Multivariate ensemble classification for the prediction of symptoms in patients with Brugada syndrome.

Identification of asymptomatic patients at higher risk for suffering cardiac events remains controversial and challenging in Brugada syndrome (BS). In this work, we proposed an ECG-based classifier to predict BS-related symptoms, by merging the most predictive electrophysiological features derived from the ventricular depolarization and repolarization periods, along with autonomic-related markers. The initial feature space included local and dynamic ECG markers, assessed during a physical exercise test performed in 110 BS patients (25 symptomatic). Morphological, temporal and spatial properties quantifying the ECG dynamic response to exercise and recovery were considered. Our model was obtained by proposing a two-stage feature selection process that combined a resampled-based regularization approach with a wrapper model assessment for balancing, simplicity and performance. For the classification step, an ensemble was constructed by several logistic regression base classifiers, whose outputs were fused using a performance-based weighted average. The most relevant predictors corresponded to the repolarization interval, followed by two autonomic markers and two other makers of depolarization dynamics. Our classifier allowed for the identification of novel symptom-related markers from autonomic and dynamic ECG responses during exercise testing, suggesting the need for multifactorial risk stratification approaches in order to predict future cardiac events in asymptomatic BS patients. Graphical abstract Pipeline for feature selection and predictive modeling of symptoms in Brugada syndrome.

Health Outcomes from Home Hospitalization: Multisource Predictive Modeling.

BACKGROUND: Home hospitalization is widely accepted as a cost-effective alternative to conventional hospitalization for selected patients. A recent analysis of the home hospitalization and early discharge (HH/ED) program at Hospital Clínic de Barcelona over a 10-year period demonstrated high levels of acceptance by patients and professionals, as well as health value-based generation at the provider and health-system levels. However, health risk assessment was identified as an unmet need with the potential to enhance clinical decision making. OBJECTIVE: The objective of this study is to generate and assess predictive models of mortality and in-hospital admission at entry and at HH/ED discharge. METHODS: Predictive modeling of mortality and in-hospital admission was done in 2 different scenarios: at entry into the HH/ED program and at discharge, from January 2009 to December 2015. Multisource predictive variables, including standard clinical data, patients' functional features, and population health risk assessment, were considered. RESULTS: We studied 1925 HH/ED patients by applying a random forest classifier, as it showed the best performance. Average results of the area under the receiver operating characteristic curve (AUROC; sensitivity/specificity) for the prediction of mortality were 0.88 (0.81/0.76) and 0.89 (0.81/0.81) at entry and at home hospitalization discharge, respectively; the AUROC (sensitivity/specificity) values for in-hospital admission were 0.71 (0.67/0.64) and 0.70 (0.71/0.61) at entry and at home hospitalization discharge, respectively. CONCLUSIONS: The results showed potential for feeding clinical decision support systems aimed at supporting health professionals for inclusion of candidates into the HH/ED program, and have the capacity to guide transitions toward community-based care at HH discharge.

Class Imbalance Impact on the Prediction of Complications during Home Hospitalization: A Comparative Study.

Home hospitalization (HH) is presented as a healthcare alternative capable of providing high standards of care when patients no longer need hospital facilities. Although HH seems to lower healthcare costs by shortening hospital stays and improving patient's quality of life, the lack of continuous observation at home may lead to complications in some patients. Since blood tests have been proven to provide relevant prognosis information in many diseases, this paper analyzes the impact of different sampling methods on the prediction of HH outcomes. After a first exploratory analysis, some variables extracted from routine blood tests performed at the moment of HH admission, such as hemoglobin, lymphocytes or creatinine, were found to unmask statistically significant differences between patients undergoing successful and unsucessful HH stays. Then, predictive models were built with these data, in order to identify unsuccessful cases eventually needing hospital facilities. However, since these hospital admissions during HH programs are rare, their identification through conventional machine-learning approaches is challenging. Thus, several sampling strategies designed to face class imbalance were herein overviewed and compared. Among the analyzed approaches, over-sampling strategies, such as ROSE (Random Over-Sampling Examples) and conventional random over-sampling, showed the best performances. Nevertheless, further improvements should be proposed in the future so as to better identify those patients not benefiting from HH.

Recursive model identification for the analysis of the autonomic response to exercise testing in Brugada syndrome.

This paper proposes the integration and analysis of a closed-loop model of the baroreflex and cardiovascular systems, focused on a time-varying estimation of the autonomic modulation of heart rate in Brugada syndrome (BS), during exercise and subsequent recovery. Patient-specific models of 44 BS patients at different levels of risk (symptomatic and asymptomatic) were identified through a recursive evolutionary algorithm. After parameter identification, a close match between experimental and simulated signals (mean error = 0.81%) was observed. The model-based estimation of vagal and sympathetic contributions were consistent with physiological knowledge, enabling to observe the expected autonomic changes induced by exercise testing. In particular, symptomatic patients presented a significantly higher parasympathetic activity during exercise, and an autonomic imbalance was observed in these patients at peak effort and during post-exercise recovery. A higher vagal modulation during exercise, as well as an increasing parasympathetic activity at peak effort and a decreasing vagal contribution during post-exercise recovery could be related with symptoms and, thus, with a worse prognosis in BS. This work proposes the first evaluation of the sympathetic and parasympathetic responses to exercise testing in patients suffering from BS, through the recursive identification of computational models; highlighting important trends of clinical relevance that provide new insights into the underlying autonomic mechanisms regulating the cardiovascular system in BS. The joint analysis of the extracted autonomic parameters and classic electrophysiological markers could improve BS risk stratification.

Global Sensitivity Analysis of a Cardiovascular Model for the Study of the Autonomic Response to Head-up Tilt Testing.

This paper proposes the integration and analysis of a mathematical model representing the cardiovascular system and its short-term autonomic response to head-up tilt (HUT) testing. A Latin Hypercube Sampling method was applied to design an optimal experimental space, including 19 model parameters coming from the cardiovascular and baroreflex control systems. Then, a global, variance-based sensitivity analysis was applied to quantity the effects of these parameters on heart rate and systolic blood pressure. Results highlight the relevant influence of the intrinsic heart rate and the sympathetic and parasympathetic baroreflex gains on heart rate regulation, as well as the impact of left ventricle diastolic parameters on systolic blood pressure. Moreover, a significant effect of right ventricle dynamics on blood pressure was noted. These results provide valuable information for the application of such an integrated model for the analysis of the autonomic mechanisms regulating the cardiovascular response induced by postural changes. In particular, they suggest a convenient set of parameters to be identified in a subject-specific manner.

Model-based analysis of the autonomic response to head-up tilt testing in Brugada syndrome.

The etiology of Brugada syndrome (BS) is complex and multifactorial, making risk stratification in this population a major challenge. Since changes in the autonomic modulation of these patients are commonly related to arrhythmic events, we analyze in this work whether the response to head-up tilt (HUT) testing on this population may provide useful, complementary information for risk stratification. In order to perform this analysis, a coupled physiological model integrating the cardiac electrical activity, the cardiovascular system and the baroreceptors reflex control of the autonomic function, in response to HUT is proposed. A sensitivity analysis was performed, based on a screening method, evidencing the influence of cardiovascular parameters on blood pressure and of baroreflex regulation on heart rate. The most sensitive parameters have been identified on a set of 20 subjects (8 controls and 12 BS patients), so as to assess subject-specific model parameters. According to the results, controls showed an increased sympathetic modulation after tilting, as well as a reduced left ventricular contractility was observed in symptomatic, with respect to asymptomatic BS patients. These results provide new insights regarding the autonomic mechanisms regulating the cardiovascular system in BS which might be used as a complementary source of information, along with classical electrophysiological parameters, for BS risk stratification.

Sex Differences in Autonomic Response to Exercise Testing in Patients with Brugada Syndrome.

INTRODUCTION: Cardiac events in patients with Brugada syndrome (BS) typically occur at rest and mainly during sleep, suggesting that changes in autonomic modulation play an important role in the arrhythmogenesis of the disease. Moreover, sex differences in clinical manifestations of BS have been reported, identifying male patients with worse prognosis. The aim of our work was to assess and compare, according to sex, autonomic response to exercise in a clinical series including 105 BS patients. METHOD: Standard 12-lead electrocardiogram recordings were collected during a physical stress test divided into four phases: warm-up, incremental exercise, active recovery, and passive recovery. Spectral non-stationary heart rate variability indicators were extracted by means of a smoothed pseudo Wigner-Ville distribution approach that adapts frequency bands to respiratory information. These indicators were then averaged in non-overlapped windows of 1 min for each patient to compare groups at each minute of the physical stress test. RESULTS: From the last minute of warm-up and until the third minute of incremental exercise, asymptomatic male patients presented significantly greater low-frequency (LF) values ([Formula: see text]: p = 0.015;[Formula: see text]: p = 0.024; [Formula: see text]: p = 0.011; [Formula: see text]: p = 0.002) than asymptomatic females. Conversely, asymptomatic women showed increased vagal modulation during the first minutes of incremental exercise ([Formula: see text]: p = 0.031; [Formula: see text]: p = 0.001). However, no significant differences were observed between symptomatic male and female patients. CONCLUSION: As previously reported in healthy subjects, enhanced parasympathetic and decreased sympathetic tones appear to be not only greater in women but also defensive during cardiac stress. Based on the results, asymptomatic patients presented same-sex tendencies. However, we observed that symptomatic males developed a more female-like autonomic modulation, probably related to a more protective autonomic response to exercise. These results could be a step forward toward the understanding of the autonomic function in BS along with a potential impact on risk stratification.

Multivariate classification of Brugada syndrome patients based on autonomic response to exercise testing.

Ventricular arrhythmias in Brugada syndrome (BS) typically occur at rest and especially during sleep, suggesting that changes in the autonomic modulation may play an important role in arrhythmogenesis. The autonomic response to exercise and subsequent recovery was evaluated on 105 patients diagnosed with BS (twenty-four were symptomatic), by means of a time-frequency heart rate variability (HRV) analysis, so as to propose a novel predictive model capable of distinguishing symptomatic and asymptomatic BS populations. During incremental exercise, symptomatic patients showed higher HFnu values, probably related to an increased parasympathetic modulation, with respect to asymptomatic subjects. In addition, those extracted HRV features best distinguishing between populations were selected using a two-step feature selection approach, so as to build a linear discriminant analysis (LDA) classifier. The final features subset included one third of the total amount of extracted autonomic markers, mostly acquired during incremental exercise and active recovery, thus evidencing the relevance of these test segments in BS patients classification. The derived predictive model showed an improved performance with respect to previous works in the field (AUC = 0.92 ± 0.01; Se = 0.91 ± 0.06; Sp = 0.90 ± 0.05). Therefore, based on these findings, some of the analyzed HRV markers and the proposed model could be useful for risk stratification in Brugada syndrome.

Aplicación del proceso enfermero en gestante hemodializada / Evaluation of complications of arteriovenous fistula for hemodialysis according to the puncture technique

La frecuencia de las gestaciones en mujeres en tratamiento con hemodiálisis está incrementándose en los últimos años. El aumento de fertilidad en estas pacientes se debe a la mejora de la eficacia de la diálisis, junto con el manejo clínico de la insuficiencia renal. Sin embargo, el embarazo de las pacientes hemodializadas sigue siendo un reto, debido a frecuentes complicaciones como la preeclampsia, la prematuridad severa, el polihidramnios, etc. Actualmente, se constata el ascenso de la tasa de supervivencia fetal y la disminución de la morbi-mortalidad materno-fetal. Presentamos el caso de una gestante en tratamiento con hemodiálisis que presenta una amenaza de parto prematuro a la 27+2 semanas de gestación. Se han formulado diagnósticos enfermeros siguiendo la taxonomía NANDA-NOC-NIC, con la finalidad de visibilizar la necesidad de un adecuado plan de cuidados en estas pacientes (AU)

The frequency of pregnancies in women being treated with hemodialys is increasing in recent years. Increasing fertility in these patients is due to improving the efficiency of dialysis, along with the clinical management of renal failure. However, pregnancy in these patients remains a challenge, due to frequent complication ssuch as preeclampsia, severe prematurity, polyhydramnios, etc. Currently, there is an aument of fetal survival and reduced maternal and fetal morbidity and mortality. This case is about pregnancy in hemodyalisis treatment with threat of premature birth in 27+2 weeks. Nursing diagnoses have been made following the NANDA -NOC -NIC taxonomy, in order to visualize the need for an adequate care plan in these patients (AU)

Left Atrial Geometry Improves Risk Prediction of Thromboembolic Events in Patients With Atrial Fibrillation.

BACKGROUND: Left atrial (LA) sphericity (LASP) is a new remodeling parameter based on LA shape analysis, with independent predictive value for recurrence after atrial fibrillation (AF) ablation. OBJECTIVES: To evaluate the association between LASP and thromboembolic events (TE) in patients with AF. METHODS: Twenty-nine AF patients and prior TE and 29 age- and gender-matched controls were included. LASP was calculated using a 3D-LA reconstruction. The LA appendage (LAA) volume and morphology were assessed. ROC curve analysis was performed for LASP, LA volume, LAA volume, and CHAD/CHA2 D-VASc scores (Stroke2 -the grouping variable-was excluded). RESULTS: Mean age of the study population was 61 ± 11 years (79.3% males, 53.4% hypertension, 8.6% diabetes). Patients with prior TE had higher LASP than those without (82.5 ± 3.3% vs. 80.2 ± 3.1%, P = 0.008); there were no differences in CHAD or CHA2 D-VASc scores, LA volume, LAA volume, or LAA morphology. The C-statistic was higher for LASP (0.71) than for other tested variables (CHAD score = 0.58, CHA2 D-VASc score = 0.59, LA volume = 0.50, LAA volume = 0.46; P < 0.01 for all vs. LASP). The best cutoff value for LASP was 83.6% (sensitivity 0.52, specificity 0.90). Logistic regression analysis showed predictive value for LASP (OR 1.26 per each 1% increase [1.85-52.20], P = 0.013), but not for clinical risk scores. The addition of LASP to the CHAD and CHA2 D-VASc scores increased the predictive value over the risk scores alone (P = 0.004), and reclassified 45.5% of patients with CHAD = 0 (no anticoagulation indicated) to moderate-risk (anticoagulation indicated). CONCLUSION: LA sphericity is associated with prior TE in AF patients and improves the performance of the CHAD and CHA2 D-VASc scores alone.

Contact force threshold for permanent lesion formation in atrial fibrillation ablation: A cardiac magnetic resonance-based study to detect ablation gaps.

BACKGROUND: Catheter contact force (CF) has a strong correlation with lesion formation during radiofrequency ablation. Delayed-enhancement cardiac magnetic resonance (DE-CMR) provides lesion information in patients with prior atrial fibrillation (AF) ablation. OBJECTIVE: The aim of this study was to determine the CF threshold to create permanent lesions detected by DE-CMR. METHODS: A total of 36 patients referred for AF ablation were included. A CF catheter was used during the ablation procedure, and DE-CMR was performed 3 months after the ablation procedure. Eighteen pulmonary vein (PV) segments were defined, and 3-dimensional (3D) reconstructions of the left atrium (LA) derived from the DE-CMR images were obtained. One observer evaluated the presence of any discontinuity of previous ablation lesions (gap) in the 3D reconstructions of the LA, and another observer (blinded to the gap findings) determined the minimum CF value in each PV segment. RESULTS: The PV segments where a gap was observed had a lower maximal CF value than did the segments without gap in the 3D LA reconstructions (6.7 ± 4.4 g vs 12.2 ± 4.7 g; P < .001). In receiver operating characteristic analysis, a CF threshold of >8 g provided 73% sensitivity and 81% specificity in the prediction of a complete PV lesion (positive predictive value [PPV] 84%). A CF threshold of >12 g had a specificity of 94% and increased the PPV to 91% in creating a complete lesion in the LA wall (area under the curve 0.834). CONCLUSION: A CF threshold of >12 g H5H20 predicts a complete lesion with high specificity and PPV when a dragging ablation strategy is used in AF ablation.

Analysis of a cardiovascular model for the study of the autonomic response of Brugada syndrome patients.

This paper describes the integration of mathematical models of the cardiac electrical activity, the cardiovascular system and the baroreceptor reflex control of the autonomic nervous system, with a model representing a head-up tilt test. Sensitivity analyses are performed in order to determine those model parameters producing the greatest significant effects on heart rate and blood pressure. An optimization step is then applied to the most influential parameters in order to find the best model fit to real cardiac data obtained from a patient suffering from Brugada syndrome and a healthy subject, in supine and upright postures during a tilt test. Results show the feasibility of the model to generate realistic autonomic responses to head-up tilt testing in health and disease.

Left atrial tachycardia after atrial fibrillation ablation: can magnetic resonance imaging assist the ablation?

We present a case of a magnetic resonance imaging-assisted ablation of an atrial tachycardia in a patient with previous atrial fibrillation ablation. A 3-D reconstruction of the delayed-enhanced cardiac magnetic resonance (CMR; CMR model) was created to identify previous ablation lesions and gaps. Multiple gaps around right-sided pulmonary veins were observed. The activation map identified a dual-loop re-entry around both right-sided pulmonary veins, confirming that the substrate identified using delayed-enhanced CMR was critical to sustain the tachycardia. Ablation at this site converted to sinus rhythm. The present case shows the usefulness of delayed-enhanced CMR substrate characterization to complement activation mapping of the tachycardia and more accurately define the anatomical circuit.

A wavelet-based electrogram onset delineator for automatic ventricular activation mapping.

Electroanatomical mapping (EAM) systems are commonly used in clinical practice for guiding catheter ablation treatments of common arrhythmias. In focal tachycardias, the ablation target is defined by locating the earliest activation area determined by the joint analysis of electrogram (EGM) signals at different sites. However, this is currently a manual time-consuming and experience-dependent task performed during the intervention and thus prone to stress-related errors. In this paper, we present an automatic delineation strategy that combines electrocardiogram (ECG) information with the wavelet decomposition of the EGM signal envelope to identify the onset of each EGM signal for activation mapping. Fourteen electroanatomical maps corresponding to ten patients suffering from non-tolerated premature ventricular contraction (PVC) beats and admitted for ablation procedure were used for evaluation. We compared the results obtained automatically with two types of manual annotations: one during the intervention by an expert technician (on-procedure) and other after the intervention (off-procedure), free from time and procedural constraints, by two other technicians. The automatic annotations show a significant correlation (0.95, p 0.01) with the evaluation reference (off-procedure annotation sets combination) and has an error of 2.1 ± 10.9 ms, around the order of magnitude of the on-procedure annotations error ( - 2.6 ± 6.8 ms). The results suggest that the proposed methodology could be incorporated into EAM systems to considerably reduce processing time during ablation interventions.

Automatic assessment of socioeconomic impact on cardiac rehabilitation.

Disability-Adjusted Life Years (DALYs) and Quality-Adjusted Life Years (QALYs), which capture life expectancy and quality of the remaining life-years, are applied in a new method to measure socioeconomic impacts related to health. A 7-step methodology estimating the impact of health interventions based on DALYs, QALYs and functioning changes is presented. It relates the latter (1) to the EQ-5D-5L questionnaire (2) to automatically calculate the health status before and after the intervention (3). This change of status is represented as a change in quality of life when calculating QALYs gained due to the intervention (4). In order to make an economic assessment, QALYs gained are converted to DALYs averted (5). Then, by inferring the cost/DALY from the cost associated to the disability in terms of DALYs lost (6) and taking into account the cost of the action, cost savings due to the intervention are calculated (7) as an objective measure of socioeconomic impact. The methodology is implemented in Java. Cases within the framework of cardiac rehabilitation processes are analyzed and the calculations are based on 200 patients who underwent different cardiac-rehabilitation processes. Results show that these interventions result, on average, in a gain in QALYs of 0.6 and a cost savings of 8,000 €.