Search

Machine Learning (ML) has extended its use in several domains to support complex analyses of data. The medical field, in which significant quantities of data are continuously generated, is one of the domains that can benefit from the application of ML pipelines to solve specific problems such as diagnosis, classification, disease detection, segmentation, assessment of organ functions, etc. However, while health professionals are experts in their domain, they can lack programming and theoretical skills regarding ML applications. Therefore, it is necessary to train health professionals in using these paradigms to get the most out of the application of ML algorithms to their data. In this work, we present a platform to assist non-expert users in defining ML pipelines in the health domain. The system’s design focuses on providing an educational experience to understand how ML algorithms work and how to interpret their outcomes and on fostering a flexible architecture to allow the evolution of the available components, algorithms, and heuristics.

A novel rare mutation in the pore region of Nav1.5 channels (p.L889V) has been found in three unrelated Spanish families that produces quite diverse phenotypic manifestations (Brugada syndrome, conduction disease, dilated cardiomyopathy, sinus node dysfunction, etc.) with variable penetrance among families. We clinically characterized the carriers and recorded the Na+ current (INa) generated by p.L889V and native (WT) Nav1.5 channels, alone or in combination, to obtain further insight into the genotypic–phenotypic relationships in patients carrying SCN5A mutations and in the molecular determinants of the Nav1.5 channel function. The variant produced a strong dominant negative effect (DNE) since the peak INa generated by p.L889V channels expressed in Chinese hamster ovary cells, either alone (−69.4 ± 9.0 pA/pF) or in combination with WT (−62.2 ± 14.6 pA/pF), was significantly (n ≥ 17, p < 0.05) reduced compared to that generated by WT channels alone (−199.1 ± 44.1 pA/pF). The mutation shifted the voltage dependence of channel activation and inactivation to depolarized potentials, did not modify the density of the late component of INa, slightly decreased the peak window current, accelerated the recovery from fast and slow inactivation, and slowed the induction kinetics of slow inactivation, decreasing the fraction of channels entering this inactivated state. The membrane expression of p.L889V channels was low, and in silico molecular experiments demonstrated profound alterations in the disposition of the pore region of the mutated channels. Despite the mutation producing a marked DNE and reduction in the INa and being located in a critical domain of the channel, its penetrance and expressivity are quite variable among the carriers. Our results reinforce the argument that the incomplete penetrance and phenotypic variability of SCN5A loss-of-function mutations are the result of a combination of multiple factors, making it difficult to predict their expressivity in the carriers despite the combination of clinical, genetic, and functional studies.

Calcific aortic valve disease (CAVD) and coronary artery disease (CAD) are related cardiovascular diseases in which common mechanisms lead to tissue calcification. Oxidative stress plays a key role in these diseases and there is also evidence that the redox state of serum albumin exerts a significant influence on these conditions. To further explore this issue, we used multimarker scores (OxyScore and AntioxyScore) to assess the global oxidative status in patients with CAVD, with and without CAD, also evaluating their plasma thiol levels. In addition, valvular interstitial cells were treated with reduced, oxidized, and native albumin to study how this protein and its modifications affect cell calcification. The differences we found suggest that oxidative status is distinct in CAVD and CAD, with differences in redox markers and thiol levels. Importantly, the in vitro interstitial cell model revealed that modified albumin affects cell calcification, accelerating this process. Hence, we show here the importance of the redox system in the development of CAVD, emphasizing the relevance of multimarker scores, while also offering evidence of how the redox state of albumin influences vascular calcification. These data highlight the relevance of understanding the overall redox processes involved in these diseases, opening the door to new studies on antioxidants as potential therapies for these patients.

AimThis study aimed to evaluate the capacity of a genetic risk score (GRS) for coronary artery disease (CAD) independent of classical cardiovascular risk factors to assess the risk of recurrence in patients with first myocardial infarction. The secondary aim was to determine the predictive value of this GRS.MethodsWe performed a meta-analysis of individual data from three studies, namely, a prospective study including 75 patients aged

Machine Learning allows facing complex tasks related to data analysis with big datasets. This Artificial Intelligence branch allows not technical contexts to get benefits related to data processing and analysis. In particular, in medicine, medical professionals are increasingly interested in Machine Learning to identify patterns in clinical cases and make predictions regarding health issues. However, many do not have the necessary programming or technological skills to perform these tasks. Many different tools focus on developing Machine Learning pipelines, from libraries for developers and data scientists to visual tools for experts or platforms to learn. However, we have identified some requirements in the medical context that raise the need to create a customized platform adapted to end-user found in this context. This work describes the design process and the first version of KoopaML, an ML platform to bridge the data science gaps of physicians while automatizing Machine Learning pipelines. The platform is focused on enhanced interactivity to improve the engagement of physicians while still providing all the benefits derived from the introduction of Machine Learning pipelines in medical departments, as well as integrated ongoing training during the use of the tool’s features.

Background: Left atrial appendage occlusion (LAAO) is a safe and effective alternative to oral anticoagulation for thromboprophylaxis in patients with nonvalvular atrial fibrillation. Technological development in devices and imaging techniques, as well as accumulated experience, have increased procedural success rates and decreased complications. Same-day discharge protocols have been proposed in the field of structural heart disease, but this approach has not been studied in detail for the LAAO procedure. Aim: The aim of this study is to assess the safety and efficacy of an outpatient program for LAAO when compared to the conventional treatment approach. Methods: We present a retrospective, non-randomized single-center study of 262 consecutive patients undergoing LAAO. Patients were divided into two groups, the first (n = 131) followed a conventional protocol (CP), and the second (n = 131) an outpatient protocol (OP). The primary composite endpoint comprised MACCE (death, stroke, and bleeding), cardiac tamponade, vascular complication, or attendance in the emergency department after hospital discharge at 30 days. Results: The overall success rate was 99.6%, with a periprocedural complication rate of 2.29%. With regards to the CP versus OP group, there were no differences between incidences of the primary composite endpoint (6.1% PC vs. 3.0% PA, p = 0.24), or after an analysis, with propensity score matching. No differences were observed in the individual endpoints. There was a decrease in hospital length of stay in the same-day discharge group (p < 0.01). Conclusions: A same-day discharge LAAO program is safe, effective, and feasible when compared to the conventional strategy. Moreover, it reduces hospital length of stay, which might have clinical and economic benefits.

Cardiotoxicity due to anthracyclines (CDA) affects cancer patients, but we cannot predict who may suffer from this complication. CDA is a complex trait with a polygenic component that is mainly unidentified. We propose that levels of intermediate molecular phenotypes (IMPs) in the myocardium associated with histopathological damage could explain CDA susceptibility, so variants of genes encoding these IMPs could identify patients susceptible to this complication. Thus, a genetically heterogeneous cohort of mice (n = 165) generated by backcrossing were treated with doxorubicin and docetaxel. We quantified heart fibrosis using an Ariol slide scanner and intramyocardial levels of IMPs using multiplex bead arrays and QPCR. We identified quantitative trait loci linked to IMPs (ipQTLs) and cdaQTLs via linkage analysis. In three cancer patient cohorts, CDA was quantified using echocardiography or Cardiac Magnetic Resonance. CDA behaves as a complex trait in the mouse cohort. IMP levels in the myocardium were associated with CDA. ipQTLs integrated into genetic models with cdaQTLs account for more CDA phenotypic variation than that explained by cda-QTLs alone. Allelic forms of genes encoding IMPs associated with CDA in mice, including AKT1, MAPK14, MAPK8, STAT3, CAS3, and TP53, are genetic determinants of CDA in patients. Two genetic risk scores for pediatric patients (n = 71) and women with breast cancer (n = 420) were generated using machine-learning Least Absolute Shrinkage and Selection Operator (LASSO) regression. Thus, IMPs associated with heart damage identify genetic markers of CDA risk, thereby allowing more personalized patient management.

The use of advanced algorithms and models such as Machine Learning, Deep Learning and other related approaches of Artificial Intelligence have grown in their use given their benefits in different contexts. One of these contexts is the medical domain, as these algorithms can support disease detection, image segmentation and other multiple tasks. However, it is necessary to organize and arrange the different data resources involved in these scenarios and tackle the heterogeneity of data sources. This work presents the CARTIER-IA platform: a platform for the management of medical data and imaging. The goal of this project focuses on providing a friendly and usable interface to organize structured data, to visualize and edit medical images, and to apply Artificial Intelligence algorithms on the stored resources. One of the challenges of the platform design is to ease these complex tasks in a way that non-AI-specialized users could benefit from the application of AI algorithms without further training. Two use cases of AI application within the platform are provided, as well as a heuristic evaluation to assess the usability of the first version of CARTIER-IA.

Abstract Background ICD patients with episodes of nonsustained ventricular tachycardias (NSVT) are at risk of appropriate therapies. However, the relationship between the cycle length (CL) of such NSVTs and the subsequent incidence of appropriate interventions is unknown. Methods 416 ICD patients with LVEF 5 NSVTs (r = 0.97; p

Background: Determining the mechanism of supraventricular tachycardias with prolongedP ventriculoatrial (VA) intervals is sometimes a challenge. Our objective is to analyse the determinants, time course and diagnostic accuracy (atypical atrioventricular nodal reentrant tachycardias [AVNRT] versus orthodromic reentrant tachycardias through an accessory pathway [ORT]) of spontaneous VA intervals variation in patients with narrow QRS tachycardias and prolonged VA. Methods: A total of 156 induced tachycardias were studied (44 with atypical AVNRT and 112 with ORT). Two sets of 10 measurements were performed for each patient—after tachycardia induction and one minute later. VA and VV intervals were determined. Results: The difference between the longest and the shortest VA interval (Dif-VA) correlates significantly with the diagnosis of atypical AVNRT (C coefficient = 0.95 and 0.85 after induction and at one minute, respectively; p < 0.001). A Dif-VA ≥ 15 ms presents a sensitivity and specificity for atypical AVNRT of 50% and 99%, respectively after induction, and of 27% and 100% one minute later. We found a robust and significant correlation between the fluctuations of VV and VA intervals in atypical AVNRTs (Coefficient Rho: 0.56 and 0.76, after induction and at one minute, respectively; p < 0.001 for both) but not in ORTs. Conclusions: The analysis of VA interval variability after induction and one minute later correctly discriminates atypical AVNRT from ORT in almost all cases.

Ischemic heart disease (IHD) and type-2 diabetes mellitus (T2DM) remain major health problems worldwide and commonly coexist in individuals. Gut microbial metabolites, such as trimethylamine N-oxide (TMAO) and short-chain fatty acids (SCFAs), have been linked to cardiovascular and metabolic diseases. Previous studies have reported dysbiosis in the gut microbiota of these patients and the prebiotic effects of some components of the Mediterranean diet. Essential oil emulsions of savory (Satureja hortensis), parsley (Petroselinum crispum) and rosemary (Rosmarinus officinalis) were assessed as nutraceuticals and prebiotics in IHD and T2DM. Humanized mice harboring gut microbiota derived from that of patients with IHD and T2DM were supplemented with L-carnitine and orally treated with essential oil emulsions for 40 days. We assessed the effects on gut microbiota composition and abundance, microbial metabolites and plasma markers of cardiovascular disease, inflammation and oxidative stress. Our results showed that essential oil emulsions in mice supplemented with L-carnitine have prebiotic effects on beneficial commensal bacteria, mainly Lactobacillus genus. There was a decrease in plasma TMAO and an increase in fecal SCFAs levels in mice treated with parsley and rosemary essential oils. Thrombomodulin levels were increased in mice treated with savory and parsley essential oils. While mice treated with parsley and rosemary essential oils showed a decrease in plasma cytokines (INFɣ, TNFα, IL-12p70 and IL-22); savory essential oil was associated with increased levels of chemokines (CXCL1, CCL2 and CCL11). Finally, there was a decrease in protein carbonyls and pentosidine according to the essential oil emulsion. These results suggest that changes in the gut microbiota induced by essential oils of parsley, savory and rosemary as prebiotics could differentially regulate cardiovascular and metabolic factors, which highlights the potential of these nutraceuticals for reducing IHD risk in patients affected by T2DM.

Background: Paravalvular leak occurs in 5–17% of patients following surgical valve replacement, more often in mitral position. The prognosis without treatment is poor. Percutaneous device closure represents an alternative to repeat surgery. The objective of this work is to evaluate the medium and long-term results in the percutaneous closure of PVL in mitral prosthesis. Methods: This observational study is based on a retrospective registry including consecutive mitral PVL cases undergoing percutaneous closure at a single tertiary-care center from April 2010 to December 2020. The safety and efficacy results of the procedure, at 90 days and in the long term, were analyzed. Also, predictors of procedure failure and long-term events were identified. Results: A total of 128 consecutive mitral paravalvular leak closure procedures were included. Technical success was achieved in 115 (89.8%) procedures. The presence of multiple PVLs was the sole factor that independently predicted procedural failure. Median follow-up of our sample was 41.8 months (mean 47.7 ± 35.7 months). Underlying hemolytic anemia as the indication for PVL closure, a recent admission for decompensated HF, and lack of improvement in functional class emerged as consistent predictors of MACE and death during long-term follow-up, while lack of procedural success during the first PVL procedure and chronic kidney disease were also associated with MACE during follow-up. Conclusions: Percutaneous mitral PVL closure displayed high technical and procedural success rates, with an acceptable safety profile, in a high-risk population. Percutaneous mitral PVL closure achieved an improvement in short- and long-term functional class and a reduction of hemolysis in the vast majority of patients. In addition, long-term survival in our study was good, in particular for patients undergoing successful PVL closure procedures.

Background: The integrated approach to electrical cardioversion (EC) in atrial fibrillation (AF) is complex; candidates can resolve spontaneously while waiting for EC, and post-cardioversion recurrence is high. Thus, it is especially interesting to avoid the programming of EC in patients who would restore sinus rhythm (SR) spontaneously or present early recurrence. We have analyzed the whole elective EC of the AF process using machine-learning (ML) in order to enable a more realistic and detailed simulation of the patient flow for decision making purposes. Methods: The dataset consisted of electronic health records (EHRs) from 429 consecutive AF patients referred for EC. For analysis of the patient outcome, we considered five pathways according to restoring and maintaining SR: (i) spontaneous SR restoration, (ii) pharmacologic-cardioversion, (iii) direct-current cardioversion, (iv) 6-month AF recurrence, and (v) 6-month rhythm control. We applied ML classifiers for predicting outcomes at each pathway and compared them with the CHA2DS2-VASc and HATCH scores. Results: With the exception of pathway (iii), all ML models achieved improvements in comparison with CHA2DS2-VASc or HATCH scores (p < 0.01). Compared to the most competitive score, the area under the ROC curve (AUC-ROC) was: 0.80 vs. 0.66 for predicting (i); 0.71 vs. 0.55 for (ii); 0.64 vs. 0.52 for (iv); and 0.66 vs. 0.51 for (v). For a threshold considered optimal, the empirical net reclassification index was: +7.8%, +47.2%, +28.2%, and +34.3% in favor of our ML models for predicting outcomes for pathways (i), (ii), (iv), and (v), respectively. As an example tool of generalizability of ML models, we deployed our algorithms in an open-source calculator, where the model would personalize predictions. Conclusions: An ML model improves the accuracy of restoring and maintaining SR predictions over current discriminators. The proposed approach enables a detailed simulation of the patient flow through personalized predictions.

Background The determinants and consequences of pulmonary hypertension after successfully corrected valvular heart disease remain poorly understood. We aim to clarify the hemodynamic bases and risk factors for mortality in patients with this condition. Methods and Results We analyzed long‐term follow‐up data of 222 patients with pulmonary hypertension and valvular heart disease successfully corrected at least 1 year before enrollment who had undergone comprehensive hemodynamic and imaging characterization as per the SIOVAC (Sildenafil for Improving Outcomes After Valvular Correction) clinical trial. Median (interquartile range) mean pulmonary pressure was 37 mm Hg (32–44 mm Hg) and pulmonary artery wedge pressure was 23 mm Hg (18–26 mm Hg). Most patients were classified either as having combined precapillary and postcapillary or isolated postcapillary pulmonary hypertension. After a median follow‐up of 4.5 years, 91 deaths accounted for 4.21 higher‐than‐expected mortality in the age‐matched population. Risk factors for mortality were male sex, older age, diabetes mellitus, World Health Organization functional class III and higher pulmonary vascular resistance—either measured by catheterization or approximated from ultrasound data. Higher pulmonary vascular resistance was related to diabetes mellitus and smaller residual aortic and mitral valve areas. In turn, the latter correlated with prosthetic nominal size. Six‐month changes in the composite clinical score and in the 6‐minute walk test distance were related to survival. Conclusions Persistent valvular heart disease–pulmonary hypertension is an ominous disease that is almost universally associated with elevated pulmonary artery wedge pressure. Pulmonary vascular resistance is a major determinant of mortality in this condition and is related to diabetes mellitus and the residual effective area of the corrected valve. These findings have important implications for individualizing valve correction procedures. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT00862043.

Background: Right ventricular (RV) to pulmonary circulation (PC) coupling can stratify prognosis in heart failure (HF). In this study, we assessed the prognostic role of the mean velocity of the pulmonary artery (mvPA) determined by cardiac magnetic resonance (CMR) in HF with preserved ejection fraction (HFpEF). Methods: Inclusion of 58 HFpEF outpatients that underwent CMR with measurement of RV–PC coupling parameters including mvPA between 2016 and 2019. The primary combined endpoint was a composite of HF readmissions and all-cause mortality. Results: Optimal cut-off value of mvPA calculated by receiver operating curve for the prediction of the primary endpoint was 9 cm/s. Over a median follow-up of 23 months (interquartile range: 24), 21 patients met the primary endpoint. The primary endpoint was more frequent in patients with mvPA ≤ 9 cm/s, as indicated by Kaplan–Meier survival curves; Log-Rank: 9.193, p = 0.02, regardless of RV dysfunction. On Cox multivariate analysis, mvPA ≤ 9 cm/s emerged as an independent prognostic predictor of the primary endpoint (HR: 4.11, 95% CI: 1.28–13.19, p = 0.017), together with left atrial area by CMR (HR: 1.08, 95% CI: 1.01–1.24, p = 0.034). Conclusions: In our HFpEF cohort, mvPA was associated with a higher rate of the primary endpoint, regardless of RV function, thus enabling identification of patients at higher risk of cardiovascular events before structural damage onset.

Fundamentos: Con frecuencia encontramos deficiencias en el manejo de los factores de riesgo en las personas hipertensas. El objetivo del estudio fue evaluar el efecto de una intervención de mejora de calidad en la atención a los factores de riesgo cardiovascular en personas hipertensas. Métodos: Estudio de mejora de calidad. Dos centros de salud y catorce médicos de familia. Un centro (siete médicos) se seleccionó para recibir una intervención de mejora de calidad y otro como grupo control. Se incluyó a 482 personas hipertensas en el grupo de estudio [64% mujeres, edad media 61,4 años (DS:6.8)] y 360 en el grupo control (63% mujeres, edad media 60,7 (DS:7.4)). La intervención consistió en una auditoria de historias clínicas con feedback, sesiones de entrenamiento y discusión de guías clínicas. Previamente a la intervención y un año después de la misma se evaluaron criterios de proceso de atención a personas hipertensas, presión arterial, peso, lípidos, tabaco, riesgo cardiovascular y fármacos antihipertensivos. Resultados: La mejora media en el proceso después de la intervención fue de 5,3 puntos porcentuales (CI95%:3,7-6,9). La presión arterial sistólica descendió 3,5 mmHg (IC95%:1,6-5,3) y la presión arterial diastólica 2,5 mmHg (IC95%:1,3-3,8). El control adecuado de la presión arterial se incrementó en el grupo de intervención (29,1% a 40,9%; p

Hasta hace poco tiempo se pensaba que el miocardio era un tejido sin capacidad de regeneración. El descubrimiento de progenitores celulares en el corazón de mamíferos adultos y la evidencia científica de que la reparación cardíaca existe han cambiado esta creencia, abriendo una nueva vía de investigación en el tratamiento de las enfermedades cardiovasculares. Durante años, circunscrita al ámbito de la investigación básica y de los ensayos preclínicos, esta nueva línea de investigación se ha trasladado al ámbito clínico, donde se están desarrollando ensayos en humanos para evaluar la seguridad, factibilidad y eficacia de dicha terapia celular en la regeneración miocárdica. En esta revisión nos centraremos en la terapia celular de la insuficiencia cardíaca crónica en humanos, recogiendo los antecedentes, tipos de células y vías de administración, así como los principales ensayos clínicos publicados hasta el momento.

After more than ten years of human research in the field of cardiac regenerative medicine, application of stem cells in different phases of ischemic heart disease has come to age. Randomized clinical trials have demonstrated that stem cell therapy can improve cardiac recovery after the acute phase of myocardial ischemia and in patients with chronic ischemic heart disease, and several efficacy phase III trials with clinical endpoints are on their way. Nevertheless, a complete knowledge on the mechanisms of action of stem cells still remains elusive. Of the three main mechanisms by which stem cells could exert their benefit, paracrine signaling from the administered cells and stimulation of endogenous repair are nowadays the most plausible ones. However, in this review we will define and discuss the concept of stem cell potency and differentiation, will examine the evidence available, and will depict future directions of research.

First randomized clinical trials have demonstrated that stem cell therapy can improve cardiac recovery after the acute phase of myocardial ischemia and in patients with chronic ischemic heart disease. Nevertheless, some trials have shown that conflicting results and uncertainties remain in the case of mechanisms of action and possible ways to improve clinical impact of stem cells in cardiac repair. In this paper we will examine the evidence available, analyze the main phase I and II randomized clinical trials and their limitations, discuss the key points in the design of future trials, and depict new directions of research in this fascinating field.

Over the past decade, cell therapy has emerged as a new approach to reversing myocardial ischemia. Several types of adult stem cells have been studied in both preclinical and clinical conditions for this purpose: bone marrow cells, circulating cells, and myoblasts. Nevertheless, the quest for the ideal “anti-ischemic” cell is still ongoing. Recently, the existence of a population of stem cells located in adipose tissue (adipose-derived stem cells) has been observed. These are able to differentiate into multiple cell lineages including cardiomyocytic differentiation. In this review we discuss the basic principles of adipose-derived stem cells (types and characteristics, harvesting, and expansion), the initial experimental studies, and the currently ongoing clinical trials.