scholarly journals BIOLOGICAL AGE ESTIMATION BASED ON HEART RATE VARIABILITY: A PILOT STUDY

2021 ◽  
Vol 65 (2) ◽  
Author(s):  
Oleksiy Bashkirtsev ◽  
◽  
Vitaliy Sagan ◽  
Vira Gaevska ◽  
Olena Zimba ◽  
...  
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Age Estimation ◽  
Statistical Tests ◽  
Frailty Index ◽  
Reference Method ◽  
Machine Learning Algorithms ◽  
Biological Age ◽  
Distribution Width ◽  
Bivariate Correlation

Introduction. Biomarkers of biological age (BA) are essential for anti-aging research and practice because of their prediction of life expectancy, detection of premature aging, and estimation of anti-ageing programs' effectiveness. The purpose of this study is a clinical validation of the method of biological age estimation based on the analysis of heart rate variability (HRV), artificial intelligence technologies, and biometric monitoring. Methods. In 51 patients who received wellness and rehabilitation services in the medical center "Edem Medical", biological age was determined based on the analysis of HRV and machine learning algorithms. A comparison was made between the proposed method and other known methods of biological age estimation. Biological age estimation by physicians which is based on the Frailty Index was chosen as a reference method. The second method was DNA methylation age (DNAm PhenoAge). This method predicts biological age based on nine parameters of blood (albumin, creatinine, glucose, C-reactive protein, lymphocytes [%], mean corpuscular volume [MCV], red cell distribution width [RDW], alkaline phosphatase, WBC count). Using the «leave one out» technique, an additional algorithm was created for approximating biological age in view of blood test parameters and ECG signals as input data. Morning HRV assessment was performed on empty stomach and after 10-minute rest in horizontal position. ECG was recorded using Mawi Vital multisensor device. The following statistical tests were used to reveal associations between different methods of biological age estimation: 1. bivariate correlation, 2. mean absolute error (MAE), 3. qualitative binary age estimation. Results. All tested methods of BA evaluation were strongly correlated with the reference method (physician-determined age). HRV based approach was superior in comparison with other methods. In 9 out of 10 cases, the qualitative binary age assessment using HRV coincided with the reference method. The HRV method was the most accurate for biological age estimation (3.62 vs 12.62) based on MAE. Conclusion. The method based on HRV is an affordable and convenient approach to biological age estimation. This method offers opportunities for early stratification of individuals at risk of accelerated aging. It combines well with the paradigm of 3 P medicine which is based on Prevention, Prediction, and Personalized approach to each patient

Heart rate variability and red cell distribution width in patients with systolic left heart failure

2013 ◽  
Vol 47 (4) ◽  
pp. 225-229 ◽  
Author(s):  
Firat Özcan ◽  
Osman Turak ◽  
Sedat Avci ◽  
Derya Tok ◽  
Ahmet İşLeyen ◽  
...  
Keyword(s):  
Heart Failure ◽  
Heart Rate ◽  
Heart Rate Variability ◽  
Red Cell Distribution Width ◽  
Red Cell ◽  
Cell Distribution ◽  
Left Heart ◽  
Left Heart Failure ◽  
Distribution Width

Validation of spontaneous assessment of baroreceptor reflex sensitivity and its relation to heart rate variability in the ovine fetus pre- and near-term

2009 ◽  
Vol 87 (9) ◽  
pp. 736-742 ◽  
Author(s):  
Martin G. Frasch ◽  
Thomas Müller ◽  
Mark Szynkaruk ◽  
Matthias Schwab
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Reference Method ◽  
Baroreceptor Reflex ◽  
Vasoactive Drugs ◽  
Sequence Method ◽  
Baroreceptor Reflex Sensitivity ◽  
Ovine Fetus ◽  
Fetal Heart Rate Variability ◽  
Near Term

Assessment of baroreceptor reflex sensitivity (BRS) in the ovine fetus provides insight into autonomic cardiovascular regulation. Currently, assessment of BRS relies on vasoactive drugs, but this approach is limited by feasibility issues and by the nonphysiologic nature of the stimulus. Thus we aimed to validate the method of spontaneous BRS assessment against the reference method of using vasoactive drugs in preterm (0.76 gestation, n = 16) and near-term (0.86 gestation, n = 16) chronically instrumented ovine fetuses. The BRS measures derived from the spontaneous and reference methods correlated at both gestational ages (R = 0.67 ± 0.03). The sequence method of spontaneous BRS measures also correlated both to the root mean square of standard deviations (RMSSD), which is a measure of fetal heart rate variability reflecting vagal modulation (R = 0.69 ± 0.03), and to fetal body weight (R = 0.65 ± 0.03), which is a surrogate for growth trajectory of each fetus. The methodology presented may aid in developing new models to study BRS and cardiovascular control in ovine fetus in the last trimester of pregnancy.

Heart Rate Variability and Biological Age: Implications for Health and Gaming

2013 ◽  
Vol 16 (4) ◽  
pp. 302-308 ◽  
Author(s):  
Carmen V. Russoniello ◽  
Yevgeniy N. Zhirnov ◽  
Vadim I. Pougatchev ◽  
Evgueni N. Gribkov
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Biological Age

scholarly journals Comparison Analysis of Different Time-Scale Heart Rate Variability Signals for Mental Workload Assessment in Human-Robot Interaction

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Shiliang Shao ◽  
Ting Wang ◽  
Yawei Li ◽  
Chunhe Song ◽  
Yihan Jiang ◽  
...  
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Time Scales ◽  
Time Scale ◽  
Mental Workload ◽  
Human Robot Interaction ◽  
Machine Learning Algorithms ◽  
Robot Interaction ◽  
Ecg Signals ◽  
Different Time Scales

Excessive mental workload affects human health and may lead to accidents. This study is motivated by the need to assess mental workload in the process of human-robot interaction, in particular, when the robot performs a dangerous task. In this study, the use of heart rate variability (HRV) signals with different time scales in mental workload assessment was analyzed. A humanoid dual-arm robot that can perform dangerous work was used as a human-robot interaction object. Electrocardiogram (ECG) signals of six subjects were collected in two states: during the task and in a relaxed state. Multiple time-scale (1, 3, and 5 min) HRV signals were extracted from ECG signals. Then, we extracted the same linear and nonlinear features from the HRV signals at different time scales. The performance of machine learning algorithms using the different time-scale HRV signals obtained during the human-robot interaction was evaluated. The results show that for the per-subject case with a 3 min HRV signal length, the K -nearest neighbor classifier achieved the best mental workload classification performance. For the cross-subject case with a 5 min time-scale signal length, the gentle boost classifier achieved the best mental workload classification accuracy. This study provides a novel research idea for using HRV signals to measure mental workload during human-robot interaction.

The effect of principal component analysis in the diagnosis of congestive heart failure via heart rate variability analysis

2021 ◽  
pp. 095441192110368
Author(s):  
Mustafa B Selek ◽  
Bartu Yesilkaya ◽  
Saadet S Egeli ◽  
Yalcin Isler
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Heart Rate ◽  
Principal Component Analysis ◽  
Congestive Heart Failure ◽  
Heart Rate Variability ◽  
Random Forest ◽  
Principal Components ◽  
Principal Component ◽  
Machine Learning Algorithms

In this study, we investigated the effect of principal component analysis (PCA) in congestive heart failure (CHF) diagnosis using various machine learning algorithms from 5-min HRV data. The extracted 59 heart rate variability (HRV) features consist of statistical time-domain measures, frequency-domain measures (power spectral density estimations from Fourier transform and Lomb-Scargle methods), time-frequency HRV measures (Wavelet transform), and nonlinear HRV measures (Poincare plot, symbolic dynamics, detrended fluctuation analysis, and sample entropy). All these HRV features are the classifiers’ inputs. We repeated the study ten times using the first one to the first 10 principal components from PCA instead of all HRV features. Nine different classifiers, namely logistic regression, Naive Bayes, k-nearest neighbors, decision tree, AdaBoost, support vector machines, stochastic gradient descent, random forest, and artificial neuronal network (multilayer perceptron) are examined. The proposed study results in the 100% accuracy, 100% specificity, and 100% sensitivity after utilizing PCA (with the first eight principal components) using the Random Forest classifier where the maximum classifier performances are the 86% accuracy, 79% specificity, and 86% sensitivity before PCA. In conclusion, PCA is beneficial in the diagnosis of patients with CHF. In addition, we experienced the online Python-based visual machine learning tool, Orange, which can implement well-known machine learning algorithms.

scholarly journals Assessing the Quality of Heart Rate Variability Estimated from Wrist and Finger PPG: A Novel Approach Based on Cross-Mapping Method

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3156
Author(s):  
Mimma Nardelli ◽  
Nicola Vanello ◽  
Guenda Galperti ◽  
Alberto Greco ◽  
Enzo Pasquale Scilingo
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Statistical Tests ◽  
Mapping Method ◽  
Signal Quality ◽  
Pulse Rate Variability ◽  
Ecg Signals ◽  
Novel Approach ◽  
Field Sensor

The non-invasiveness of photoplethysmographic (PPG) acquisition systems, together with their cost-effectiveness and easiness of connection with IoT technologies, is opening up to the possibility of their widespread use. For this reason, the study of the reliability of PPG and pulse rate variability (PRV) signal quality has become of great scientific, technological, and commercial interest. In this field, sensor location has been demonstrated to play a crucial role. The goal of this study was to investigate PPG and PRV signal quality acquired from two body locations: finger and wrist. We simultaneously acquired the PPG and electrocardiographic (ECG) signals from sixteen healthy subjects (aged 28.5 ± 3.5, seven females) who followed an experimental protocol of affective stimulation through visual stimuli. Statistical tests demonstrated that PPG signals acquired from the wrist and the finger presented different signal quality indexes (kurtosis and Shannon entropy), with higher values for the wrist-PPG. Then we propose to apply the cross-mapping (CM) approach as a new method to quantify the PRV signal quality. We found that the performance achieved using the two sites was significantly different in all the experimental sessions (p < 0.01), and the PRV dynamics acquired from the finger were the most similar to heart rate variability (HRV) dynamics.

scholarly journals Feature Selection Algorithms Enhance the Accuracy of Frailty Indexes as Measures of Biological Age

2021 ◽  
Author(s):  
Sangkyu Kim ◽  
Jessica Fuselier ◽  
David A Welsh ◽  
Katie E Cherry ◽  
Leann Myers ◽  
...  
Keyword(s):  
Machine Learning ◽  
Proportional Hazards ◽  
Oldest Old ◽  
Frailty Index ◽  
Cox Proportional Hazards ◽  
Independent Study ◽  
Machine Learning Algorithms ◽  
Biological Age ◽  
Biological Aging ◽  
Age Estimates

Abstract Biological age captures some of the variance in life expectancy for which chronological age is not accountable, and it quantifies the heterogeneity in the presentation of the aging phenotype in various individuals. Among the many quantitative measures of biological age, the mathematically uncomplicated frailty/deficit index is simply the proportion of the total health deficits in various health items surveyed in different individuals. We used 3 different statistical methods that are popular in machine learning to select 17–28 health items that together are highly predictive of survival/mortality, from independent study cohorts. From the selected sets, we calculated frailty indexes and Klemera–Doubal’s biological age estimates, and then compared their mortality prediction performance using Cox proportional hazards regression models. Our results indicate that the frailty index outperforms age and Klemera–Doubal’s biological age estimates, especially among the oldest old who are most prone to biological aging-caused mortality. We also showed that a DNA methylation index, which was generated by applying the frailty/deficit index calculation method to 38 CpG sites that were selected using the same machine learning algorithms, can predict mortality even better than the best performing frailty index constructed from health, function, and blood chemistry.

scholarly journals Heart Rate Variability Responses to an Undulating Resistance Training Program in Free-Living Conditions: A Case Study in a Collegiate Athlete

Sports ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 121
Author(s):  
Clifton Holmes ◽  
Stefanie Wind ◽  
Michael Esco
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Resistance Training ◽  
Training Program ◽  
Perceived Exertion ◽  
Smartphone Application ◽  
Resistance Training Program ◽  
Total Load ◽  
Bivariate Correlation

The purpose of this case study was to evaluate the response in heart rate variability via the parasympathetically-mediated metric of the log-transformed root mean square of successive R-R interval differences (lnRMSSD) to weekly variations in total volume-load (TVL) during an 18-week periodized strength training program in a competitive collegiate hockey athlete. The program consisted of three 60–90 min full-body exercise sessions per week with at least 24-h of rest between each session. Daily lnRMSSD measurements were taken immediately after waking using a validated smartphone application and the pulse-wave finger sensor. The weekly lnRMSSD values were calculated as the mean (lnRMSSDMEAN) and the coefficient of variation (lnRMSSDCV). A Pearson’s bivariate correlation of lnRMSSDMEAN and TVL revealed no statistically significant correlation between the two variables; TVL (r = −0.105, p = 0.678). However, significant correlations were found between lnRMSSDCV and both total load (TL) (r = −0.591, p = 0.013) and total volume (TV) (r = 0.765, p < 0.001). Additionally, weekly ratings of perceived exertion (RPE) mean values were statistically significantly correlated to TVL, r = 0.853, p < 0.001. It was concluded that lnRMSSDCV increased or decreased proportionally to an increase or decrease in TVL during the periodized resistance training program with TV being the strongest, independent indicator of these changes.

Sign in / Sign up

Export Citation Format

Share Document