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

Wearable biosensors in cardiovascular disease

This review provides a comprehensive overview of the latest advancements in wearable biosensors, emphasizing their applications in cardiovascular disease monitoring. Initially, the key sensing signals and biomarkers crucial for cardiovascular health, such as electrocardiogram, phonocardiography, pulse wave velocity, blood pressure, and specific biomarkers, are highlighted. Following this, advanced sensing techniques for cardiovascular disease monitoring are examined, including wearable electrophysiology devices, optical fibers, electrochemical sensors, and implantable cardiac devices. The review also delves into hydrogel-based wearable electrochemical biosensors, which detect biomarkers in sweat, interstitial fluids, saliva, and tears. Further attention is given to flexible electronics-based biosensors, including resistive, capacitive, and piezoelectric force sensors, as well as resistive and pyroelectric temperature sensors, flexible biochemical sensors, and sensor arrays. Moreover, the discussion extends to polymer-based wearable sensors, focusing on innovations in contact lens, textile-type, patch-type, and tattoo-type sensors. Finally, the review addresses the challenges associated with recent wearable biosensing technologies and explores future perspectives, highlighting potential groundbreaking avenues for transforming wearable sensing devices into advanced diagnostic tools with multifunctional capabilities for cardiovascular disease monitoring and other healthcare applications.

Automatic identification of hypertension and assessment of its secondary effects using artificial intelligence: A systematic review (2013-2023)

Artificial Intelligence (AI) techniques are increasingly used in computer-aided diagnostic tools in medicine. These techniques can also help to identify Hypertension (HTN) in its early stage, as it is a global health issue. Automated HTN detection uses socio-demographic, clinical data, and physiological signals. Additionally, signs of secondary HTN can also be identified using various imaging modalities. This systematic review examines related work on automated HTN detection. We identify datasets, techniques, and classifiers used to develop AI models from clinical data, physiological signals, and fused data (a combination of both). Image-based models for assessing secondary HTN are also reviewed. The majority of the studies have primarily utilized single-modality approaches, such as biological signals (e.g., electrocardiography, photoplethysmography), and medical imaging (e.g., magnetic resonance angiography, ultrasound). Surprisingly, only a small portion of the studies (22 out of 122) utilized a multi-modal fusion approach combining data from different sources. Even fewer investigated integrating clinical data, physiological signals, and medical imaging to understand the intricate relationships between these factors. Future research directions are discussed that could build better healthcare systems for early HTN detection through more integrated modeling of multi-modal data sources.

Effects of Aerobic Exercise Combined With Attentional Bias Modification in the Care of Male Patients With a Methamphetamine Use Disorder

OBJECTIVE

It remains unclear which individual or combined strategies are most beneficial for methamphetamine use disorders (MUDs). We compared the effects of aerobic exercise, attentional bias modification, and combined intervention on male patients with MUD.

METHOD

One hundred male patients with MUD were randomly assigned to combined intervention, aerobic exercise, attentional bias modification, or control groups (25 patients per group). The 8-week intervention protocol included three 60-minute sessions of aerobic exercises per week. Primary outcomes included high- and low-frequency heart rate variability, executive function, and cardiorespiratory fitness measured by customized software, computerized tests, and the Harvard step test, respectively. Secondary outcomes included psychiatric symptoms, drug craving, training acceptability, and persistence.

RESULTS

Participant characteristics were matched between groups at baseline. Executive function, heart rate variability, cardiorespiratory fitness, drug craving, and most psychiatric symptoms had significant time-group interactions at posttest (p < .05, η2 = .08-.28). Compared with the attentional bias modification and control groups, the combined intervention and aerobic exercise groups improved significantly in executive function, heart rate variability, cardiorespiratory fitness, and most secondary outcomes. In addition, high-frequency heart rate variability and cardiorespiratory fitness in the aerobic exercise group were significantly higher than those in the combined intervention group.

CONCLUSIONS

Combination strategies showed comparable efficacy to aerobic exercise alone in improving executive function, psychiatric symptoms, and drug craving and significantly exceeded other conditions. For heart rate variability and cardiorespiratory fitness, aerobic exercise alone was the most effective. For acceptability and persistence, combination strategies were preferred over single-domain training and health education intervention.

Age and Gender Impact on Heart Rate Variability towards Noninvasive Glucose Measurement

Heart rate variability (HRV) parameters can reveal the performance of the autonomic nervous system and possibly estimate the type of its malfunction, such as that of detecting the blood glucose level. Therefore, we aim to find the impact of other factors on the proper calculation of HRV. In this paper, we research the relation between HRV and the age and gender of the patient to adjust the threshold correspondingly to the noninvasive glucose estimator that we are developing and improve its performance. While most of the literature research so far addresses healthy patients and only short- or long-term HRV, we apply a more holistic approach by including both healthy patients and patients with arrhythmia and different lengths of HRV measurements (short, middle, and long). The methods necessary to determine the correlation are (i) point biserial correlation, (ii) Pearson correlation, and (iii) Spearman rank correlation. We developed a mathematical model of a linear or monotonic dependence function and a machine learning and deep learning model, building a classification detector and level estimator. We used electrocardiogram (ECG) data from 4 different datasets consisting of 284 subjects. Age and gender influence HRV with a moderate correlation value of 0.58. This work elucidates the intricate interplay between individual input and output parameters compared with previous efforts, where correlations were found between HRV and blood glucose levels using deep learning techniques. It can successfully detect the influence of each input.

Effects of 8 months of high-intensity interval training on physical fitness and health-related quality of life in substance use disorder

Objective

This study aimed to investigate the effect of 8 months of high-intensity interval training (HIIT) on physical fitness and health-related quality of life in substance use disorder.

Methods

Sixty substance use disorder were randomly assigned to either the HIIT group or the control group according to a random sampling method. The HIIT group received 8 months of four 60-min sessions per week under supervision. Weight, waist circumference, body fat percentage, heart rate, blood pressure, VO2max, reaction time, grip strength, standing on one foot with eyes closed, sitting forward flexion, and quadrant jumping, standing on one foot with eyes closed, the number of push-ups, quality of life (SF-36) score, and craving (VAS) scored were monitored in the HIIT and control groups at baseline, 4 months, and 8 months. SPSS 22.0 was used to conduct repeated measurement analysis of variance and Pearson correlation analysis on the collected subject data.

Results

Compared with baseline, weight (p < 0.001), waist circumference (p < 0.001), body fat percentage (p < 0.001), heart rate (p < 0.05), Systolic blood pressure (p < 0.01), systolic blood pressure (p < 0.05), reaction time (p < 0.001),PSQI (p < 0.001), Total cholesterol (p < 0.001), Triglyceride (p < 0.001), Blood sugar (p < 0.001) and VAS score (p < 0.001) were significantly decreased after 8 months of exercise intervention. Contrastingly, VO2max (p < 0.05), grip strength (p < 0.05), eyes closed and one foot Standing (p < 0.001), sitting forward flexion (p < 0.001), quadrant jumping (p < 0.001), push-ups (p < 0.001), PCS (p < 0.001), and MCS (p < 0.001) were significantly increased. VO2max was significantly negatively correlated with VAS (r = -0.434, p < 0.001), and significantly positively correlated with PCS (r = 0.425, p < 0.001). There was a positive correlation between standing on one foot with closed eyes and MCS (r = 0.283, p < 0.05).

Conclusion

Eight months of HIIT can comprehensively improve the physical health level and health-related quality of life of men with substance use disorders, reduce the desire for drugs, and lay the foundation for better starting a happy life.

A Disentangled VAE-BiLSTM Model for Heart Rate Anomaly Detection

Cardiovascular diseases (CVDs) remain a leading cause of death globally. According to the American Heart Association, approximately 19.1 million deaths were attributed to CVDs in 2020, in particular, ischemic heart disease and stroke. Several known risk factors for CVDs include smoking, alcohol consumption, lack of regular physical activity, and diabetes. The last decade has been characterized by widespread diffusion in the use of wristband-style wearable devices which can monitor and collect heart rate data, among other information. Wearable devices allow the analysis and interpretation of physiological and activity data obtained from the wearer and can therefore be used to monitor and prevent potential CVDs. However, these data are often provided in a manner that does not allow the general user to immediately comprehend possible health risks, and often require further analytics to draw meaningful conclusions. In this paper, we propose a disentangled variational autoencoder (β-VAE) with a bidirectional long short-term memory network (BiLSTM) backend to detect in an unsupervised manner anomalies in heart rate data collected during sleep time with a wearable device from eight heterogeneous participants. Testing was performed on the mean heart rate sampled both at 30 s and 1 min intervals. We compared the performance of our model with other well-known anomaly detection algorithms, and we found that our model outperformed them in almost all considered scenarios and for all considered participants. We also suggest that wearable devices may benefit from the integration of anomaly detection algorithms, in an effort to provide users more processed and straightforward information.

Nonlinear analysis of heart rate variability signals in meditative state: a review and perspective

INTRODUCTION

In recent times, an upsurge in the investigation related to the effects of meditation in reconditioning various cardiovascular and psychological disorders is seen. In majority of these studies, heart rate variability (HRV) signal is used, probably for its ease of acquisition and low cost. Although understanding the dynamical complexity of HRV is not an easy task, the advances in nonlinear analysis has significantly helped in analyzing the impact of meditation of heart regulations. In this review, we intend to present the various nonlinear approaches, scientific findings and their limitations to develop deeper insights to carry out further research on this topic.

RESULTS

Literature have shown that research focus on nonlinear domain is mainly concentrated on assessing predictability, fractality, and entropy-based dynamical complexity of HRV signal. Although there were some conflicting results, most of the studies observed a reduced dynamical complexity, reduced fractal dimension, and decimated long-range correlation behavior during meditation. However, techniques, such as multiscale entropy (MSE) and multifractal analysis (MFA) of HRV can be more effective in analyzing non-stationary HRV signal, which were hardly used in the existing research works on meditation.

CONCLUSIONS

After going through the literature, it is realized that there is a requirement of a more rigorous research to get consistent and new findings about the changes in HRV dynamics due to the practice of meditation. The lack of adequate standard open access database is a concern in drawing statistically reliable results. Albeit, data augmentation technique is an alternative option to deal with this problem, data from adequate number of subjects can be more effective. Multiscale entropy analysis is scantily employed in studying the effect of meditation, which probably need more attention along with multifractal analysis.

METHODS

Scientific databases, namely PubMed, Google Scholar, Web of Science, Scopus were searched to obtain the literature on "HRV analysis during meditation by nonlinear methods". Following an exclusion criteria, 26 articles were selected to carry out this scientific analysis.

Machine Learning-Based Prediction of Digoxin Toxicity in Heart Failure: A Multicenter Retrospective Study

Digoxin toxicity (plasma digoxin concentration ≥0.9 ng/mL) is associated with worsening heart failure (HF). Decision tree (DT) analysis, a machine learning method, has a flowchart-like model where users can easily predict the risk of adverse drug reactions. The present study aimed to construct a flowchart using DT analysis that can be used by medical staff to predict digoxin toxicity. We conducted a multicenter retrospective study involving 333 adult patients with HF who received oral digoxin treatment. In this study, we employed a chi-squared automatic interaction detection algorithm to construct DT models. The dependent variable was set as the plasma digoxin concentration (≥ 0.9 ng/mL) in the trough during the steady state, and factors with p < 0.2 in the univariate analysis were set as the explanatory variables. Multivariate logistic regression analysis was conducted to validate the DT model. The accuracy and misclassification rates of the model were evaluated. In the DT analysis, patients with creatinine clearance <32 mL/min, daily digoxin dose ≥1.6 µg/kg, and left ventricular ejection fraction ≥50% showed a high incidence of digoxin toxicity (91.8%; 45/49). Multivariate logistic regression analysis revealed that creatinine clearance <32 mL/min and daily digoxin dose ≥1.6 µg/kg were independent risk factors. The accuracy and misclassification rates of the DT model were 88.2 and 46.2 ± 2.7%, respectively. Although the flowchart created in this study needs further validation, it is straightforward and potentially useful for medical staff in determining the initial dose of digoxin in patients with HF.

Recent Advances in Cardiovascular Disease Biosensors and Monitoring Technologies

Cardiovascular disease (CVD) causes significant mortality and remains the leading cause of death globally. Thus, to reduce mortality, early diagnosis by measurement of cardiac biomarkers and heartbeat signals presents fundamental importance. Traditional CVD examination requires bulky hospital instruments to conduct electrocardiography recording and immunoassay analysis, which are both time-consuming and inconvenient. Recently, development of biosensing technologies for rapid CVD marker screening attracted great attention. Thanks to the advancement in nanotechnology and bioelectronics, novel biosensor platforms are developed to achieve rapid detection, accurate quantification, and continuous monitoring throughout disease progression. A variety of sensing methodologies using chemical, electrochemical, optical, and electromechanical means are explored. This review first discusses the prevalence and common categories of CVD. Then, heartbeat signals and cardiac blood-based biomarkers that are widely employed in clinic, as well as their utilizations for disease prognosis, are summarized. Emerging CVD wearable and implantable biosensors and monitoring bioelectronics, allowing these cardiac markers to be continuously measured are introduced. Finally, comparisons of the pros and cons of these biosensing devices along with perspectives on future CVD biosensor research are presented.

Risk evaluation of carbapenem-induced liver injury based on machine learning analysis

INTRODUCTION

Information regarding carbapenem-induced liver injury is limited, and the rate of liver injury caused by meropenem (MEPM) and doripenem (DRPM) remains unknown. Decision tree (DT) analysis, a machine learning method, has a flowchart-like model where users can easily predict the risk of liver injury. Thus, we aimed to compare the rate of liver injury between MEPM and DRPM and construct a flowchart that can be used to predict carbapenem-induced liver injury.

METHODS

We investigated patients treated with MEPM (n = 310) or DRPM (n = 320) and confirmed liver injury as the primary outcome. We used a chi-square automatic interaction detection algorithm to construct DT models. The dependent variable was set as liver injury from a carbapenem (MEPM or DRPM), and factors including alanine aminotransferase (ALT), albumin-bilirubin (ALBI) score, and concomitant use of acetaminophen were used as explanatory variables.

RESULTS

The rates of liver injury were 22.9% (71/310) and 17.5% (56/320) in the MEPM and DRPM groups, respectively; no significant differences in the rate were observed (95% confidence interval: 0.710-1.017). Although the DT model of MEPM could not be constructed, DT analysis showed that the incidence of introducing DRPM in patients with ALT >22 IU/L and ALBI scores > -1.87 might be high-risk.

CONCLUSIONS

The risk of developing liver injury did not differ significantly between the MEPM and DRPM groups. Since ALT and ALBI score are evaluated in clinical settings, this DT model is convenient and potentially useful for medical staff in assessing liver injury before DRPM administration.

The combination of heart rate variability and ABCD2 score portends adverse outcomes after minor stroke or transient ischemic attack

BACKGROUND AND PURPOSE

The residual recurrent risk of stroke, which cannot be entirely explained by the traditional ABCD2 score, still existed. Heart rate variability (HRV), a method for reflecting the function of automatic nervous system (ANS), was a novel predictor of secondary stroke events. We aimed to investigate the relationships of combined HRV and ABCD² score with adverse outcomes after acute minor stroke (MS) or transient ischemic attack (TIA), and further investigate the independent associations between HRV and adverse outcomes after MS/TIA stratified by ABCD² score.

METHODS

Data were obtained from the Third China National Stroke Registry (CNSR-III) study. We assessed the activity of ANS using standard deviation of NN intervals (SDNN), a time domain index of HRV. Trained investigators collected clinical characteristics and estimated ABCD² score for each participant. All enrolled patients were categorized into different risk groups based on SDNN level and ABCD² score. The clinial outcomes included recurrent stroke, recurrent ischemic stroke, and disability within 1-year follow-up. We evaluated whether combined SDNN and ABCD² score were associated with recurrent events using multivariable Cox regression models, and those with disability using multivariable logistic regression models. The independent associations between SDNN and diverse outcomes stratified by ABCD² score were explored using multivariable Cox and logistic regression analyses.

RESULTS

A total of 5,743 participants [3,316 (70.02) males, 62.0 (54.0-69.0) years] were included. Patients with low SDNN and ABCD² ≥ 4 were associated with higher risk of recurrent stroke within 1 year (10.8% versus 4.9%; [HR] 1.31, 95% [CI] 0.92-1.88, P = 0.14) compared to patients with high SDNN with ABCD² < 4. Lower SDNN was associated with higher recurrent stroke in patients with ABCD² 0-3 score ([HR] 0.73, 95% [CI] 0.57-0.947, P = 0.01) and ABCD² 4-5 score ([HR] 0.85, 95% [CI] 0.74-0.97, P = 0.02), but not in patients with ABCD² 6-7 score.

CONCLUSION

The combination of HRV and ABCD² score might efficiently stratify the risk of 1-year recurrent stroke after MS/TIA. Moreover, lower SDNN was independently related to recurrent stroke in patients with MS/TIA, especially for those with low-to-moderate traditional vascular risk factors.

Cloud-based healthcare framework for real-time anomaly detection and classification of 1-D ECG signals

Real-time data collection and pre-processing have enabled the recognition, realization, and prediction of diseases by extracting and analysing the important features of physiological data. In this research, an intelligent end-to-end system for anomaly detection and classification of raw, one-dimensional (1D) electrocardiogram (ECG) signals is given to assess cardiovascular activity automatically. The acquired raw ECG data is pre-processed carefully before storing it in the cloud, and then deeply analyzed for anomaly detection. A deep learning-based auto-encoder(AE) algorithm is applied for the anomaly detection of 1D ECG time-series signals. As a next step, the implemented system identifies it by a multi-label classification algorithm. To improve the classification accuracy and model robustness the improved feature-engineered parameters of the large and diverse datasets have been incorporated. The training has been done using the amazon web service (AWS) machine learning services and cloud-based storage for a unified solution. Multi-class classification of raw ECG signals is challenging due to a large number of possible label combinations and noise susceptibility. To overcome this problem, a performance comparison of a large set of machine algorithms in terms of classification accuracy is presented on an improved feature-engineered dataset. The proposed system reduces the raw signal size up to 95% using wavelet time scattering features to make it less compute-intensive. The results show that among several state-of-the-art techniques, the long short-term memory (LSTM) method has shown 100% classification accuracy, and an F1 score on the three-class test dataset. The ECG signal anomaly detection algorithm shows 98% accuracy using deep LSTM auto-encoders with a reconstructed error threshold of 0.02 in terms of absolute error loss. Our approach provides performance and predictive improvement with an average mean absolute error loss of 0.0072 for normal signals and 0.078 for anomalous signals.

Advancement in the Cuffless and Noninvasive Measurement of Blood Pressure: A Review of the Literature and Open Challenges

Hypertension is a chronic condition that is one of the prominent reasons behind cardiovascular disease, brain stroke, and organ failure. Left unnoticed and untreated, the deterioration in a health condition could even result in mortality. If it can be detected early, with proper treatment, undesirable outcomes can be avoided. Until now, the gold standard is the invasive way of measuring blood pressure (BP) using a catheter. Additionally, the cuff-based and noninvasive methods are too cumbersome or inconvenient for frequent measurement of BP. With the advancement of sensor technology, signal processing techniques, and machine learning algorithms, researchers are trying to find the perfect relationships between biomedical signals and changes in BP. This paper is a literature review of the studies conducted on the cuffless noninvasive measurement of BP using biomedical signals. Relevant articles were selected using specific criteria, then traditional techniques for BP measurement were discussed along with a motivation for cuffless measurement use of biomedical signals and machine learning algorithms. The review focused on the progression of different noninvasive cuffless techniques rather than comparing performance among different studies. The literature survey concluded that the use of deep learning proved to be the most accurate among all the cuffless measurement techniques. On the other side, this accuracy has several disadvantages, such as lack of interpretability, computationally extensive, standard validation protocol, and lack of collaboration with health professionals. Additionally, the continuing work by researchers is progressing with a potential solution for these challenges. Finally, future research directions have been provided to encounter the challenges.

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.

Using wearable devices to generate real-world, individual-level data in rural, low-resource contexts in Burkina Faso, Africa: A case study

Background

Wearable devices may generate valuable data for global health research for low- and middle-income countries (LMICs). However, wearable studies in LMICs are scarce. This study aims to investigate the use of consumer-grade wearables to generate individual-level data in vulnerable populations in LMICs, focusing on the acceptability (quality of the devices being accepted or even liked) and feasibility (the state of being workable, realizable, and practical, including aspects of data completeness and plausibility).

Methods

We utilized a mixed-methods approach within the health and demographic surveillance system (HDSS) to conduct a case study in Nouna, Burkina Faso (BF). All HDSS residents older than 6 years were eligible. N = 150 participants were randomly selected from the HDSS database to wear a wristband tracker (Withings Pulse HR) and n = 69 also a thermometer patch (Tucky thermometer) for 3 weeks. Every 4 days, a trained field worker conducted an acceptability questionnaire with participants, which included questions for the field workers as well. Descriptive and qualitative thematic analyses were used to analyze the responses of study participants and field workers.

Results

In total, n = 148 participants were included (and n = 9 field workers). Participant's acceptability ranged from 94 to 100% throughout the questionnaire. In 95% of the cases (n = 140), participants reported no challenges with the wearable. Most participants were not affected by the wearable in their daily activities (n = 122, 83%) and even enjoyed wearing them (n = 30, 20%). Some were concerned about damage to the wearables (n = 7, 5%). Total data coverage (i.e., the proportion of the whole 3-week study duration covered by data) was 43% for accelerometer (activity), 3% for heart rate, and 4% for body shell temperature. Field workers reported technical issues like faulty synchronization (n = 6, 1%). On average, participants slept 7 h (SD 3.2 h) and walked 8,000 steps per day (SD 5573.6 steps). Acceptability and data completeness were comparable across sex, age, and study arms.

Conclusion

Wearable devices were well-accepted and were able to produce continuous measurements, highlighting the potential for wearables to generate large datasets in LMICs. Challenges constituted data missingness mainly of technical nature. To our knowledge, this is the first study to use consumer-focused wearables to generate objective datasets in rural BF.

Prediction of postoperative cardiac events in multiple surgical cohorts using a multimodal and integrative decision support system

Postoperative patients are at risk of life-threatening complications such as hemodynamic decompensation or arrhythmia. Automated detection of patients with such risks via a real-time clinical decision support system may provide opportunities for early and timely interventions that can significantly improve patient outcomes. We utilize multimodal features derived from digital signal processing techniques and tensor formation, as well as the electronic health record (EHR), to create machine learning models that predict the occurrence of several life-threatening complications up to 4 hours prior to the event. In order to ensure that our models are generalizable across different surgical cohorts, we trained the models on a cardiac surgery cohort and tested them on vascular and non-cardiac acute surgery cohorts. The best performing models achieved an area under the receiver operating characteristic curve (AUROC) of 0.94 on training and 0.94 and 0.82, respectively, on testing for the 0.5-hour interval. The AUROCs only slightly dropped to 0.93, 0.92, and 0.77, respectively, for the 4-hour interval. This study serves as a proof-of-concept that EHR data and physiologic waveform data can be combined to enable the early detection of postoperative deterioration events.

Postoperative effects of bariatric surgery on heart rate recovery and heart rate variability

Background: Several studies have reported associations between obesity and autonomic dysfunction. However, little research has investigated the effect of bariatric surgery on heart rate recovery (HRR) in the treadmill test and heart rate variability (HRV) in 24-hour Holter monitoring. We investigated the effects of bariatric surgery on HRR and HRV, which are parameters related to autonomic dysfunction. Methods: We retrospectively investigated patients who underwent bariatric surgery in 2019. The treadmill test, 24-hour Holter monitoring, and echocardiography were performed before and 6 months after surgery. We compared the changes in HRR in the treadmill test and HRV parameters such as the time domain and spectral domain in 24-hour Holter monitoring before and after surgery. Results: Of the 40 patients who underwent bariatric surgery, 25 patients had the treadmill test or 24-hour Holter monitoring both before and after surgery. Body weight and body mass index significantly decreased after surgery (112.86±24.37 kg vs. 89.10±20.26 kg, p<0.001; 39.22±5.69 kg/m2 vs. 31.00±5.09 kg/m2, p<0.001, respectively). HRR significantly increased (n=23; 43.00±20.97 vs. 64.29±18.49, p=0.001). The time domain of HRV parameters increased (n=21; standard deviation of the N-N interval 123.57±28.05 vs. 152.57±39.49, p=0.002 and mean N-N interval 791.57±88.84 vs. 869.05±126.31, p=0.002).Conclusions: Our data showed that HRR after exercise and HRV during 24-hour Holter monitoring improved after weight reduction with bariatric surgery through improved cardiac autonomic function.

Leveraging Continuous Vital Sign Measurements for Real-Time Assessment of Autonomic Nervous System Dysfunction After Brain Injury: A Narrative Review of Current and Future Applications

Subtle and profound changes in autonomic nervous system (ANS) function affecting sympathetic and parasympathetic homeostasis occur as a result of critical illness. Changes in ANS function are particularly salient in neurocritical illness, when direct structural and functional perturbations to autonomic network pathways occur and may herald impending clinical deterioration or intervenable evolving mechanisms of secondary injury. Sympathetic and parasympathetic balance can be measured quantitatively at the bedside using multiple methods, most readily by extracting data from electrocardiographic or photoplethysmography waveforms. Work from our group and others has demonstrated that data-analytic techniques can identify quantitative physiologic changes that precede clinical detection of meaningful events, and therefore may provide an important window for time-sensitive therapies. Here, we review data-analytic approaches to measuring ANS dysfunction from routine bedside physiologic data streams and integrating this data into multimodal machine learning-based model development to better understand phenotypical expression of pathophysiologic mechanisms and perhaps even serve as early detection signals. Attention will be given to examples from our work in acute traumatic brain injury on detection and monitoring of paroxysmal sympathetic hyperactivity and prediction of neurologic deterioration, and in large hemispheric infarction on prediction of malignant cerebral edema. We also discuss future clinical applications and data-analytic challenges and future directions.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

Association between heart rate and cardiovascular death in patients with coronary heart disease: A NHANES-based cohort study

BACKGROUND

Due to the lack of research, this study aimed to assess the association between the specific range of heart rate and cardiovascular (CV) death in coronary heart disease (CHD) patients.

HYPOTHESIS

Heart rate of 70-79 bpm may be associated with reduced risk of CV death in CHD patients.

METHODS

This retrospective cohort study collected the data of CHD patients from the eight cycles of the Health and Nutrition Examination Survey (NHANES). The included patients were divided into four groups: <60, 60-69, 70-79, and ≥80 bpm. The start of follow-up date was the mobile examination center date, the last follow-up date was December 31, 2015. The average follow-up time was 81.70 months, and the longest follow-up time was 200 months. Competing risk models were developed to evaluate the association between heart rate and CV death, with hazard ratios (HRs) and 95% confidence intervals (CIs) calculated.

RESULTS

A total of 1648 patients with CHD were included in this study. CHD patients at heart rate of <60 (HR, 1.35; 95% CI, 1.34-1.36), 60-69 (HR, 1.05; 95% CI, 1.04-1.06) or ≥80 (HR, 1.39; 95% CI, 1.38-1.41) bpm had a higher risk of CV death than those at heart rate of 70-79 bpm.

CONCLUSIONS

Heart rate of <70 or ≥80 bpm was associated with an elevated risk of CV death among CHD patients. Continuous monitoring of heart rate may help to screen for health risks and offer early interventions to corresponding patients.

Automated Detection of Hypertension Using Continuous Wavelet Transform and a Deep Neural Network with Ballistocardiography Signals

Managing hypertension (HPT) remains a significant challenge for humanity. Despite advancements in blood pressure (BP)-measuring systems and the accessibility of effective and safe anti-hypertensive medicines, HPT is a major public health concern. Headaches, dizziness and fainting are common symptoms of HPT. In HPT patients, normalcy may be observed at one instant and abnormality may prevail during a long duration of 24 h ambulatory BP. This may cause difficulty in identifying patients with HPT, and hence there is a possibility that individuals may be untreated or administered insufficiently. Most importantly, uncontrolled HPT can lead to severe complications (stroke, heart attack, kidney disease, and heart failure), mainly ignoring the signs in nascent stages. HPT in the beginning stages may not present distinct symptoms and may be difficult to diagnose from standard physiological signals. Hence, ballistocardiography (BCG) signal was used in this study to detect HPT automatically. The processed signals from BCG were converted into scalogram images using a continuous wavelet transform (CWT) and were then fed into a 2-D convolutional neural network model (2D-CNN). The model was trained to learn and recognize BCG patterns of healthy controls (HC) and HPT classes. Our proposed model obtained a high classification accuracy of 86.14% with a ten-fold cross-validation (CV) strategy. Hence, this is the first use of a 2D-CNN model (deep-learning algorithm) to detect HPT employing BCG signals.

Prediction of Myocardial Infarction From Patient Features With Machine Learning

This study proposes machine learning-based models to automatically evaluate the severity of myocardial infarction (MI) from physiological, clinical, and paraclinical features. Two types of machine learning models are investigated for the MI assessment: the classification models classify the presence of the infarct and the persistent microvascular obstruction (PMO), and the regression models quantify the Percentage of Infarcted Myocardium (PIM) of patients suspected of having an acute MI during their reception in the emergency department. The ground truth labels for these supervised models are derived from the corresponding Delayed Enhancement MRI (DE-MRI) exams and manual annotations of the myocardium and scar tissues. Experiments were conducted on 150 cases and evaluated with cross-validation. Results showed that for the MI (PMO inclusive) and the PMO (infarct exclusive), the best models obtained respectively a mean error of 0.056 and 0.012 for the quantification, and 88.67 and 77.33% for the classification accuracy of the state of the myocardium. The study of the features' importance also revealed that the troponin value had the strongest correlation to the severity of the MI among the 12 selected features. For the proposal's translational perspective, in cardiac emergencies, qualitative and quantitative analysis can be obtained prior to the achievement of MRI by relying only on conventional tests and patient features, thus, providing an objective reference for further treatment by physicians.

Anomaly Detection Framework for Wearables Data: A Perspective Review on Data Concepts, Data Analysis Algorithms and Prospects

Wearable devices use sensors to evaluate physiological parameters, such as the heart rate, pulse rate, number of steps taken, body fat and diet. The continuous monitoring of physiological parameters offers a potential solution to assess personal healthcare. Identifying outliers or anomalies in heart rates and other features can help identify patterns that can play a significant role in understanding the underlying cause of disease states. Since anomalies are present within the vast amount of data generated by wearable device sensors, identifying anomalies requires accurate automated techniques. Given the clinical significance of anomalies and their impact on diagnosis and treatment, a wide range of detection methods have been proposed to detect anomalies. Much of what is reported herein is based on previously published literature. Clinical studies employing wearable devices are also increasing. In this article, we review the nature of the wearables-associated data and the downstream processing methods for detecting anomalies. In addition, we also review supervised and un-supervised techniques as well as semi-supervised methods that overcome the challenges of missing and un-annotated healthcare data.

Heart Rate Variability and Recurrent Stroke and Myocardial Infarction in Patients With Acute Mild to Moderate Stroke

Objectives: In patients with acute ischemic stroke, reduced heart rate variability (HRV) may indicate poor outcome. We tested whether HRV in the acute phase of stroke is associated with higher rates of mortality, recurrent stroke, myocardial infarction (MI) or functional outcome.

Materials and Methods: Patients with acute mild to moderate ischemic stroke without known atrial fibrillation were prospectively enrolled to the investigator-initiated Heart and Brain interfaces in Acute Ischemic Stroke (HEBRAS) study (NCT 02142413). HRV parameters were assessed during the in-hospital stay using a 10-min section of each patient's ECG recording at day- and nighttime, calculating time and frequency domain HRV parameters. Frequency of a combined endpoint of recurrent stroke, MI or death of any cause and the respective individual events were assessed 12 months after the index stroke. Patients' functional outcome was measured by the modified Rankin Scale (mRS) at 12 months.

Results: We included 308 patients (37% female, median NIHSS = 2 on admission, median age 69 years). Complete follow-up was achieved in 286/308 (93%) patients. At 12 months, 32 (9.5%), 5 (1.7%) and 13 (3.7%) patients had suffered a recurrent stroke, MI or death, respectively. After adjustment for age, sex, stroke severity and vascular risk factors, there was no significant association between HRV and recurrent stroke, MI, death or the combined endpoint. We did not find a significant impact of HRV on a mRS ≥ 2 12 months after the index stroke.

Conclusion: HRV did not predict recurrent vascular events in patients with acute mild to moderate ischemic stroke.

Different acquisition systems for heart rate variability analysis may lead to diverse outcomes

Heart rate variability (HRV) is a relevant physiological variable for the estimation of cardiac autonomic function. Although the gold standard for HRV registration is the electrocardiogram (ECG), several applications (APPs) have been increasingly developed. The evaluation carried out by these devices must be compatible with ECG standards. The aim of this study was to compare the data obtained simultaneously with ECG and APP with chest heart rate transmitters. Fifty-six healthy individuals (28 men and 28 women) were evaluated at rest through a short simultaneous HRV measurement with both devices. Data from both acquisition systems were analyzed separately using their own analysis software and exported and analyzed using a validated software. Signal recordings were compatible between the two acquisition systems (Pearson r=0.99; P<0.0001). Although a high correlation was found for the HRV variables obtained in the time domain (Spearman r=0.99; P<0.0001), the correlation decreased in the frequency domain (Pearson r=0.85; P<0.0001) when two software programs were used. Comparison of the averages of spectral analysis parameters also showed differences when HRV data were analyzed separately in each device for low-frequency (LF) and high-frequency (HF) bands. Although the portability of these mobile devices allows for optimal HRV evaluation, the direct analysis obtained from these devices must be carefully evaluated with respect to frequency domain parameters.

Effect of aerobic exercise on executive function in individuals with methamphetamine use disorder: Modulation by the autonomic nervous system

This study assessed the effects of aerobic exercise on cardiac autonomic nervous system function (based on heart rate variability [HRV]) and executive function among individuals with methamphetamine use disorder (MUD). We further examine the role of autonomic nervous system control in aerobic exercise (assessed via cardiopulmonary fitness) and executive function. A total of 330 individuals with MUD were randomly divided into exercise (n = 165) and control (n = 165) groups, who underwent eight-week aerobic exercise/health education program consisting of five 60 min sessions a week. The outcome measures included cardiopulmonary fitness, HRV time-domain and frequency-domain parameters, and executive function. Our statistical analyses comprised repeated-measures analyses of variance, correlation analyses, and mediation and moderation effect tests. The results indicated that aerobic exercise could simultaneously improve autonomic nervous system function and executive function among individuals with MUD. Moreover, the changes in cardiopulmonary fitness, high frequency HRV, and executive function were positively correlated. HRV did not significantly mediate the relationship between aerobic exercise and executive function; however, it did have a moderating effect, which was eliminated after adjusting for demographic and drug-use covariates. Among the covariates, age was the greatest confounder and was inversely proportional to cardiopulmonary function, HRV, and executive function. Cardiac autonomic nervous system function exerted a moderating, rather than a mediating, effect on the relationship between aerobic exercise and executive function. However, this potential effect was largely influenced by covariates, particularly age.

Relationship between electrocardiogram-based features and personality traits: Machine learning approach

Background

Based on the known relationship between the human emotion and standard surface electrocardiogram (ECG), we explored the relationship between features extracted from standard ECG recorded during relaxation and seven personality traits (Honesty/humility, Emotionality, eXtraversion, Agreeableness, Conscientiousness, Openness, and Disintegration) by using the machine learning (ML) approach which learns from the ECG‐based features and predicts the appropriate personality trait by adopting an automated software algorithm.

Methods

A total of 71 healthy university students participated in the study. For quantification of 62 ECG‐based parameters (heart rate variability, as well as temporal and amplitude‐based parameters) for each ECG record, we used computation procedures together with publicly available data and code. Among 62 parameters, 34 were segregated into separate features according to their diagnostic relevance in clinical practice. To examine the feature influence on personality trait classification and to perform classification, we used random forest ML algorithm.

Results

Classification accuracy when clinically relevant ECG features were employed was high for Disintegration (81.3%) and Honesty/humility (75.0%) and moderate to high for Openness (73.3%) and Conscientiousness (70%), while it was low for Agreeableness (56.3%), eXtraversion (47.1%), and Emotionality (43.8%). When all calculated features were used, the classification accuracies were the same or lower, except for the eXtraversion (52.9%). Correlation analysis for selected features is presented.

Conclusions

Results indicate that clinically relevant features might be applicable for personality traits prediction, although no remarkable differences were found among selected groups of parameters. Physiological associations of established relationships should be further explored.

Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

The human right ventricle is barely monitored during open-chest surgery due to the absence of intraoperative imaging techniques capable of elaborating its complex function. Accordingly, artificial intelligence could not be adopted for this specific task. We recently proposed a video-based approach for the real-time evaluation of the epicardial kinematics to support medical decisions. Here, we employed two supervised machine learning algorithms based on our technique to predict the patients’ outcomes before chest closure. Videos of the beating hearts were acquired before and after pulmonary valve replacement in twelve Tetralogy of Fallot patients and recordings were properly labeled as the “unhealthy” and “healthy” classes. We extracted frequency-domain-related features to train different supervised machine learning models and selected their best characteristics via 10-fold cross-validation and optimization processes. Decision surfaces were built to classify two additional patients having good and unfavorable clinical outcomes. The k-nearest neighbors and support vector machine showed the highest prediction accuracy; the patients’ class was identified with a true positive rate ≥95% and the decision surfaces correctly classified the additional patients in the “healthy” (good outcome) or “unhealthy” (unfavorable outcome) classes. We demonstrated that classifiers employed with our video-based technique may aid cardiac surgeons in decision making before chest closure.

COVID-19 detection with traditional and deep features on cough acoustic signals

The COVID-19 epidemic, in which millions of people suffer, has affected the whole world in a short time. This virus, which has a high rate of transmission, directly affects the respiratory system of people. While symptoms such as difficulty in breathing, cough, and fever are common, hospitalization and fatal consequences can be seen in progressive situations. For this reason, the most important issue in combating the epidemic is to detect COVID-19(+) early and isolate those with COVID-19(+) from other people. In addition to the RT-PCR test, those with COVID-19(+) can be detected with imaging methods. In this study, it was aimed to detect COVID-19(+) patients with cough acoustic data, which is one of the important symptoms. Based on these data, features were obtained from traditional feature extraction methods using empirical mode decomposition (EMD) and discrete wavelet transform (DWT). Deep features were also obtained using pre-trained ResNet50 and pre-trained MobileNet models. Feature selection was applied to all obtained features with the ReliefF algorithm. In this case, the highest 98.4% accuracy and 98.6% F1-score values were obtained by selecting the EMD + DWT features using ReliefF. In another study in which deep features were used, features obtained from ResNet50 and MobileNet using scalogram images were used. For the features selected using the ReliefF algorithm, the highest performance was found with support vector machines-cubic as 97.8% accuracy and 98.0% F1-score. It has been determined that the features obtained by traditional feature approaches show higher performance than deep features. Among the chaotic measurements, the approximate entropy measurement was determined to be the highest distinguishing feature. According to the results, a highly successful study is presented with cough acoustic data that can easily be obtained from mobile and computer-based applications. We anticipate that this study will be useful as a decision support system in this epidemic period, when it is important to correctly identify even one person.

Automated Detection of Hypertension Using Physiological Signals: A Review

Arterial hypertension (HT) is a chronic condition of elevated blood pressure (BP), which may cause increased incidence of cardiovascular disease, stroke, kidney failure and mortality. If the HT is diagnosed early, effective treatment can control the BP and avert adverse outcomes. Physiological signals like electrocardiography (ECG), photoplethysmography (PPG), heart rate variability (HRV), and ballistocardiography (BCG) can be used to monitor health status but are not directly correlated with BP measurements. The manual detection of HT using these physiological signals is time consuming and prone to human errors. Hence, many computer-aided diagnosis systems have been developed. This paper is a systematic review of studies conducted on the automated detection of HT using ECG, HRV, PPG and BCG signals. In this review, we have identified 23 studies out of 250 screened papers, which fulfilled our eligibility criteria. Details of the study methods, physiological signal studied, database used, various nonlinear techniques employed, feature extraction, and diagnostic performance parameters are discussed. The machine learning and deep learning based methods based on ECG and HRV signals have yielded the best performance and can be used for the development of computer-aided diagnosis of HT. This work provides insights that may be useful for the development of wearable for continuous cuffless remote monitoring of BP based on ECG and HRV signals.

Optimal Length of Heart Rate Variability Data and Forecasting Time for Ventricular Fibrillation Prediction Using Machine Learning

Ventricular fibrillation (VF) is a cardiovascular disease that is one of the major causes of mortality worldwide, according to the World Health Organization. Heart rate variability (HRV) is a biomarker that is used for detecting and predicting life-threatening arrhythmias. Predicting the occurrence of VF in advance is important for saving patients from sudden death. We extracted features from seven HRV data lengths to predict the onset of VF before nine different forecast times and observed the prediction accuracies. By using only five features, an artificial neural network classifier was trained and validated based on 10-fold cross-validation. Maximum prediction accuracies of 88.18% and 88.64% were observed at HRV data lengths of 10 and 20 s, respectively, at a forecast time of 0 s. The worst prediction accuracy was recorded at an HRV data length of 70 s and a forecast time of 80 s. Our results showed that features extracted from HRV signals near the VF onset could yield relatively high VF prediction accuracies.

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.

Targeting the Autonomic Nervous System for Risk Stratification, Outcome Prediction and Neuromodulation in Ischemic Stroke

Ischemic stroke is a worldwide major cause of mortality and disability and has high costs in terms of health-related quality of life and expectancy as well as of social healthcare resources. In recent years, starting from the bidirectional relationship between autonomic nervous system (ANS) dysfunction and acute ischemic stroke (AIS), researchers have identified prognostic factors for risk stratification, prognosis of mid-term outcomes and response to recanalization therapy. In particular, the evaluation of the ANS function through the analysis of heart rate variability (HRV) appears to be a promising non-invasive and reliable tool for the management of patients with AIS. Furthermore, preclinical molecular studies on the pathophysiological mechanisms underlying the onset and progression of stroke damage have shown an extensive overlap with the activity of the vagus nerve. Evidence from the application of vagus nerve stimulation (VNS) on animal models of AIS and on patients with chronic ischemic stroke has highlighted the surprising therapeutic possibilities of neuromodulation. Preclinical molecular studies highlighted that the neuroprotective action of VNS results from anti-inflammatory, antioxidant and antiapoptotic mechanisms mediated by α7 nicotinic acetylcholine receptor. Given the proven safety of non-invasive VNS in the subacute phase, the ease of its use and its possible beneficial effect in hemorrhagic stroke as well, human studies with transcutaneous VNS should be less challenging than protocols that involve invasive VNS and could be the proof of concept that neuromodulation represents the very first therapeutic approach in the ultra-early management of stroke.

Multimodal tensor-based method for integrative and continuous patient monitoring during postoperative cardiac care

Patients recovering from cardiovascular surgeries may develop life-threatening complications such as hemodynamic decompensation, making the monitoring of patients for such complications an essential component of postoperative care. However, this need has given rise to an inexorable increase in the number and modalities of data points collected, making it challenging to effectively analyze in real time. While many algorithms exist to assist in monitoring these patients, they often lack accuracy and specificity, leading to alarm fatigue among healthcare practitioners. In this study we propose a multimodal approach that incorporates salient physiological signals and EHR data to predict the onset of hemodynamic decompensation. A retrospective dataset of patients recovering from cardiac surgery was created and used to train predictive models. Advanced signal processing techniques were employed to extract complex features from physiological waveforms, while a novel tensor-based dimensionality reduction method was used to reduce the size of the feature space. These methods were evaluated for predicting the onset of decompensation at varying time intervals, ranging from a half-hour to 12 h prior to a decompensation event. The best performing models achieved AUCs of 0.87 and 0.80 for the half-hour and 12-h intervals respectively. These analyses evince that a multimodal approach can be used to develop clinical decision support systems that predict adverse events several hours in advance.

An hybrid ECG-based deep network for the early identification of high-risk to major cardiovascular events for hypertension patients

BACKGROUND AND OBJECTIVE

As the population becomes older and more overweight, the number of potential high-risk subjects with hypertension continues to increase. ICT technologies can provide valuable support for the early assessment of such cases since the practice of conducting medical examinations for the early recognition of high-risk subjects affected by hypertension is quite difficult, time-consuming, and expensive.

METHODS

This paper presents a novel time series-based approach for the early identification of increases in hypertension to discriminate between cardiovascular high-risk and low-risk hypertensive patients through the analyses of electrocardiographic holter signals.

RESULTS

The experimental results show that the proposed model achieves excellent results in terms of classification accuracy compared with the state-of-the-art. In terms of performances, our model reaches an average accuracy at 98%, Sensitivity and Specificity achieve both an average value at 97%.

CONCLUSION

The analysis of the whole time series shows promising results in terms of highlighting the tiny differences between subjects affected by hypertension.

Analysis of temporal correlation in heart rate variability through maximum entropy principle in a minimal pairwise glassy model

In this work we apply statistical mechanics tools to infer cardiac pathologies over a sample of M patients whose heart rate variability has been recorded via 24 h Holter device and that are divided in different classes according to their clinical status (providing a repository of labelled data). Considering the set of inter-beat interval sequences \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\{\mathbf {r}(i) \} = \{ r_1(i), r_2(i), \ldots , \}$$\end{document}{r(i)}={r1(i),r2(i),…,}, with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$i=1,\ldots ,M$$\end{document}i=1,…,M, we estimate their probability distribution \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P(\mathbf {r})$$\end{document}P(r) exploiting the maximum entropy principle. By setting constraints on the first and on the second moment we obtain an effective pairwise \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(r_n,r_m)$$\end{document}(rn,rm) model, whose parameters are shown to depend on the clinical status of the patient. In order to check this framework, we generate synthetic data from our model and we show that their distribution is in excellent agreement with the one obtained from experimental data. Further, our model can be related to a one-dimensional spin-glass with quenched long-range couplings decaying with the spin–spin distance as a power-law. This allows us to speculate that the 1/f noise typical of heart-rate variability may stem from the interplay between the parasympathetic and orthosympathetic systems.

Analysis of autonomic nervous pattern in hypertension based on short-term heart rate variability

Physiological studies have found that the autonomic nervous system plays an important role in controlling blood pressure values. This paper, based on machine learning approaches, analysed short-term heart rate variability to determine differences in autonomic nervous function between hypertensive patients and normal population. The electrocardiogram (ECG) of hypertensive patients are 137 ECG recordings provided by Smart Health for Assessing the Risk of Events via ECG (SHAREE database). The RR intervals of healthy subjects include the data of 18 subjects from the MIT-BIH Normal Sinus Rhythm Database (nsrdb) and 54 subjects from the Normal Sinus Rhythm RR Interval Database (nsr2db). In this paper, each RR segment includes continuous 500 beats. Seventeen features were extracted to distinguish the hypertensive heart beat rhythms from the normal ones, and Kolmogorov-Smirnov test and sequential backward selection (SBS) were applied to get the best feature combinations. In addition, support vector machine (SVM), k-nearest neighbor (KNN) and random forest (RF) were applied as classifiers in the study. The performance of each classifier was evaluated independently using the leave-one-subject-out validation method. The best predictive model was based on RF and enabled to identify hypertensive patients by five features with an accuracy of 86.44%. The best five HRV features are sample entropy (SampEn), very low frequency spectral powers (VLF), root mean square of successful differences (RMSSD), ratio of low frequency spectral powers and high frequency spectral powers (LF/HF) and vector angle index (VAI). The results of the study show sympathetic overactivity and decreased parasympathetic tone in hypertensive patients.

A primer on artificial intelligence for the paediatric cardiologist

The combination of pediatric cardiology being both a perceptual and a cognitive subspecialty demands a complex decision-making model which makes artificial intelligence a particularly attractive technology with great potential. The prototypical artificial intelligence system would autonomously impute patient data into a collaborative database that stores, syncs, interprets and ultimately classifies the patient's profile to specific disease phenotypes to compare against a large aggregate of shared peer health data and outcomes, the current medical body of literature and ongoing trials to offer morbidity and mortality prediction, drug therapy options targeted to each patient's genetic profile, tailored surgical plans and recommendations for timing of sequential imaging. The focus of this review paper is to offer a primer on artificial intelligence and paediatric cardiology by briefly discussing the history of artificial intelligence in medicine, modern and future applications in adult and paediatric cardiology across selected concentrations, and current barriers to implementation of these technologies.

Detecting cardiac pathologies via machine learning on heart-rate variability time series and related markers

In this paper we develop statistical algorithms to infer possible cardiac pathologies, based on data collected from 24 h Holter recording over a sample of 2829 labelled patients; labels highlight whether a patient is suffering from cardiac pathologies. In the first part of the work we analyze statistically the heart-beat series associated to each patient and we work them out to get a coarse-grained description of heart variability in terms of 49 markers well established in the reference community. These markers are then used as inputs for a multi-layer feed-forward neural network that we train in order to make it able to classify patients. However, before training the network, preliminary operations are in order to check the effective number of markers (via principal component analysis) and to achieve data augmentation (because of the broadness of the input data). With such groundwork, we finally train the network and show that it can classify with high accuracy (at most ~85% successful identifications) patients that are healthy from those displaying atrial fibrillation or congestive heart failure. In the second part of the work, we still start from raw data and we get a classification of pathologies in terms of their related networks: patients are associated to nodes and links are drawn according to a similarity measure between the related heart-beat series. We study the emergent properties of these networks looking for features (e.g., degree, clustering, clique proliferation) able to robustly discriminate between networks built over healthy patients or over patients suffering from cardiac pathologies. We find overall very good agreement among the two paved routes.

Application of a convolutional neural network for predicting the occurrence of ventricular tachyarrhythmia using heart rate variability features

Predicting the occurrence of ventricular tachyarrhythmia (VTA) in advance is a matter of utmost importance for saving the lives of cardiac arrhythmia patients. Machine learning algorithms have been used to predict the occurrence of imminent VTA. In this study, we used a one-dimensional convolutional neural network (1-D CNN) to extract features from heart rate variability (HRV), thereby to predict the onset of VTA. We also compared the prediction performance of our CNN with other machine leaning (ML) algorithms such as an artificial neural network (ANN), a support vector machine (SVM), and a k-nearest neighbor (KNN), which used 11 HRV features extracted using traditional methods. The proposed CNN achieved relatively higher prediction accuracy of 84.6%, while the ANN, SVM, and KNN algorithms obtained prediction accuracies of 73.5%, 67.9%, and 65.9% using 11 HRV features, respectively. Our result showed that the proposed 1-D CNN could improve VTA prediction accuracy by integrating the data cleaning, preprocessing, feature extraction, and prediction.

A computational intelligence tool for the detection of hypertension using empirical mode decomposition

Hypertension (HPT), also known as high blood pressure, is a precursor to heart, brain or kidney diseases. Some symptoms of HPT include headaches, dizziness and fainting. The potential diagnosis of masked hypertension is of specific interest in this study. In masked hypertension (MHPT), the instantaneous blood pressure appears normal, but the 24-h ambulatory blood pressure is abnormal. Hence patients with MHPT are difficult to identify and thus remain untreated or are treated insufficiently. Hence, a computational intelligence tool (CIT) using electrocardiograms (ECG) signals for HPT and possible MHPT detection is proposed in this work. Empirical mode decomposition (EMD) is employed to decompose the pre-processed signals up to five levels. Nonlinear features are extracted from the five intrinsic mode functions (IMFs) thereafter. Student's t-test is subsequently applied to select a set of highly discriminatory features. This feature set is then input to various classifiers, in which, the best accuracy of 97.70% is yielded by the k-nearest neighbor (k-NN) classifier. The developed tool is evaluated by the 10-fold cross validation technique. Our findings suggest that the developed system is useful for diagnostic computational intelligence tool in hospital settings, and that it enables the automatic classification of HPT versus normal ECG signals.