Recent advancements and applications of deep learning in heart failure: Α systematic review.

BACKGROUND: Heart failure (HF), a global health challenge, requires innovative diagnostic and management approaches. The rapid evolution of deep learning (DL) in healthcare necessitates a comprehensive review to evaluate these developments and their potential to enhance HF evaluation, aligning clinical practices with technological advancements. OBJECTIVE: This review aims to systematically explore the contributions of DL technologies in the assessment of HF, focusing on their potential to improve diagnostic accuracy, personalize treatment strategies, and address the impact of comorbidities. METHODS: A thorough literature search was conducted across four major electronic databases: PubMed, Scopus, Web of Science and IEEE Xplore, yielding 137 articles that were subsequently categorized into five primary application areas: cardiovascular disease (CVD) classification, HF detection, image analysis, risk assessment, and other clinical analyses. The selection criteria focused on studies utilizing DL algorithms for HF assessment, not limited to HF detection but extending to any attempt in analyzing and interpreting HF-related data. RESULTS: The analysis revealed a notable emphasis on CVD classification and HF detection, with DL algorithms showing significant promise in distinguishing between affected individuals and healthy subjects. Furthermore, the review highlights DL's capacity to identify underlying cardiomyopathies and other comorbidities, underscoring its utility in refining diagnostic processes and tailoring treatment plans to individual patient needs. CONCLUSIONS: This review establishes DL as a key innovation in HF management, highlighting its role in advancing diagnostic accuracy and personalized care. The insights provided advocate for the integration of DL in clinical settings and suggest directions for future research to enhance patient outcomes in HF care.

An echocardiographic study of acute, progressive cardiac changes following a 246 km running race.

We describe the case of an ultra-marathon runner who finished first the "Spartathlon", a 246 km running race. The finishing time was the second fastest time ever in "Spartathlon". After finishing the race, the athlete suffered non-cardiac syncope and was administered intravenously 3 L of fluids for 5 hours. He underwent two echocardiographic assessments, one immediately after the finish of the race and the second 5 h later. Post-exercise fluid administration led to an increase in dimensions of all cardiac cavities, accompanied by a decrease in left ventricular (LV) end-diastolic interventricular septum thickness and posterior wall thickness of 0.1 cm. Dimensions and the respiratory profile of inferior vena cava improved after the race, reflecting alleviation of exercise-related hypovolaemia. Additionaly, LV global longitudinal strain improved, but right ventricular (RV) systolic function continued to deteriorate, mainly due to impairment of basal and medial RV free wall longitudinal strain. Study of this case offers a unique model for understanding the successive changes of cardiac structure and function following an ultra-marathon running race.

Clinical Validation of an Artificial Intelligence-Based Tool for Automatic Estimation of Left Ventricular Ejection Fraction and Strain in Echocardiography: Protocol for a Two-Phase Prospective Cohort Study.

BACKGROUND: Echocardiography (ECHO) is a type of ultrasonographic procedure for examining the cardiac function and morphology, with functional parameters of the left ventricle (LV), such as the ejection fraction (EF) and global longitudinal strain (GLS), being important indicators. Estimation of LV-EF and LV-GLS is performed either manually or semiautomatically by cardiologists and requires a nonnegligible amount of time, while estimation accuracy depends on scan quality and the clinician's experience in ECHO, leading to considerable measurement variability. OBJECTIVE: The aim of this study is to externally validate the clinical performance of a trained artificial intelligence (AI)-based tool that automatically estimates LV-EF and LV-GLS from transthoracic ECHO scans and to produce preliminary evidence regarding its utility. METHODS: This is a prospective cohort study conducted in 2 phases. ECHO scans will be collected from 120 participants referred for ECHO examination based on routine clinical practice in the Hippokration General Hospital, Thessaloniki, Greece. During the first phase, 60 scans will be processed by 15 cardiologists of different experience levels and the AI-based tool to determine whether the latter is noninferior in LV-EF and LV-GLS estimation accuracy (primary outcomes) compared to cardiologists. Secondary outcomes include the time required for estimation and Bland-Altman plots and intraclass correlation coefficients to assess measurement reliability for both the AI and cardiologists. In the second phase, the rest of the scans will be examined by the same cardiologists with and without the AI-based tool to primarily evaluate whether the combination of the cardiologist and the tool is superior in terms of correctness of LV function diagnosis (normal or abnormal) to the cardiologist's routine examination practice, accounting for the cardiologist's level of ECHO experience. Secondary outcomes include time to diagnosis and the system usability scale score. Reference LV-EF and LV-GLS measurements and LV function diagnoses will be provided by a panel of 3 expert cardiologists. RESULTS: Recruitment started in September 2022, and data collection is ongoing. The results of the first phase are expected to be available by summer 2023, while the study will conclude in May 2024, with the end of the second phase. CONCLUSIONS: This study will provide external evidence regarding the clinical performance and utility of the AI-based tool based on prospectively collected ECHO scans in the routine clinical setting, thus reflecting real-world clinical scenarios. The study protocol may be useful to investigators conducting similar research. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/44650.

Iron therapy and severe arrhythmias in HFrEF: rationale, study design, and baseline results of the RESAFE-HF trial.

AIMS: The Iron Intravenous Therapy in Reducing the burden of Severe Arrhythmias in HFrEF (RESAFE-HF) registry study aims to provide real-word evidence on the impact of intravenous ferric carboxymaltose (FCM) on the arrhythmic burden of patients with heart failure with reduced ejection fraction (HFrEF), iron deficiency (ID), and implanted cardiac implantable electronic devices (CIEDs). METHODS AND RESULTS: The RESAFE-HF (NCT04974021) study was designed as a prospective, single-centre, and open-label registry study with baseline, 3, 6, and 12 month visits. Adult patients with HFrEF and CIEDs scheduled to receive IV FCM as treatment for ID as part of clinical practice were eligible to participate. The primary endpoint is the composite iron-related endpoint of haemoglobin ≥ 12 g/dL, ferritin ≥ 50 ng/L, and transferrin saturation > 20%. Secondary endpoints include unplanned HF-related hospitalizations, ventricular tachyarrhythmias detected by CIEDs and Holter monitors, echocardiographic markers, functional status (VO2 max and 6 min walk test), blood biomarkers, and quality of life. In total, 106 patients with a median age of 72 years (14.4) were included. The majority were male (84.9%), whereas 92.5% of patients were categorized to New York Heart Association II/III. Patients' arrhythmic burden prior to FCM administration was significant-19 patients (17.9%) received appropriate CIED therapy for termination of ventricular tachyarrhythmia in the preceding 12 months, and 75.5% of patients have frequent, repetitive multiform premature ventricular contractions. CONCLUSIONS: The RESAFE-HF trial is expected to provide evidence on the effect of treating ID with FCM in HFrEF based on real-world data. Special focus will be given on the arrhythmic burden post-FCM administration.

Angiographic predictors of aberrant circumflex artery during cardiac catheterization.

OBJECTIVES: To identify angiographic predictors of aberrant left circumflex artery (LCx) by comparing left main (LM) length and bifurcation angle between patients with aberrant LCx and normal anatomy. BACKGROUND: Failure to recognize aberrant LCx during a cardiac catheterization may hamper correct diagnosis, delay intervention in acute coronary syndromes, and result in increased contrast volume, radiation exposure, and infarct size. METHODS: We retrospectively analyzed angiograms of aberrant LCx patients and normal anatomy matched controls, in three-participating centers. LM-length, bifurcation angle between the left anterior descending (LAD) and the first non-LAD branch of the LM, and procedural data were compared. RESULTS: Between 2003 and 2020, 136 patients with aberrant LCx and 135 controls were identified. More catheters (2.4 ± 0.6 vs. 2.2 ± 0.9, p = 0.009), larger contrast volumes (169 ± 94 ml vs. 129 ± 68 ml, p < 0.0005), and prolonged fluoroscopy time (652.9 ± 623.7 s vs. 393.1 ± 332.1 s, p < 0.0005), were required in the aberrant LCx-group compared with controls. Patients with aberrant LCx had a longer LM-length and a more acute bifurcation angle, both in caudal and cranial views, compared with controls (24.7 ± 8.1 vs. 10.8 ± 4.5 mm, p < 0.0005 and 26.7 ± 7.4 vs. 12 ± 5.5 mm, p < 0.0005, respectively, and 45.2° ± 12° vs. 88.8° ± 23°, p < 0.0005 and 51.9° ± 21° vs. 68.2° ± 28.3°, p < 0.0005, respectively). In ROC analysis, LM-length showed the best diagnostic accuracy for detecting aberrant LCx. In multiple logistic regression analysis, a cranially measured LM-length > 17.7 mm was associated with a 5.3 times greater probability of predicting aberrant LCx [95% CI (3.4-8.1), p < 0.0001]. CONCLUSIONS: Our study suggests that a long LM-length and an acute bifurcation angle can indicate the presence of aberrant LCx. We present a practical algorithm for its rapid identification.

Neuromuscular diseases and their cardiac manifestations under the spectrum of cardiovascular imaging.

Neuromuscular diseases (NMDs) include a broad spectrum of disorders that affect motor unit in every possible site, extending from the cell body of peripheral nerves to the muscle. The different lesion sites make this group of inherited disorders difficult to diagnose. Many NMDs, especially those involving skeletal muscles, can present significant cardiovascular complications, ranging from rhythm disturbances to the development of dilated or hypertrophic cardiomyopathy. Heart disease represents a major cause of morbidity and mortality among NMD patients, underlining the vital need for further familiarization with the pathogenesis and assessment of cardiac involvement. Cardiovascular imaging is the cornerstone for the evaluation of heart disorders in NMDs, with conventional echocardiography still offering a portable, affordable, and easily accessible solution. Meanwhile, newer echocardiographic techniques such as speckle tracking imaging in combination with cardiac magnetic resonance add new insights into further substrate characterization. The purpose of this review is to offer a brief presentation of the main NMDs and their cardiovascular complications, as well as the presentation of data that highlight the importance of cardiovascular imaging in early diagnosis, monitoring, and prognosis of these patients. Lastly, the authors provide a simple guide about which clinical features, imaging findings, and follow-up plan to adopt in each myopathic disorder.

Impact of a 246 Km ultra-marathon running race on heart: Insights from advanced deformation analysis.

Although previous studies suggest that prolonged intense exercise such as marathon running transitorily alters cardiac function, there is little information regarding ultramarathon races. Aim of this study was to investigate the acute impact of ultra-endurance exercise (UEE) on heart, applying advanced strain imaging. Echocardiographic assessment was performed the day before and at the finish line of "Spartathlon": A 246 Km ultra-marathon running race. 2D speckle-tracking echocardiography was performed in all four chambers, evaluating longitudinal strain (LS) for both ventricles and atria. Peak strain values and temporal parameters adjusted for heart rate were extracted from the derived curves. Out of 60 participants initially screened, 27 athletes (19 male, age 45 ± 7 years) finished the race in 33:34:27(28:50:38-35:07:07) hours. Absolute values of right (RV) and left ventricular (LV) LS (RVLS -22.9 ± 3.6 pre- to -21.2 ± 3.0% post-, p=0.04 and LVLS -20.9 ± 2.3 pre- to -18.8 ± 2.0 post-, p=0.009) slightly decreased post-race, whereas atrial strain did not change. RV and LV LS decrease was caused mainly by strain impairment of basal regions with apical preservation. Inter-chamber relationships assessed through RV/LV, LV/LA, RV/RA and RA/LA peak values' ratios remained unchanged from pre to post-race. Finally, UEE caused an extension of the systolic phase of cardiac cycle with concomitant diastole reduction (p<0.001 for all strain curves). Conclusively, ventricular LS strain as well as effective diastolic period slightly decreased, whereas atrial strain and inter-chamber relationships remained unchanged after running a 246-km-ultra-marathon race. These changes may be attributed to concomitant pre- and afterload alterations following UEE.

Relationship of Mechanical Dyssynchrony and LV Remodeling With Improvement of Mitral Regurgitation After CRT.

OBJECTIVES: The aim of this study was to explore the association between mechanical dyssynchrony of the left ventricle before cardiac resynchronization therapy (CRT) and improvement of mitral regurgitation (MR) after CRT. BACKGROUND: MR is very frequent among patients with dilated cardiomyopathy and conduction delay. METHODS: Echocardiograms (pre-CRT and 12 ± 3.8 months thereafter) of 314 patients with dilated cardiomyopathy and any degree of MR, who underwent CRT device implantation according to guidelines, were analyzed. Left ventricular (LV) mechanical dyssynchrony was assessed by apical rocking (ApRock) and septal flash (SF), while MR severity was graded from I to IV on the basis of vena contracta width, regurgitation jet size, and proximal isovelocity surface area. RESULTS: At baseline, 30% of patients presented with severe MR (grade III or IV). In 62% of patients, MR decreased after CRT, and these patients more frequently had left bundle branch block, had more severe MR, had more dilated left ventricles, had lower ejection fractions, and more often had ApRock and SF. Reverse remodeling was more frequent among patients with MR reduction (ΔLV end-systolic volume -35.5% ± 27.2% vs -4.1% ± 33.2%; P < 0.001). In a multivariable logistic stepwise regression, only ApRock (odds ratio [OR]: 3.8; 95% CI: 1.7-8.5; P = 0.001), SF (OR: 3.6; 95% CI: 1.6-7.9; P = 0.002), and baseline MR (OR: 1.4; 95% CI: 1.0-1.9; P = 0.046) remained significantly associated with MR reduction. CONCLUSIONS: ApRock, SF, and severity of MR at baseline are strongly associated with MR reduction after CRT, while LV reverse remodeling is its underlying mechanism. Therefore, in patients with heart failure with LV dyssynchrony on optimal medical treatment, CRT should be the primary treatment attempt for relevant MR.

Exploring the Anthropometric, Cardiorespiratory, and Haematological Determinants of Marathon Performance.

AIM: We aimed to investigate the main anthropometric, cardiorespiratory and haematological factors that can determine marathon race performance in marathon runners. METHODS: Forty-five marathon runners (36 males, age: 42 ± 10 years) were examined during the training period for a marathon race. Assessment of training characteristics, anthropometric measurements, including height, body weight (n = 45) and body fat percentage (BF%) (n = 33), echocardiographic study (n = 45), cardiopulmonary exercise testing using treadmill ergometer (n = 33) and blood test (n = 24) were performed. We evaluated the relationships of these measurements with the personal best marathon race time (MRT) within a time frame of one year before or after the evaluation of each athlete. RESULTS: The training age regarding long-distance running was 9 ± 7 years. Training volume was 70 (50-175) km/week. MRT was 4:02:53 ± 00:50:20 h. The MRT was positively associated with BF% (r = 0.587, p = 0.001). Among echocardiographic parameters, MRT correlated negatively with right ventricular end-diastolic area (RVEDA) (r = -0.716, p < 0.001). RVEDA was the only independent echocardiographic predictor of MRT. With regard to respiratory parameters, MRT correlated negatively with maximum minute ventilation indexed to body surface area (VEmax/BSA) (r = -0.509, p = 0.003). Among parameters of blood test, MRT correlated negatively with haemoglobin concentration (r = -0.471, p = 0.027) and estimated haemoglobin mass (Hbmass) (r = -0.680, p = 0.002). After performing multivariate linear regression analysis with MRT as dependent variable and BF% (standardised ß = 0.501, p = 0.021), RVEDA (standardised ß = -0.633, p = 0.003), VEmax/BSA (standardised ß = 0.266, p = 0.303) and Hbmass (standardised ß = -0.308, p = 0.066) as independent variables, only BF% and RVEDA were significant independent predictors of MRT (adjusted R2 = 0.796, p < 0.001 for the model). CONCLUSIONS: The main physiological determinants of better marathon performance appear to be low BF% and RV enlargement. Upregulation of both maximum minute ventilation during exercise and haemoglobin mass may have a weaker effect to enhance marathon performance. CLINICAL TRIAL REGISTRATION: www.ClinicalTrials.gov, identifier NCT04738877.

The impact of atrial mechanical function on age-dependent presentation of neurocardiogenic syncope.

BACKGROUND: The contribution of atrial and ventricular function in neurocardiogenic syncope (NCS) pathophysiology is elusive. HYPOTHESIS: We assessed the influence of echocardiographic properties to the age of presentation and NCS recurrences. METHODS: We assigned 124 patients with symptoms suggesting NCS, to those with syncope initiation at age <35 (group A, n = 56) and >35 years (group B, n = 68). Echocardiographic indices were measured before head-up tilt test (HUTT). RESULTS: A total of 55 had positive HUTT (44%) with a trend favoring group A (p = .08). Group A exhibited lower left atrial (LA) volume index (17 ± 6 vs. 22 ± 11 ml/m2 , p = .015), higher LA ejection fraction (69 ± 10 vs. 63 ± 11%, p = .008), LA peak strain (reservoir phase 41 ± 13 vs. 31 ± 14%, p = .001, contraction phase 27 ± 11 vs. 15 ± 10%, p < .001) and LA peak strain rate (reservoir phase 1.83 ± 1.04 vs. 1.36 ± 0.96 1/s, p = .012, conduit phase 2.36 ± 1.25 vs. 1.36 ± 0.78 1/s, p = .001). Group A showed smaller minimum right atrial (RA) volume, better RA systolic function, superior left ventricular diastolic indices, and lower filling pressures. Group A patients were more likely to have >3 recurrences (82.0% vs. 50.1%, p < .05). CONCLUSIONS: Patients with younger age of NCS onset and more syncopal recurrences manifest smaller LA and RA dimensions with distinct patterns of systolic and diastolic function and better LA reservoir and contraction properties. These findings may indicate an increased susceptibility to preload reduction, thereby triggering the NCS mechanism.

Fibrosis in hypertrophic cardiomyopathy: role of novel echo techniques and multi-modality imaging assessment.

Hypertrophic cardiomyopathy (HCM) represents one of the primary cardiomyopathies and may lead to heart failure and sudden cardiac death. Among various histologic features of the disease examined, assessment of myocardial fibrosis may offer valuable information, since it may be considered the common nominator for all HCM connected complications. Late gadolinium-enhanced cardiac magnetic resonance (LGE-CMR) has emerged as the reference noninvasive method for visualizing and quantifying myocardial fibrosis in patients with HCM. T1 mapping, a promising new CMR technique, may provide an advantage over conventional LGE-CMR, by permitting a more valid quantification of diffuse fibrosis. On the other hand, echocardiography offers a significantly more portable, affordable, and easily accessible solution for the study of fibrosis. Various echocardiographic techniques ranging from integrated backscatter and contrast-enhanced ultrasound to two- (2D) or three-dimensional (3D) deformation and shear wave imaging may offer new insights into substrate characterization in HCM. The aim of this review is to describe thoroughly all different modalities that may be used in everyday clinical practice for HCM fibrosis evaluation (with special focus on echocardiographic techniques), to concisely present available evidence and to argue in favor of multi-modality imaging application. It is essential to understand that the role of various imaging modalities is not competitive but complementary, since the information provided by each one is necessary to illuminate the complex pathophysiologic pathways of HCM, offering a personalized approach and treatment in every patient.

Arterial Function after a 246 km Ultra-marathon Running Race.

There is little research about the effects of ultra-endurance exercise on arterial morphological and functional properties. The aim was to assess the acute changes of the carotid-femoral pulse wave velocity and carotid doppler-derived parameters following an ultra-marathon race as well as the intima-media thickness of the carotid artery in ultra-marathon runners. Twenty athletes were examined at baseline and within 10 mins after a 246 km running race. Measurements included carotid-femoral pulse wave velocity, peak-systolic and end-diastolic velocities of carotid artery blood flow, pulsatility and resistivity indices and blood biochemical parameters. The intima-media thickness of the right and left carotid artery was measured before the race. Arterial stiffness and carotid artery intima media thickness at rest remained within known normal limits. The ultra-marathon race significantly increased carotid-femoral pulse wave velocity by 22.6% and pulsatility index by 10.2%. There was a decrease in body weight by 3.35% and an increase of all biochemical markers of muscle damage after the race. Additionally, C-reactive protein was correlated with both pulsatility and resistivity indices post-race. This study shows that immediately after a 246 km ultra-marathon running race, acute increase of arterial stiffness and vascular resistance were evident. The carotid artery thickness of ultra-marathon runners was within normal range.

Inter-vendor variability in strain measurements depends on software rather than image characteristics.

Despite standardization efforts, vendors still use specific proprietary software algorithms for echocardiographic strain measurements, which result in high inter-vendor variability. Using vendor-independent software could be one solution. Little is known, however, how vendor specific image characteristics can influence tracking results of such software. We therefore investigated the reproducibility, accuracy, and scar detection ability of strain measurements on images from different vendors by using a vendor-independent software. A vendor-independent software (TomTec Image Arena) was used to analyse datasets of 63 patients which were obtained on machines from four different ultrasound machine vendors (GE, Philips, Siemens, Toshiba). We measured the tracking feasibility, inter-vendor bias, the relative test-re-test variability and scar discrimination ability of strain measurements. Cardiac magnetic resonance delayed enhancement images were used as the reference standard of scar definition. Tracking feasibility on vendor datasets were significantly different (p < 0.001). Variability of global longitudinal strain (GLS) measurements was similar among the vendors whereas variability of segmental longitudinal strain (SLS) showed modest difference. Relative test-re-test variability of GLS and SLS showed no relevant differences. No significant difference in scar detection capability was observed. Average GLS and SLS values were similar among vendors. Reproducibility of GLS measurements showed no difference among vendors and was in acceptable range. SLS reproducibility was high but similar for all vendors. No relevant difference was found for identifying regional dysfunction. Tracking feasibility showed a substantial difference among images from different vendors. Our findings demonstrate that tracking results depend mainly on the software used and show little influence from vendor specific image characteristics.

Impact of centre volume on atrial fibrillation ablation outcomes in Europe: a report from the ESC EHRA EORP Atrial Fibrillation Ablation Long-Term (AFA LT) Registry.

AIMS: The aim of the study was to investigate differences in clinical outcomes and complication rates among European atrial fibrillation (AF) ablation centres related to the volume of AF ablations performed. METHODS AND RESULTS: Data for this analysis were extracted from the ESC EHRA EORP European AF Ablation Long-Term Study Registry. Based on 33rd and 67th percentiles of number of AF ablations performed, the participating centres were classified into high volume (HV) (≥ 180 procedures/year), medium volume (MV) (<180 and ≥74/year), and low volume (LV) (<74/year). A total of 91 centres in 26 European countries enrolled in 3368 patients. There was a significantly higher reporting of cardiovascular complications and stroke incidence in LV centres compared with HV and MV (P = 0.039 and 0.008, respectively) and a lower success rate after AF ablation (55.3% in HV vs. 57.2% in LV vs. 67.4% in MV centres, P < 0.001), despite lower CHA2DS2-VASc score of patients, enrolled in LVs and less complex ablation techniques used. Adjustments of confounding factors (including type of AF ablation) led to elimination of these differences. CONCLUSION: Low-volume centres tended to present slightly higher cardiovascular complications' and stroke incidence and a lower unadjusted success rate after AF ablation, despite the fact that ablation procedures and patients were of lower risk compared with MV and HV centres. On the other hand, adjusted overall complication and recurrence rates were non-significantly different among different volume centres, a fact reflecting the heterogeneity of patient and procedural profiles, and a counterbalance between expertise and risk level among participating centres.