortality related to coronavirus disease 2019 (COVID‐19). To reduce the risk of COVID‐19 in HF patients, telemedicine has been encouraged.Methods and resultsDuring the COVID‐19 pandemic, telemedical management with mainly over‐the‐phone appointments became a major strategy of follow‐up of our HF clinic patients. Previously, the large majority of patients have been seen in the hospital with direct patient‐provider contact. We compared both strategies of follow‐up, in pre‐pandemic (PPP) and pandemic (PP) periods, regarding total mortality and hospitalizations/emergency department (ED) visits due to HF exacerbation. We prospectively studied a cohort of 196 patients. The mean follow‐up time in PPP was 1.4 years. In this period, 20 patients died. In PP (follow‐up of 71 days), there was one additional death. Total mortality in the first year of follow‐up was 12.0%, matching the mortality predicted by the Meta‐Analysis Global Group in Chronic Heart Failure score. Considering hospitalizations/ED visits due to decompensated HF, there was no statistically significant difference between PPP and PP. Only one patient was diagnosed with COVID‐19.ConclusionsIn the light of an increase in telemedical management of this cohort of HF patients, we were able to maintain a low rate of admissions due to HF decompensation, without an increment in mortality. Regarding these results, we encourage the incremental use of telemedicine in HF patients in the context of this or future pandemics and also in situations in which physical consultation might not be possible due to logistic issues.

Hybrid transcatheter left ventricular reconstruction for the treatment of ischemic cardiomyopathy.

Left ventricular (LV) enlargement is a mechanical adaptation to accommodate LV systolic inefficiency following an acute damage or a progressive functional deterioration, which fails to correct the decline of stroke volume in the long term, leading to progressive heart failure (HF). Surgical ventricular reconstruction (SVR) is a treatment for patients with severe ischemic HF aiming to restore LV efficiency by volume reduction and LV re-shaping. Recently, a new minimally-invasive hybrid technique for ventricular reconstruction has been developed by means of the Revivent™ system (BioVentrix Inc., San Ramon, CA, USA). The device for ventricular reconstruction consists of anchor pairs that enable plication of the anterior and free wall LV scar against the right ventricular (RV) septal scar of anteroseptal infarctions to decrease cardiac volume without ventriculotomy in a beating-heart minimally-invasive procedure, consisting of a transjugular and left thoracotomy approach. Patients with severe (Grade 4) functional mitral regurgitation (FMR) or with previous cardiac surgery procedures were excluded. Outcome of the reconstruction procedure: from 2012 until 2019, it has been applied to 203 patients, with 5 (2.5%) in-hospital deaths. LV volume reduction varied according to experience gained along years: LV end-systolic volume index decreased from baseline 43% (post-market registry) vs. 27% (CE-mark study); left ventricular ejection fraction (LVEF) increased from baseline 25% (post-market registry) vs. 16% (CE-mark study). Clinical status (NYHA class, HF questionnaire, 6-minute walking test) improved significantly compared to baseline, and re-hospitalization rate was only 13% at 6-month follow-up (60% of patients in NYHA =3). FMR grade decreased at follow-up in 63%, while it was unchanged in 37% of patients. The hybrid ventricular reconstruction (HVR) seems a promising treatment for HF patients who may benefit from LV volume reduction, with reasonable mortality and good results at follow-up. A baseline less severe clinical profile was not associated to better outcome at follow-up, which makes the procedure feasible in patients with very large ventricles and depressed ejection fraction (EF). LV reshaping has no detrimental effect on FMR, that may, on the contrary, benefit owing to less papillary muscle displacement, partial recovery of torsion dynamics and of myofibers re-orientation. A controlled study on top of optimal medical treatment is warranted to confirm its role in the management of HF patients.

Value of intraventricular dyssynchrony assessment by gated-SPECT myocardial perfusion imaging in the management of heart failure patients undergoing cardiac resynchronization therapy (VISION-CRT)

BackgroundPlacing the left ventricular (LV) lead in a viable segment with the latest mechanical activation (vSOLA) may be associated with optimal cardiac resynchronization therapy (CRT) response. We assessed the role of gated SPECT myocardial perfusion imaging (gSPECT MPI) in predicting clinical outcomes at 6 months in patients submitted to CRT. MethodsTen centers from 8 countries enrolled 195 consecutive patients. All underwent gSPECT MPI before and 6 months after CRT. The procedure was performed as per current guidelines, the operators being unaware of gSPECT MPI results. Regional LV dyssynchrony (Phase SD) and vSOLA were automatically determined using a 17 segment model. The lead was considered on-target if placed in vSOLA. The primary outcome was improvement in ≥1 of the following: ≥1 NYHA class, left ventricular ejection fraction (LVEF) by ≥5%, reduction in end-systolic volume by ≥15%, and ≥5 points in Minnesota Living With Heart Failure Questionnaire (MLHFQ). ResultsSixteen patients died before the follow-up gSPECT MPI. The primary outcome occurred in 152 out of 179 (84.9%) cases. Mean change in LV phase standard deviation (PSD) at 6 months was 10.5°. Baseline dyssynchrony was not associated with the primary outcome. However, change in LV PSD from baseline was associated with the primary outcome (OR 1.04, 95% CI 1.01-1.07, P = .007). Change in LV PSD had an AUC of 0.78 (0.66-0.90) for the primary outcome. Improvement in LV PSD of 4° resulted in the highest positive likelihood ratio of 7.4 for a favorable outcome. In 23% of the patients, the CRT lead was placed in the vSOLA, and in 42% in either this segment or in a segment within 10° of it. On-target lead placement was not significantly associated with the primary outcome (OR 1.53, 95% CI 0.71-3.28). ConclusionLV dyssynchrony improvement by gSPECT MPI, but not on-target lead placement, predicts clinical outcomes in patients undergoing CRT.

Beyond the stethoscope: managing ambulatory heart failure during the COVID-19 pandemic.

There have been nearly 70 million cases of COVID‐19 worldwide, with over 1.5 million deaths at the time of this publication. This global pandemic has mandated dramatic changes in healthcare delivery with a particular focus on social distancing in order to reduce viral transmission. Heart failure patients are among the highest utilizers of health care and are at increased risk for COVID‐related vulnerabilities. Effectively managing this complex and resource‐intensive patient population from a distance presents new and unique challenges. Here, we review relevant data on telemedicine and remote monitoring strategies for heart failure patients and provide a framework to help providers treat this population during the COVID‐19 pandemic. This includes (i) dedicated pre‐visit contact and planning (i.e. confirm clinical appropriateness, presence of compatible technology, and patient comfort); (ii) utilization of virtual clinic visits (use of telehealth platforms, a video‐assisted exam, self‐reported vital signs, and weights); and (iii) use of existing remote heart failure monitoring sensors when applicable (CardioMEMS, Optivol, and HeartLogic). While telemedicine and remote monitoring strategies are not new, these technologies are emerging as an important tool for the effective management of heart failure patients during the COVID‐19 pandemic. In general, these strategies appear to be safe; however, additional data will be needed to determine their effectiveness with respect to both process and outcomes measures.

MONITORIA: The start of a new era of ambulatory heart failure monitoring? Part I – Theoretical Rationale

Heart failure (HF) is a multifactorial chronic syndrome with progressive increasing incidence causing a huge financial burden worldwide.Remote monitoring should, in theory, improve HF management, but given increasing morbidity and mortality, a question remains: are we monitoring it properly?Device-based home monitoring enables objective and continuous measurement of vital variables and non-invasive devices should be first choice for elderly patients. There is no shortage of literature on the subject, however, most studies were designed to monitor a single variable or class of variables that were not properly assembled and, to the best of our knowledge, there are no large randomized studies about their impact on HF patient management. To overcome this problem, we carefully selected the most critical possible HF decompensating factors to design MONITORIA, a non-invasive device for comprehensive HF home monitoring.MONITORIA stands for MOnitoring Non-Invasively To Overcome mortality Rates of heart Insufficiency on Ambulatory, and in this paper, which is part I of a series of three articles, we discuss the theoretical basis for its design.MONITORIA and its inherent follow-up strategy will optimize HF patient care as it is a promising device, which will essentially adapt innovation not to the disease but rather to the patients.

Heart failure and COVID-19: synergism of two inflammatory conditions?

Heart failure as a comorbidity in the older population with COVID-19 poses an additional threat to those affected. Patients with both COVID-19 and heart failure share similar risk factors, which result in magnification of pathological outcomes. These include a common inflammatory pathology and related coagulopathy. Both illnesses pose a risk of arrhythmia. Polypharmacy further complicates safe drug administration and worsens the risk of medication-induced arrhythmia. Additionally, both conditions present challenges regarding attaining and maintaining an appropriate nutritional state. Exploration of the interplay between these factors demonstrates the gravity of the co-existence of these conditions and helps understand the difficulties faced when caring for this patient group. Although care provided to COVID-19 patients is primarily related to symptom presentation, based on the analysis conducted, there are some recommendations for practice in relation to evidence and guidelines when managing heart failure patients in primary care within the context of the COVID-19 pandemic.

Contemporary management of heart failure patients with reduced ejection fraction: the role of implantable devices and catheter ablation

Heart failure (HF) is a complex clinical syndrome characterised by significant morbidity and mortality worldwide. Evidence-based therapies for the management of HF include several well-established neurohormonal antagonists and antiarrhythmic drug therapy to mitigate the onset of cardiac arrhythmia. However, the degree of rate and rhythm control achieved is often suboptimal and mortality rates continue to remain high. Implantable cardioverter-defibrillators (ICDs), cardiac resynchronization (CRT), and combined (CRT-D) therapies have emerged as integral and rapidly expanding technologies in the management of select patients with heart failure with reduced ejection fraction (HFrEF). ICDs treat ventricular arrhythmia and are used as primary prophylaxis for sudden cardiac death, while CRT resynchronizes ventricular contraction to improve left ventricular systolic function. Left ventricular assist device therapy has also been shown to provide clinically meaningful survival benefits in patients with advanced HF, and His-bundle pacing has more recently emerged as a safe, viable, and promising pacing modality for patients with CRT indication. Catheter ablation is another important and well-established strategy for managing cardiac arrhythmia in HF, demonstrating superior efficacy when compared with antiarrhythmic drug therapy alone. In this article, we provide a comprehensive and in-depth evaluation of the role of implantable devices and catheter ablation in patients with HFrEF, outlining current applications, recent advances, and future directions in practice.

First experience with a ready to use solution for remote monitoring of patients suffering from heart failure in France

Heart failure (HF) is associated with a high mortality rate and recurrent hospitalizations. To present the first data of the patients using the innovative solution Satelia® Cardio (NP Medical/WeHealth™ Digital Medicine). Satelia® Cardio is a HF patient management solution with a remote monitoring system and a therapeutic guidance by dedicated nurse phone platform, supported by ETAPES Program. The system is accessible from any devices, requiring no installation, and the use is possible by non-connected patients. After the inclusion, the patient is contacted by the nurse, he then receives an SMS alert on regular basis, with a link leading to a web page to answer 7 questions, and to give his current body weight. Satelia algorithm is based on this signs,their variability, and the weight. In case of worsening of symptoms, the cardiologist will be notified. 124 centers (200 cardiologists) are using Satelia® Cardio with 1832 HF patients monitored in the last 18 months. The patients, mean age of 72 years (19-97) are predominantly males (69%), and mostly NYHA II/III (68%/30%). The adherence to the system is very good (81%) with 86% of patients still monitored (N = 1569). The main reasons for stopping are related to the occurrence of death (105/263) or non-fatal events (71/263), or patient decision (87/263). Over the period of analysis, the HF patients answered to 46 637 questionnaires, generating 2429 alerts transmitted to the referent cardiologists. Since Covid-19 lockdown, more than 600 patients have been monitored with the solution. Patient management solution with a remote monitoring system is key to improving the follow-up of HF patients. The solution Satelia® Cardio is an easy way to use a web application to monitor HF patients, accepted by the patients with a low rate of premature discontinuation. A further step will be to initiate studies to assess the clinical impact of such remote monitoring solution in HF.

Current Status of Nutrition Management in Heart Failure Patients

心不全患者における栄養状態は予後予測因子であり，その評価は重要である．栄養障害の要因は多岐にわたるが心機能の面からは左心機能より右心機能の関与が注目されている．栄養状態の評価は問診，採血項目，身体計測，バイオインピーダンス法などの生理機能検査などが行われているが決定的な方法は確立されていない．当院では簡便な指標としてエコーを用いた大腿直筋厚の有用性を報告してきた．また，退院前の食事摂取エネルギー量の評価をすることで必要な食事摂取ができているか評価をし，どのような要因がその阻害因子になっているかを検討して介入している．当院での取り組みを紹介しながら心不全患者における栄養について概説する

Exploring the opinion of stakeholders about self-care, home care and hospital management of heart failure patients: A qualitative study

Introduction Heart failure is a widespread chronic cardiac illness with varying etiologies. If the HF patients manage themselves at home by following the appropriate advice by healthcare professionals, they tend to have better quality of life and less readmissions. This study was aimed to identify and explore practices of self-management by heart failure patients, home management of heart failure by their family caregivers and hospital management by healthcare providers. Methods A qualitative study was conducted in a tertiary care center in Northern India on participants (patients, their family caregivers, doctors and nurses) who were recruited purposively and interviewed individually by principle investigator using semi-structured questionnaires. Interviews were audio recorded and transcribed after taking informed consent. Iterative process including coding, reviewing and analyzing was done by four researchers and themes were finalized. Results Total 41 participants (15 patients, 12 family caregivers, 4 doctors and 10 nurses) completed the interviews. It was observed that patients and family caregivers were not able to manage heart failure efficiently. Nurses and doctors reported many barriers to provide specialized care to these patients. Discussion There were definite barriers and challenges in the management of heart failure symptoms by the stakeholders. For the patients and family members who suffer this debilitating illness, managing heroically is a challenge. It is important to develop self-care management protocol for the heart failure patients. Healthcare professionals must overcome the barriers to train patients and family caregivers. Multidisciplinary integration can fulfill the gap in providing care to such patients.

PCV18 Use of Human-Centred Design Thinking to Reimagine Access to Innovative Medicines in Africa for Patients, Undetected for Heart Failure, WHO Have NO Access to Healthcare and Diagnostics - an Experimental Case Study

To explore the use of a human-centred approach to co-create patient access solutions to innovative heart failure (HF) medicines in Africa. We targeted patients undetected for HF who currently have no access to healthcare and diagnostics. We used a Design Thinking framework collaborating with a multidisciplinary cross-country team from Nigeria and South Africa and developed patient ecosystem maps to identify key stakeholders (e.g., community workers) for interviews to reveal access hurdles for these patients. A targeted literature review, accompanied with insights from Energy sector, inspired an outside-in perspective to the solution-finding process. We applied creative techniques and visual thinking to ideate and prototype solution concepts, addressing hurdles to access for the target patient population. We obtained the initial feedback from internal disease and access experts. Key hurdles for these patients were “low access to healthcare infrastructure” and “lack of disease awareness”. We identified government officials and community nurses as key stakeholders in the access path of HF patients. Lack of robust data supporting evidence-based decision-making, disease awareness, disease management systems and allocation of funds due to low priority of cardiovascular diseases for governments, are perceived as main challenges. Prototypes of solution concepts co-created by the African team consider (1) community-based multi-stakeholder HF management networks, (2) partnerships with professional associations for systematic real-world evidence generation using local diagnostics, mobile clinics and digital infrastructure to ultimately reach patients with no access to healthcare and (3) engage policy makers with data to enable policy change to improve the management of HF patients. A human-centred collaborative approach focusing on patient ecosystem can foster new ideas to solve complex and persistent healthcare problems. We can facilitate win-win situations to benefit inaccessible patients with HF by understanding their needs and deep diving into the pains and gains of key decision-makers and influencers.

Abstract 16766: Intraprocedural Ablation and Fluid Status Management in Heart Failure Patients Undergoing Catheter Ablation for Atrial Fibrillation

Background: Recent randomized clinical trial data has supported catheter ablation (CA) of atrial fibrillation (AF) in patients with heart failure (HF). Ablation and fluid management strategies could impact periprocedural outcomes especially in HF patients. Methods: We conducted a single-center retrospective analysis of 200 consecutive patients with and without HF undergoing CA at a tertiary care academic center from July 2017 through June 2018. HF was defined as any EF &lt; 40%, prior inpatient admission for HF exacerbation, or ambulatory management of HF confirmed by independent chart review. Diuretic regimens were reported as furosemide equivalent. Results: Among 200 patients, 65 (32.5%) had HF and 135 (67.5%) did not. HF patients had longer mean procedure times (299.8 ± 96 min vs 268.4 ± 96 min, p = 0.03) and were more likely to require mitral isthmus (p &lt; 0.001), posterior wall isolation (p = 0.002), and cavotriscupid isthmus (p = 0.004) ablations. There were no differences between the HF vs. non-HF groups’ intraprocedural volume intake, intraprocedural volume output, net fluid status, or intraprocedural diuretic dose (Table 1). HF patients received higher doses of IV (41.5 ± 43.0 mg vs 23.6 ± 11.8 mg, p = 0.007) and PO (43.2 ± 16.7 mg vs 26.7 ± 10.0 mg, p &lt; 0.001) postprocedural diuretic. There were no differences in the rates of major in-hospital complications (Table 1). In a multivariable regression analysis adjusted for procedural covariates, there were higher proportions of posterior wall isolation (p = 0.01) as well as postprocedural PO (p = 0.01) and IV diuretic (p = 0.002) administration in the HF cohort. Conclusion: Intraprocedural volume and diuretic management was similar between HF and non-HF patients undergoing CA of AF, though HF patients tended to receive more aggressive diuresis post procedurally with no difference in complications. Table 1. Intra- and post-procedural management and outcomes in HF vs non-HF patients undergoing CA for AF

Abstract 17060: Machine Learning and Video Recognition for Automated Detection of Fluid Status in Heart Failure Patients

Introduction: There is a need for innovative solutions to better screen and diagnose the 7 million patients with chronic heart failure. A key component of assessing these patients is monitoring fluid status by evaluating for the presence and height of jugular venous distension (JVD). We hypothesize that video analysis of a patient’s neck using machine learning algorithms and image recognition can identify the amount of JVD. We propose the use of high fidelity video recordings taken using a mobile device camera to determine the presence or absence of JVD, which we will use to develop a point of care testing tool for early detection of acute exacerbation of heart failure. Methods: In this feasibility study, patients in the Duke cardiac catheterization lab undergoing right heart catheterization were enrolled. RGB and infrared videos were captured of the patient’s neck to detect JVD and correlated with right atrial pressure on the heart catheterization. We designed an adaptive filter based on biological priors that enhances spatially consistent frequency anomalies and detects jugular vein distention, with implementation done on Python. Results: We captured and analyzed footage for six patients using our model. Four of these six patients shared a similar strong signal outliner within the frequency band of 95bpm – 200bpm when using a conservative threshold, indicating the presence of JVD. We did not use statistical analysis given the small nature of our cohort, but in those we detected a positive JVD signal the RA mean was 20.25 mmHg and PCWP mean was 24.3 mmHg. Conclusions: We have demonstrated the ability to evaluate for JVD via infrared video and found a relationship with RHC values. Our project is innovative because it uses video recognition and allows for novel patient interactions using a non-invasive screening technique for heart failure. This tool can become a non-invasive standard to both screen for and help manage heart failure patients.

Abstract 14884: Invasive Hemodynamic Remote Monitoring for Heart Failure: A Systematic Review and Meta-Analysis of Randomized Controlled Trials

Background: In heart failure (HF) patients, remote monitoring of hemodynamics using implantable devices may be used to predict and reduce HF exacerbations. Methods: A meta-analysis of randomized controlled trials (RCTs) testing remote monitoring versus standard of care for management of HF patients was performed. Endpoints included all-cause mortality and Cardiovascular (CV)/HF hospitalizations. Risk Ratios (RR) and 95% confidence intervals (CI) were calculated for each endpoint. A secondary analysis tested for heterogeneity of treatment effect (HTE) using Chi 2 and I 2 tests comparing implanted right ventricular/pulmonary pressure monitoring versus impedance-based monitoring on HF hospitalization. Results: 10 RCTs (n=6,020) were identified with a mean follow-up of 1.74 years. The mean age and reported ejection fraction were 64.1 and 27.1%, respectively. Remote monitoring did not reduce mortality (RR 0.88, [95% CI 0.76, 1.03]) or CV/HF hospitalizations (RR 0.99, [0.81, 1.20]) (Figure 1). When performing the test of subgroup differences, there was significant HTE for HF hospitalization between those studies that used implanted right ventricular/pulmonary pressure monitoring versus impedance-based monitoring (Chi 2 = 7.92, p = 0.005, I 2 = 87.4%). Conclusions: Compared to standard of care, remote monitoring of physiologic markers of HF did not reduce mortality and CV or HF hospitalization. However, right ventricular/pulmonary pressure monitoring may reduce HF hospitalization compared to impendence-based monitoring. Further studies are necessary to evaluate the role of remote monitoring in patients with heart failure.

Abstract 312: A Multi-view Echocardiography Video Deep Learning Model Outperforms the Seattle Heart Failure Model in Predicting Mortality

Introduction: Managing heart failure patients relies on mortality prediction models such as the Seattle Heart Failure (SHF) model. We hypothesized that a deep learning model that leverages echocardiography video data could improve prediction performance. Methods: We trained deep neural networks (DNN) to predict 1-year all-cause mortality using echocardiography videos and 158 additional clinical variables (labs, vitals, diagnoses, etc.) acquired from 34,362 patients (812,278 videos). We tested both the DNN and the SHF model on a separate cohort of 2,404 patients with heart failure who underwent 3,384 echocardiograms. We computed the area under the receiver operating characteristic curve (AUC) and its bootstrapped 95% confidence interval (CI) in the test set. Results: The DNN model (AUC of 0.76, 95% CI [0.74, 0.77]) outperformed the SHF model (AUC of 0.70, 95% CI [0.68, 0.71]). This superior performance was observed for patients with both reduced (n=2,026, AUC of 0.76 [0.74, 0.78] vs 0.70 [0.67, 0.72]) and preserved left ventricular ejection fraction (n=1,356, AUC of 0.75 [0.72, 0.78] vs 0.69 [0.66, 0.72]). A Cox Proportional Hazard survival analysis showed that, despite the prediction being for 1-year all-cause mortality, the result held long-term predictive power over the next 9 years with a superior hazard ratio of 2.9 [2.6, 3.2] for the DNN model compared to 2.2 [2, 2.4] for the SHF model. At mid-range operating points, the DNN model also maintained a higher negative predictive value, predicting survival, compared to the SHF model (89% vs 83%, respectively), while maintaining the same positive predictive value of 40%. Conclusion: A deep neural network that automatically analyzes echocardiography videos can outperform traditional risk modeling approaches such as the Seattle Heart Failure Model. This provides additional evidence that deep learning can help improve our ability to make clinically relevant predictions by leveraging complex datasets.