Statistical and Machine Learning Approach to Study the Smoking Impact on Heart Rate Variability Features

Physiological stress is human body's response to a challenge by multiple systems in the body, in which ANS (Autonomic Nervous System) plays key roles. This paper proposes a stress level evaluation method based on time-frequency domain analysis of HRV (Heart Rate Variability) features combining statistical optimization. The most reliable and efficient indicator to ANS is HRV features obtained from time and frequency domain analysis of R-R intervals recorded during the modified Stroop test. A BP Neural network is utilized to train HRV features selected by t-test and one-way Anova test and classify new samples into four stress level categories i.e. relaxed state, low stress, medium stress and high stress. Weighing factors in classification and number of neurons in hidden layer are considered for optimized network. The proposed method has been validated by experimental results.

Objective:This study aims to evaluate the features of heart rate variability (HRV) and respiratory signals as indices for a driver"s drowsiness and waking status in order to develop the classification model for a driver"s drowsiness and waking status using those features. Background: Driver"s drowsiness is one of the major causal factors for traffic accidents. This study hypothesized that the application of combined bio-signals to monitor the alertness level of drivers would improve the effectiveness of the classification techniques of driver"s drowsiness. Method: The features of three heart rate variability (HRV) measurements including low frequency (LF), high frequency (HF), and LF/HF ratio and two respiratory measurements including peak and rate were acquired by the monotonous car driving simulation experiments using the photoplethysmogram (PPG) and respiration sensors. The experiments were repeated a total of 50 times on five healthy male participants in their 20s to 50s. The classification model was developed by selecting the optimal measurements, applying a binary logistic regression method and performing 3-fold cross validation. Results: The power of LF, HF, and LF/HF ratio, and the respiration peak of drowsiness status were reduced by 38%, 22%, 31%, and 7%, compared to those of waking status, while respiration rate was increased by 3%. The classification sensitivity of the model using both HRV and respiratory features (91.4%) was improved, compared to that of the model using only HRV feature (89.8%) and that using only respiratory feature (83.6%). Conclusion: This study suggests that the classification of driver"s drowsiness and waking status may be improved by utilizing a combination of HRV and respiratory features. Application: The results of this study can be applied to the development of driver"s drowsiness prevention systems.

Heart Rate Variability (HRV) evaluates the autonomic nervous system regulation and can be used as a monitoring tool in conditions such as cardiovascular diseases, neuropathies and sleep staging. It can be extracted from the electrocardiogram (ECG) and the photoplethysmogram (PPG) signals. Typically, the HRV is obtained from the ECG processing. Being the PPG sensor widely used in clinical setups for physiological parameters monitoring such as blood oxygenation and ventilatory rate, the question arises regarding the PPG adequacy for HRV extraction. There is not a consensus regarding the PPG being able to replace the ECG in the HRV estimation. This work aims to be a contribution to this research area by comparing the HRV estimation obtained from simultaneously acquired ECG and PPG signals from forty subjects. A peak detection method is herein introduced based on the Hilbert transform: Hilbert Double Envelope Method (HDEM). Two other peak detector methods were also evaluated: Pan-Tompkins and Wavelet-based. HRV parameters for time, frequency and the non-linear domain were calculated for each algorithm and the Pearson correlation, T-test and RMSE were evaluated. The HDEM algorithm showed the best overall results with a sensitivity of 99.07% and 99.45% for the ECG and the PPG signals, respectively. For this algorithm, a high correlation and no significant differences were found between HRV features and the gold standard, for the ECG and PPG signals. The results show that the PPG is a suitable alternative to the ECG for HRV feature extraction.

Purpose: Heart rate variability (HRV) has been used for decades as a tool for measuring systemic health through the autonomic nervous system (ANS). The purpose of this paper was to examine the literature on HRV and to investigate its use in the long COVID (LC) population. Summary of Key Points: Measurement devices vary significantly in their validity and reliability when compared with the gold standard of electrocardiogram (ECG). Wrist and hand devices typically demonstrate diminished validity for capturing HRV signal, while chest strap devices often exhibit high reliability and validity. Lack of transparency in third-party software used to clean and analyze HRV data makes assessment for accuracy problematic. This is of particular concern when single beat miscalculations can result in significantly dissimilar output. The conditions under which HRV data are collected, such as natural or paced breathing, activity intensity, and patient position, can dramatically affect HRV readings. While some individual HRV metrics have consistently been shown to reflect certain components of the ANS, such as high-frequency power as a measure of parasympathetic function, the meaning of other metrics is less clear. Recommendations for Clinical Practice: Heart rate variability can be an extraordinarily valuable tool to measure systemic function. However, it is recommended that clinicians be judicious in the interpretation of HRV, considering inconsistencies in presentation. This is particularly true in LC, where individual HRV varies greatly. In all populations, clinicians should consider using valid devices to assess trends in HRV values over time, along with consideration of unique physical conditions.

The autonomic nervous system dysfunction has been reported in up to 76% of stroke patients 7 days after an acute stroke. Heart rate variability (HRV) is one of the important indicators reflecting the balance of sympathetic and parasympathetic nerves. Therefore, we performed a systematic literature review of existing literature on the association between heart rate variability and the different types of stroke. We included studies published in the last 32 years (1990 to 2022). The electronic databases MEDLINE and PubMed were searched. We selected the research that met the inclusion or exclusion criteria. A narrative synthesis was performed. This review aimed to summarize evidence regarding the potential mechanism of heart rate variability among patients after stroke. In addition, the association of clinical characteristics of heart rate variability and stroke has been depicted. The review further discussed the relationship between post-stroke infection and heart rate variability, which could assist in curbing clinical infection in patients with stroke. HRVas a noninvasive clinical monitoring tool can quantitatively assess the changes in autonomic nervous system activity and further predict the outcome of stroke. HRV could play an important role in guiding the clinical practice for autonomic nervous system disorder after stroke.

Early and noninvasive identification of heart failure progression is an important adjunct to successful and timely intervention. Severity of heart failure (HF) was assessed by Left Ventricular Ejection Fraction (LVEF). In this paper, we explore the circadian (24-hour) heart rate variability (HRV) features from ''normal" (EF >50%), "at-risk" (EF <40%), and "border-line" (40% ≤ EF ≤ 50%) patient data to determine whether HRV features can predict the stage of heart failure. All coronary artery disease (CAD) 24-hour circadian heart rate data were fitted by a cosinor analysis algorithm. Hourly HRV features from time- and frequency-domains were then extracted from all 24-hour patient data. A one-way ANOVA test was performed followed by a Tukey post-hoc multiple comparison test to investigate the differences among the three groups. The results showed a statistically significant difference between the three groups when using the normalized high frequency (HF Norm), low frequency peak (LF Peak), and the normalized very-low frequency (VLF Norm) for the 05:00-06:00 and 18:00-19:00 time periods. These results highlight a possible link between the circadian variation of sympathetic and parasympathetic nervous system activity and LVEF for CAD patients. The results could be useful in differentiating the various degrees of LVEF by using only noninvasive HRV features derived over a 24-hour period.Clinical relevance- The proposed method could be clinically useful to estimate the extent of LVEF associated with the severity of heart failure by recording the circadian variation of the heart rate in CAD patients. However, further clinical trials on a larger cohort of patients and controls are required.

Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features

Fatigue is important in aviation because the risks associated with fatigue pose a threat to many people. The purpose of this study is to investigate the possibility of using a wearable ECG device to detect mental fatigue in pilots. 22 healthy individuals were recruited from Beihang University and each subject wore a Polar H10 heart rate band with a Polar IGNITE sports watch to record heart rate variability (HRV) data. To stimulate the fatigue state, each subject performed a simulated flight experiment of 1h and the number of blinks was recorded by the face recognition method as a label for fatigue. HRV data and blink frequency were collected every 5 minutes throughout the experiment. After feature selection, four HRV indicators SDNN, LF_HF, LF and VLF were extracted for subsequent analysis. Five machine learning algorithms: support vector machine (SVM), Random Forest, AdaBoost, K-nearest neighbor (KNN), Naïve Bayes (NB) were used to build a classifier for automatic detection of pilot fatigue. Naïve Bayes (NB) had the best performance and had an average CV F1 score of 0.9065 on the training set and 0.9250 on the test set.

Prediction of GABA receptor antagonist-induced convulsion in cynomolgus monkeys by combining machine learning and heart rate variability analysis

Within the framework of the research into pathological conditions and syndromes associated with undifferentiated connective tissue dysplasia (UCTD), an emphasis needs to be placed on the changes in heart rhythm. In puberty, the severity of neurovegetative disorders caused by the presence of UCTD might increase manifold. The features of heart rate variability (HRV) in pubertal children against the background of UCTD have been studied insufficiently and require more detailed analysis. This study aims to assess heart rate variability and tone of the autonomic nervous system (ANS) in puberty-aged children with UCTD. Two groups of children were examined, with methods including electrocardiography and cardiointervalography. The main group consisted of 36 puberty-aged children with UCTD, the control group consisted of 30 healthy children. ANS tone was assessed based on the HRV. In the control group of children aged 11, the value of variation range (VR) was 0.18±0.4, mode amplitude (MA) 35.2±2.4, stress index (IN) 72.8±4.3, which corresponds to the state of vegetative balance. As the puberty progresses, the state of eutonia is replaced by the activation of the sympathetic division of the ANS, which becomes most pronounced at the age of 13 years. In the control group of children aged 13, the value of VR was 0.08±0.02, MA 61.7±2.1, SI 210.6±8.6, which corresponds to moderate sympathicotonia. By the end of puberty, in healthy children, the severity of sympathetic activation begins to decrease, and at the age of 15 years, vegetative balance is again observed. However, this pattern is violated in children with UCTD. Upon entering puberty, moderate activation of the sympathetic division of the ANS is already observed in children with UCTD. At the age of 11 years in this group, the value of VR is 0.06±0.02, MA 72.4±3.1, SI 211.2±8.6. At the age of 13, pronounced sympathicotonia is observed, which is confirmed by the values of VR - 0.04±0.01, MA 80.2±4.3 and SI 34.3±14.7. By the end of puberty in children with UCTD, in contrast to the control group, the analyzed parameters indicate not an equilibrium of the ANS, but the predominance of parasympathetic activation. The research provides an insight into heart rate variability in puberty-aged children with UCTD. It was established that healthy children enter puberty in a state of equilibrium of the autonomic nervous system, which in the middle of puberty is replaced by moderate sympathicotonia, and then returns to its original values. Children with the presence of UCTD enter puberty with moderately pronounced sympathicotonia, which gradually increases to pronounced values and is replaced by moderate vagotonia. Funding Acknowledgement Type of funding sources: None.

Background: The hallmarks of fibromyalgia (FM), a chronic pain syndrome, include tiredness, cognitive impairment, and extensive musculoskeletal discomfort. An imbalance in the autonomic nerve system may play a major role in its pathogenesis, leading to changes in visceral and cardiovascular control, according to mounting evidence. Heart rate variability (HRV) is a sensitive, non-invasive measure of sympathovagal balance and autonomic regulation. Aims and Objectives: The purpose of this study was to compare HRV indices between FM patients and age- and sex-matched healthy controls in order to evaluate autonomic dysfunction in FM utilizing short-term HRV analysis. Materials and Methods: Thirty patients with FM diagnosed using the 2016 updated American College of Rheumatology’s criteria, and 30 healthy volunteers were included in this cross-sectional research. In accordance with Task Force standards, standardized 5-min rested electrocardiograms were obtained, and HRV characteristics were examined in the time domains and frequency domains. The data were analyzed using Statistical Package for the Social Sciences 26.0, with t-tests for between-group comparisons. P&lt;0.05 was considered statistically significant. Results: When compared to healthy controls, FM patients showed a significant decrease in HRV indicators. The RMSSD was 19.3±7.2 ms compared to 38.7 ± 10.1 ms (P&lt;0.001*), and the mean standard deviation of NN intervals (SDNN) was 22.6±8.1 ms rather than 41.2±9.4 ms (P&lt;0.001*). Frequency-domain measurements revealed a higher low-frequency/high-frequency (LF/HF) ratio (1.72±0.65 vs. 1.15±0.48, P=0.003*), indicating greater sympathetic dominance and decreased parasympathetic modulation, along with significantly lower LF power (315±120 ms2 vs. 520±160 ms2, P&lt;0.001*) and HF power (210±98 ms2 vs. 450±142 ms2, P&lt;0.001*). Conclusion: Significantly decreased HRV in both the temporal and frequency domains is a symptom of substantial autonomic dysfunction linked to FM. The concept of impaired central autonomic control in FM is supported by these data, which highlight a condition of sympathovagal imbalance. For determining the severity of an illness and tracking treatment plans meant to restore autonomic balance, HRV may be a helpful biomarker.

Smoking impacts the pattern of heart rate variability (HRV); HRV therefore acts as a predictor of cardiac diseases (CD). In this study, to predict CD non-invasively among smokers, ensemble machine learning methods have been used. A single model is created based on ensemble voting classifier with a combined boosting technique to improve the accuracy of predictive model. The final ensemble model shows an accuracy of 95.20%, precision of 97.27%, sensitivity of 92.35%, specificity of 98.07%, F1 score of 0.95, AUC of 0.961, MCE of 0.0479, kappa statistics value of 0.9041, and MSE of 0.2189. The obtained accuracy by using the proposed method is the highest value achieved so far for the prediction of CD among smokers using HRV data.

High-risk working conditions in construction, such as working at height, may elicit elevated mental stress in workers and pose significant safety challenges. This study aims to physiologically assess construction workers' mental stress under high-risk working conditions using heart rate variability (HRV) features derived from electrocardiograph (ECG) signals. An experimental study in the field was conducted, where inexperienced scaffolding workers' (n = 20) ECG signals were collected when working at three different heights corresponding to low, medium, and high levels of mental stress. Supervised machine learning algorithms, including Support Vector Machine (SVM), KNearest Neighbor (KNN), Linear Discriminant Analysis (LDA), and Random Forest (RF), were applied for model development. The results show that the HRV features obtained good prediction accuracy. The classification accuracy is up to 85.00% between low and medium stress levels, 92.50% for differentiating low and high stress levels, and 87.50% for classifying medium and high stress levels. These findings demonstrate the potential of ECG-derived HRV features for differentiating the mental stress responses of construction workers under high-risk working conditions and provide empirical evidence supporting the feasibility of physiological monitoring of workers' mental stress in real construction environments.

Heart rate variability (HRV) analysis has increasingly become a promising marker for the assessment of the autonomic nervous system. The easy derivation of the HRV has determined its popularity, being successfully used in many research and clinical studies. However, the conventional HRV analysis is performed on 5 min ECG recordings which in e-health monitoring might be unsuitable, due to real-time requirements. Thus, the aim of this study is to evaluate the association between the raw ECG heartbeats and the HRV features to further reduce the number of heart beats required for the HRV estimation enabling real time monitoring. We propose a deep learning based system, specifically a recurrent neural network for the inference of two time domain HRV features: AVNN (the average of all the NN intervals) and IHR (instantaneous heart rate). The obtained results suggest that both AVNN and IHR can be accurately inferred from a shorter ECG interval of about 1 min, with a mean error of <5% of the computed HRV features.

Acute mountain sickness (AMS) is a common condition among non-acclimatized individuals ascending to high altitude. Exercise, a characteristic feature of hiking and mountaineering, has been suggested to exacerbate AMS prevalence and to cause modifications of the autonomic nervous system. A reduction of the heart rate variability (HRV) is a common finding during acute hypoxia, however characteristics of HRV during exercise in subjects suffering from AMS are unknown. Therefore, the aim of the present study was to investigate the effects of acute normobaric hypoxia (FiO2=11.0% ≙ 5 500 m) at rest (PHE) and during exercise (AHE) on the cardiac autonomic function and the development of AMS in 20 healthy, male individuals. HRV recordings were performed during normoxia and after 2, 4, 6 and 8 h in hypoxia during PHE and AHE, respectively. AMS was assessed using the Lake Louise Score. During PHE 50% of participants developed AMS and 70% during AHE (p=0.22). The analysis of HRV data showed a significant reduction of total power (TP), high frequency (HF) and low frequency (LF) components and an increase of the LF:HF ratio during PHE, however without further modification during AHE. Exercise did not increase AMS prevalence or severity, but increased "non-gastrointestinal" symptoms including headache, fatigue and dizziness. HRV indices were not related to the overall incidence of AMS or the development of "non-gastrointestinal" symptoms but we detected significant correlations between gastrointestinal complaints and HRV components. Thus, we suggest that the cardiac autonomic modulation during acute normobaric hypoxia does not play an important role in the development of AMS, but seems to be related to gastrointestinal complaints at high altitude. However, the influence of moderate exercise on HRV and AMS is minor, only "non-GI" symptoms seem to be exacerbated when exercise is applied.