Usefulness of the heart-rate variability complex for predicting cardiac mortality after acute myocardial infarction

Guideline for the application of heart rate and heart rate variability in occupational medicine and occupational health science

This updated guideline replaces the "Guideline for the application of heart rate and heart rate variability in occupational medicine and occupational health science" first published in 2014. Based on the older version of the guideline, the authors have reviewed and evaluated the findings on the use of heart rate (HR) and heart rate variability (HRV) that have been published in the meantime and incorporated them into a new version of this guideline.This guideline was developed for application in clinical practice and research purposes in the fields of occupational medicine and occupational science to complement evaluation procedures with respect to exposure and risk assessment at the workplace by the use of objective physiological workload indicators. In addition, HRV is also suitable for assessing the state of health and for monitoring the progress of illnesses and preventive medical measures. It gives an overview of factors influencing the regulation of the HR and HRV at rest and during work. It further illustrates methods for measuring and analyzing these parameters under standardized laboratory and real workload conditions, areas of application as well as the quality control procedures to be followed during the recording and evaluation of HR and HRV.

Which indices of heart rate variability are the best predictors of mortality after acute myocardial infarction? Meta-analysis of observational studies

BACKGROUND

Cardiovascular disease is the first cause of death globally with myocardial infarction as the main event. Heart rate variability (HRV) has been associated with an increased risk of mortality post-myocardial infarction. However, which indices of heart rate variability are the best predictors for total and cardiac mortality post-myocardial infarction remains unclear. We performed a systematic review to evaluate this association.

METHODS AND RESULTS

PubMed, Google Scholar, Embase and Cochrane databases were searched for studies with HRV as a predictive mortality marker. Two authors independently selected papers and extracted data and disagreements were solved with a third author. HRV indices included were SDNN, SDANN, HRV index, Total power, RMSSD, LF, HF, ULF, VLF, and LF/HF. For these clinical and statistical heterogeneity was assessed, forest and funnel plot graphs were made and sensitivity analysis, cumulative and regression meta-analysis were performed. Stata 16 was used for statistical analysis. Out of 19.960 articles found, 332 were initially selected for abstract screening and 27 finally fulfilled the criteria and allowed the extraction of data. After a sensitivity analysis, low values of SDNN, HRV index, ULF, VLF, Total Power, LF, LF/HF ratio and HF showed a statistically significant association with cardiac mortality, but SDNN index had the highest association (RR 4.19, CI95% 3.36-5.22, I2 39.7%). For total mortality, HRV index, VLF, ULF, LF, Total power, SDNNN, LF/HF ratio, HF were significantly associated, but HRV index was the index with highest association, (RR 3.60, CI95% 2.30-5.64, I2 27.5%).

CONCLUSIONS

Based on a sensitivity analysis, the best index associated with cardiac mortality post-myocardial infarction is low values of SDNN and for total mortality is low values of HRV index.

Smart Wearables for the Detection of Occupational Physical Fatigue: A Literature Review

Today's world is changing dramatically due to the influence of various factors. Whether due to the rapid development of technological tools, advances in telecommunication methods, global economic and social events, or other reasons, almost everything is changing. As a result, the concepts of a "job" or work have changed as well, with new work shifts being introduced and the office no longer being the only place where work is done. In addition, our non-stop active society has increased the stress and pressure at work, causing fatigue to spread worldwide and becoming a global problem. Moreover, it is medically proven that persistent fatigue is a cause of serious diseases and health problems. Therefore, monitoring and detecting fatigue in the workplace is essential to improve worker safety in the long term. In this paper, we provide an overview of the use of smart wearable devices to monitor and detect occupational physical fatigue. In addition, we present and discuss the challenges that hinder this field and highlight what can be done to advance the use of smart wearables in workplace fatigue detection.

Brain entropy, fractal dimensions and predictability: A review of complexity measures for EEG in healthy and neuropsychiatric populations

There has been an increasing trend towards the use of complexity analysis in quantifying neural activity measured by electroencephalography (EEG) signals. On top of revealing complex neuronal processes of the brain that may not be possible with linear approaches, EEG complexity measures have also demonstrated their potential as biomarkers of psychopathology such as depression and schizophrenia. Unfortunately, the opacity of algorithms and descriptions originating from mathematical concepts have made it difficult to understand what complexity is and how to draw consistent conclusions when applied within psychology and neuropsychiatry research. In this review, we provide an overview and entry-level explanation of existing EEG complexity measures, which can be broadly categorized as measures of predictability and regularity. We then synthesize complexity findings across different areas of psychological science, namely, in consciousness research, mood and anxiety disorders, schizophrenia, neurodevelopmental and neurodegenerative disorders, as well as changes across the lifespan, while addressing some theoretical and methodological issues underlying the discrepancies in the data. Finally, we present important considerations when choosing and interpreting these metrics.

Accuracy Assessment of Oura Ring Nocturnal Heart Rate and Heart Rate Variability in Comparison With Electrocardiography in Time and Frequency Domains: Comprehensive Analysis

Background

Photoplethysmography is a noninvasive and low-cost method to remotely and continuously track vital signs. The Oura Ring is a compact photoplethysmography-based smart ring, which has recently drawn attention to remote health monitoring and wellness applications. The ring is used to acquire nocturnal heart rate (HR) and HR variability (HRV) parameters ubiquitously. However, these parameters are highly susceptible to motion artifacts and environmental noise. Therefore, a validity assessment of the parameters is required in everyday settings.

Objective

This study aims to evaluate the accuracy of HR and time domain and frequency domain HRV parameters collected by the Oura Ring against a medical grade chest electrocardiogram monitor.

Methods

We conducted overnight home-based monitoring using an Oura Ring and a Shimmer3 electrocardiogram device. The nocturnal HR and HRV parameters of 35 healthy individuals were collected and assessed. We evaluated the parameters within 2 tests, that is, values collected from 5-minute recordings (ie, short-term HRV analysis) and the average values per night sleep. A linear regression method, the Pearson correlation coefficient, and the Bland–Altman plot were used to compare the measurements of the 2 devices.

Results

Our findings showed low mean biases of the HR and HRV parameters collected by the Oura Ring in both the 5-minute and average-per-night tests. In the 5-minute test, the error variances of the parameters were different. The parameters provided by the Oura Ring dashboard (ie, HR and root mean square of successive differences [RMSSD]) showed relatively low error variance compared with the HRV parameters extracted from the normal interbeat interval signals. The Pearson correlation coefficient tests (P<.001) indicated that HR, RMSSD, average of normal heart beat intervals (AVNN), and percentage of successive normal beat-to-beat intervals that differ by more than 50 ms (pNN50) had high positive correlations with the baseline values; SD of normal beat-to-beat intervals (SDNN) and high frequency (HF) had moderate positive correlations, and low frequency (LF) and LF:HF ratio had low positive correlations. The HR, RMSSD, AVNN, and pNN50 had narrow 95% CIs; however, SDNN, LF, HF, and LF:HF ratio had relatively wider 95% CIs. In contrast, the average-per-night test showed that the HR, RMSSD, SDNN, AVNN, pNN50, LF, and HF had high positive relationships (P<.001), and the LF:HF ratio had a moderate positive relationship (P<.001). The average-per-night test also indicated considerably lower error variances than the 5-minute test for the parameters.

Conclusions

The Oura Ring could accurately measure nocturnal HR and RMSSD in both the 5-minute and average-per-night tests. It provided acceptable nocturnal AVNN, pNN50, HF, and SDNN accuracy in the average-per-night test but not in the 5-minute test. In contrast, the LF and LF:HF ratio of the ring had high error rates in both tests.

Heart rate recovery is useful for evaluating the recovery of exercise tolerance in patients with heart failure and atrial fibrillation

This study aimed to examine the factors that contribute to improvement of exercise tolerance in patients with heart failure (HF) and atrial fibrillation (AF) following cardiac rehabilitation. Our hypothesis is that parasympathetic values are important for recovering exercise tolerance in those patients. We included 84 consecutive patients with HF and AF (mean age: 69 ± 15 years, 80% men). All of the patients underwent a cardiopulmonary exercise test and had pre and post 5 month cardiac rehabilitation assessed. After 155 ± 11 days and 44 ± 8 sessions, 73 patients (86%) showed an increase in peak oxygen uptake (VO₂) and VO₂ at the anaerobic threshold. In univariate linear regression analysis, the % change in heart rate recovery, plasma B-type natriuretic peptide levels, resting heart rate, and the minute ventilation /carbon dioxide output slope were significantly related to that of peak VO₂ (p < 0.01, p = 0.03, p = 0.02, p < 0.01, respectively). Stepwise multivariate linear regression analysis showed that the % change in heart rate recovery was independently related to that of peak VO₂ (p < 0.05). Our results suggest that heart rate recovery is closely associated with recovery of exercise tolerance in patients with HF and AF after CR.

Estimating Left Ventricle Ejection Fraction Levels Using Circadian Heart Rate Variability Features and Support Vector Regression Models

OBJECTIVES

The purpose of this study was to set an optimal fit of the estimated LVEF at hourly intervals from 24-hour ECG recordings and compare it with the fit based on two gold-standard guidelines.

METHODS

Support vector regression (SVR) models were applied to estimate LVEF from ECG derived heart rate variability (HRV) data in one-hour intervals from 24-hour ECG recordings of patients with either preserved, mid-range, or reduced LVEF, obtained from the Intercity Digital ECG Alliance (IDEAL) study. A step-wise feature selection approach was used to ensure the best possible estimations of LVEF levels.

RESULTS

The experimental results have shown that the lowest Root Mean Square Error (RMSE) between the original and estimated LVEF levels was during 3-4 am, 5-6 am and 6-7 pm.

CONCLUSION

The observations suggest these hours as possible times for intervention and optimal treatment outcomes. In addition, LVEF classifications following the ACCF/AHA guidelines leads to a more accurate assessment of mid-range LVEF.

SIGNIFICANCE

This study paves the way to explore the use of HRV features in the prediction of LVEF percentages as an indicator of disease progression, which may lead to an automated classification process for CAD patients.

Predicting mortality with applied machine learning: Can we get there?

There is growing interest in using AI-based algorithms to support clinician decision-making. An important consideration is how transparent complex algorithms can be for predictions, particularly with respect to imminent mortality in a hospital environment. Understanding the basis of predictions, the process used to generate models and recommendations, how to generalize models based on one patient population to another, and the role of oversight organizations such as the Food and Drug Administration are important topics. In this paper, we debate opposing positions regarding whether these algorithms are 'ready yet' for use today in clinical settings for physicians, patients and caregivers. We report voting results from participating audience members in attendance at the conference debate for each of these positions obtained real-time from a smartphone-based platform.

Heart rate variability as a marker of recovery from critical illness in children

Objectives

The purpose of this study was to Identify whether changes in heart rate variability (HRV) could be detected as critical illness resolves by comparing HRV from the time of pediatric intensive care unit (PICU) admission with HRV immediately prior to discharge. We also sought to demonstrate that HRV derived from electrocardiogram (ECG) data from bedside monitors can be calculated in critically-ill children using a real-time, streaming analytics platform.

Methods

This was a retrospective, observational pilot study of 17 children aged 0 to 18 years admitted to the PICU of a free-standing, academic children’s hospital. Three time-domain measures of HRV were calculated in real-time from bedside monitor ECG data and stored for analysis. Measures included: root mean square of successive differences between NN intervals (RMSSD), percent of successive NN interval differences above 50 ms (pNN50), and the standard deviation of NN intervals (SDNN).

Results

HRV values calculated from the first and last 24 hours of PICU stay were analyzed. Mixed effects models demonstrated that all three measures of HRV were significantly lower during the first 24 hours compared to the last 24 hours of PICU admission (p<0.001 for all three measures). In models exploring the relationship between time from admission and log HRV values, the predicted average HRV remained consistently higher in the last 24 hours of PICU stay compared to the first 24 hours.

Conclusion

HRV was significantly lower in the first 24 hours compared to the 24 hours preceding PICU discharge, after resolution of critical illness. This demonstrates that it is feasible to detect changes in HRV using an automated, streaming analytics platform. Continuous tracking of HRV may serve as a marker of recovery in critically ill children.

Dose-response relationship between very vigorous physical activity and cardiovascular health assessed by heart rate variability in adults: Cross-sectional results from the EPIMOV study

The minimum amount of physical activity needed to obtain health benefits has been widely determined. Unlikely, the impact of extreme amounts of very vigorous physical activity (VVPA, ≥ 8 metabolic equivalents) to the heart remains controversial. We aimed to evaluate the dose-response relationship between VVPA and heart rate variability (HRV) in adults. We selected 1040 asymptomatic individuals (60% women, 42 ± 15 years, 28 ± 6 kg/m2) from the Epidemiology and Human Movement Study (EPIMOV). Participants remained in the supine position for 10 min, and we selected an intermediate 5-min window for HRV analysis. The standard deviation of the RR intervals, root mean square of RR intervals, successive RR intervals that differ > 50 ms, powers of the low-and high-frequency bands and Poincaré plot standard deviations were quantified. Participants used a triaxial accelerometer (Actigraph GT3x+) above the dominant hip for 4-7 consecutive days for quantifying their physical activity. We also evaluated the maximum oxygen uptake ([Formula: see text]) during an exercise test. We stratified participants into five groups according to the VVPA in min/week (group 1, ≤ 1.50; 2, 1.51-3.16; 3, 3.17-3.54; 4, 3.55-20.75; and 5, > 20.75). The linear trends of the HRV through the quintiles of VVPA were investigated. We used logarithmic transformations to compare the five groups adjusted for age, sex, cardiovascular risk, and [Formula: see text]. We found a better HRV with increased VVPA for all HRV indices studied (p trend < 0.05). However, group 5 did not differ from group 4 (p > 0.05) for none of the indices. We conclude that there is an incremental benefit of VVPA on HRV of asymptomatic adults. Since we found neither additional benefits nor the harmful impact of amounts of VVPA as high as 22 min/week on HRV, our results should not discourage asymptomatic adults to perform VVPA.

Electrocardiomatrix facilitates qualitative identification of diminished heart rate variability in critically ill patients shortly before cardiac arrest

BACKGROUND

Although heart rate variability (HRV) has diagnostic and prognostic value for the assessment of cardiac risk, HRV analysis is not routinely performed in a hospital setting. Current HRV analysis methods are primarily quantitative; such methods are sensitive to signal contamination and require extensive post hoc processing.

METHODS AND RESULTS

Raw electrocardiogram (ECG) data from the Sleep Heart Health Study was transformed into electrocardiomatrix (ECM), in which sequential cardiac cycles are aligned, in parallel, along a shared axis. Such juxtaposition facilitates the visual evaluation of beat-to-beat changes in the R-R interval without sacrificing the morphology of the native ECG signal. Diminished HRV, verified by traditional methods, was readily identifiable. We also examined data from a cohort of hospitalized patients who suffered cardiac arrest within 24 h of data acquisition, all of whom exhibited severely diminished HRV that were visually apparent on ECM display.

CONCLUSIONS

ECM streamlines the identification of depressed HRV, which may signal deteriorating patient condition.

Heart rate recovery of individuals undergoing cardiac rehabilitation after acute coronary syndrome

BACKGROUND

An efficient cardiac rehabilitation programme (CRP) can improve the functional ability of patients after acute coronary syndrome (ACS).

OBJECTIVE

To examine the effect of a CRP on parasympathetic reactivation and heart rate recovery (HRR) measured after a 6-min walk test (6MWT), and correlation with 6MWT distance and well-being after ACS.

METHODS

Eleven normoweight patients after ACS (BMI<25kg/m²; 10 males; mean [SD] age 61 [9] years) underwent an 8-week CRP. Before (pre-) and at weeks 4 (W4) and 8 (W8) during the CRP, they performed a 6MWT on a treadmill, followed by 10-min of seated passive recovery, with HRR and HR variability (HRV) recordings. HRR was measured at 1, 3, 5 and 10min after the 6MWT (HRR1, HRR3, HRR5, HRR10), then modelized by a mono-exponential function. Time-domain (square root of the mean of the sum of the squares of differences between adjacent normal R-R intervals [RMSSD]) and frequency-domain (with high- and low-frequency band powers) were used to analyse HRV. Participants completed a mental and physical well-being questionnaire at pre- and W8. Exhaustion after tests was assessed by the Borg scale. Pearson correlation was used to assess correlations.

RESULTS

HRR3, HRR5 and HRR10 increased by 37%, 36% and 28%, respectively, between pre- and W8 (P<0.05), and were positively correlated with change in 6MWT distance (r=0.58, 0.66 and 0.76; P<0.05). Percentage change in HRR3 was positively correlated with change in well-being (r=0.70; P=0.01). Parasympathic reactivation (RMSSD) was improved only during the first 30sec of recovery (P=0.04).

CONCLUSION

Among patients undergoing a CRP after ACS, increased HRR after a 6MWT, especially at 3min, was positively correlated with 6MWT distance and improved well-being. HRR raw data seem more sensitive than post-exercise HRV analysis for monitoring functional and autonomic improvement after ACS.

Can Illness Perceptions Predict Lower Heart Rate Variability following Acute Myocardial Infarction?

Objective: Decreased heart rate variability (HRV) has been reported to be a predictor of mortality after myocardial infarction (MI). Patients' beliefs and perceptions concerning their illness may play a role in decreased HRV. This study investigated if illness perceptions predict HRV at 3 months following acute MI.

Methods: 130 patients referred to a tertiary cardiology center, were examined within 48 h and 3 months following acute MI. At admission, patients' cognitive representations of their MI were assessed using the German version of the self-rated Brief Illness Perception Questionnaire (Brief IPQ). At admission and after 3 months (follow-up), frequency and time domain measures of HRV were obtained from 5-min electrocardiogram (ECG) recordings during stable supine resting.

Results: Linear hierarchical regression showed that the Brief IPQ dimensions timeline (β coefficient = 0.29; p = 0.044), personal control (β = 0.47; p = 0.008) and illness understanding (β = 0.43; p = 0.014) were significant predictors of HRV, adjusted for age, gender, baseline HRV, diabetes, beta-blockers, left ventricular ejection fraction (LVEF), attendance of cardiac rehabilitation, and depressive symptoms.

Conclusions: As patients' negative perceptions of their illness are associated with lower HRV following acute MI, a brief illness perception questionnaire may help to identify patients who might benefit from a specific illness perceptions intervention.

Is there cardiac risk in panic disorder? An updated systematic review

BACKGROUND

The recognized relationship between panic disorder (PD) and cardiac disorders (CDs) is not unequivocal. We reviewed the association between PD and coronary artery disease (CAD), arrhythmias, cardiomyopathies, and sudden cardiac death.

METHODS

We undertook an updated systematic review, according to PRISMA guidelines. Relevant studies dating from January 1, 2000, to December 31, 2014, were identified using the PubMed database and a review of bibliographies. The psychiatric and cardiac diagnostic methodology used in each study was then to very selective inclusion criteria.

RESULTS

Of 3044 studies, 14 on CAD, 2 on cardiomyopathies, and 1 on arrhythmias were included. Overall, the studies supported a panic-CAD association. Furthermore, in some of the studies finding no association between current full-blown PD and CAD, a broader susceptibility to panic, manifesting as past PD, current agoraphobia, or subthreshold panic symptoms, appeared to be relevant to the development of CAD. Preliminary data indicated associations between panic, arrhythmias, and cardiomyopathies.

LIMITATIONS

The studies were largely cross-sectional and conducted in cardiological settings. Only a few included blind settings. The clinical conditions of patients with CDs and the qualifications of raters of psychiatric diagnoses were highly heterogeneous. CDs other than CAD had been insufficiently investigated.

CONCLUSIONS

Our review supported a relationship between PD and CDs. Given the available findings and the involvement of the cardiorespiratory system in the pathophysiology of PD, an in-depth investigation into the panic-CDs association is highly recommended. This should contribute to improved treatment and prevention of cardiac events and/or mortality, linked to PD.

Current Approaches to Quantifying Tonic and Reflex Autonomic Outflows Controlling Cardiovascular Function in Humans and Experimental Animals

The role of the autonomic nervous system in the pathophysiology of human and experimental models of cardiovascular disease is well established. In the recent years, there have been some rapid developments in the diagnostic approaches used to assess and monitor autonomic functions. Although most of these methods are devoted for research purposes in laboratory animals, many have still found their way to routine clinical practice. To name a few, direct long-term telemetry recording of sympathetic nerve activity (SNA) in rodents, single-unit SNA recording using microneurography in human subjects and spectral analysis of blood pressure and heart rate in both humans and animals have recently received an overwhelming attention. In this article, we therefore provide an overview of the methods and techniques used to assess tonic and reflex autonomic functions in humans and experimental animals, highlighting current advances available and procedure description, limitations and usefulness for diagnostic purposes.

Cardiovascular and metabolic risk markers are related to parasympathetic indices in pre-pubertal adolescents

OBJECTIVE

To analyse the relationship between different heart rate variability indices, resting heart rate, and cardiovascular markers in adolescents.

METHODS

A cross-sectional study was carried out with information from an ongoing cohort study. The sample was composed of 99 adolescents who complied with the following inclusion criteria: aged between 11 and 14 years; enrolled in a school unit of elementary education; absence of any known diseases; no drug consumption; and a formal consent signed by the parents or legal guardians. Weight, height, heart rate variability, lipid profile, inflammatory markers, blood pressure, resting heart rate, intima-media thickness, blood flow, and trunk fatness were measured. Partial correlation and linear regression (expressed by β and 95% confidence intervals [95%CI]) analyses were used to analyse the relationships between the variables.

RESULTS

In the linear regression analysis, even after adjustments for sex, age, trunk fatness, and somatic maturation, parasympathetic activity presented significant correlations with maximum carotid artery blood flow (β=-0.111 [95%CI=-0.216; -0.007]), systolic blood pressure (β=-0.319 [95%CI=-0.638; -0.001]), and resting heat rate (β=-0.005 [95%CI=-0.009; -0.002]).

CONCLUSION

Parasympathetic activity at rest is inversely related to maximum and minimum blood flow, triacylglycerol levels, and systolic blood pressure. These findings suggest that heart rate variability has the potential to discriminate pre-pubertal adolescents at increased risk.

A pilot study of prognostic value of non-invasive cardiac parameters for major adverse cardiac events in patients with acute coronary syndrome treated with percutaneous coronary intervention

The objective of this study was to determine the combination of left ventricular ejection fraction (LVEF) and individual electrocardiographic parameters related to abnormal depolarization/repolarization or baroreceptor sensitivity that had the best predictive value for major adverse cardiac events (MACE) in patients with acute coronary syndrome (ACS). Patients with ACS who underwent coronary angiography and percutaneous coronary intervention (PCI) were included in this prospective study. Ventricular late potential (VLP), heart rate turbulence (HRT), heart rate variability (HRV), and T wave alternans (TWA) parameters were measured using 24 h Holter monitoring 2-4 weeks after onset of ACS. Initial and follow-up LVEF was measured by ultrasound. Patients were followed for at least 6 months to record the occurrence of MACE. Models using combinations of the individual independent prognostic factors found by multivariate analysis were then constructed to use for estimation of risk of MACE. In multivariate analysis, VLP measured as QRS duration, HRV measured as standard deviation of normal RR intervals, and followup LVEF, but none of the other parameters studied, were independent risk factors for MACE. Areas under ROC curve (AUCs) for combinations of 2 or all 3 factors ranged from 0.73 to 0.76. Combinations of any of the three independent risk factors for MACE in ACS patients with PCI improved prediction and, because these risk factors were obtained non-invasively, may have future clinical usefulness.

Cloud-Based Smart Health Monitoring System for Automatic Cardiovascular and Fall Risk Assessment in Hypertensive Patients

The aim of this paper is to describe the design and the preliminary validation of a platform developed to collect and automatically analyze biomedical signals for risk assessment of vascular events and falls in hypertensive patients. This m-health platform, based on cloud computing, was designed to be flexible, extensible, and transparent, and to provide proactive remote monitoring via data-mining functionalities. A retrospective study was conducted to train and test the platform. The developed system was able to predict a future vascular event within the next 12 months with an accuracy rate of 84 % and to identify fallers with an accuracy rate of 72 %. In an ongoing prospective trial, almost all the recruited patients accepted favorably the system with a limited rate of inadherences causing data losses (<20 %). The developed platform supported clinical decision by processing tele-monitored data and providing quick and accurate risk assessment of vascular events and falls.

Automatic prediction of cardiovascular and cerebrovascular events using heart rate variability analysis

Background

There is consensus that Heart Rate Variability is associated with the risk of vascular events. However, Heart Rate Variability predictive value for vascular events is not completely clear. The aim of this study is to develop novel predictive models based on data-mining algorithms to provide an automatic risk stratification tool for hypertensive patients.

Methods

A database of 139 Holter recordings with clinical data of hypertensive patients followed up for at least 12 months were collected ad hoc. Subjects who experienced a vascular event (i.e., myocardial infarction, stroke, syncopal event) were considered as high-risk subjects. Several data-mining algorithms (such as support vector machine, tree-based classifier, artificial neural network) were used to develop automatic classifiers and their accuracy was tested by assessing the receiver-operator characteristics curve. Moreover, we tested the echographic parameters, which have been showed as powerful predictors of future vascular events.

Results

The best predictive model was based on random forest and enabled to identify high-risk hypertensive patients with sensitivity and specificity rates of 71.4% and 87.8%, respectively. The Heart Rate Variability based classifier showed higher predictive values than the conventional echographic parameters, which are considered as significant cardiovascular risk factors.

Conclusions

Combination of Heart Rate Variability measures, analyzed with data-mining algorithm, could be a reliable tool for identifying hypertensive patients at high risk to develop future vascular events.