Applying learning algorithms to extract anxiety levels using the heart rate variability measure

Abstract Objective To assess the role of the heart rate variability (HRV) in the relationship between prenatal anxiety exposure and subsequent child anxiety levels. Methods A longitudinal study of mother–child dyads (subsample of 89) measured maternal anxiety during the second trimester of pregnancy (self-reported via STAI-S) and subsequent child anxiety (maternal-reported via BASC-3) and baseline autonomic physiological measures (high and low frequency band of HRV power spectrum) at 5-years-old. Mediation analysis was conducted to test whether child high and/or low frequency HRV mediates the relationship between prenatal anxiety and child anxiety. Results Prenatal anxiety predicted child anxiety (β = 0.137, p = 0.004) and high frequency HRV (β = −0.009, p < 0.001), but not low frequency HRV (β = −0.002, p = 0.231). Mediation analysis using bootstrapping procedure revealed that high frequency HRV (β = 0.044, 95% CI [0.007, 0.085]), but not low frequency HRV (β = 0.0117, 95% CI [−0.007, 0.047]), mediated the relationship between prenatal anxiety and child anxiety. After controlling for high frequency HRV, prenatal anxiety was no longer associated with child anxiety (β = 0.0753, p = 0.148). Conclusion Results indicate that in-utero exposure to maternal anxiety influences the child’s high frequency but not low frequency HRV. Importantly, changes in only high frequency HRV from prenatal anxiety is driving the relationship between prenatal anxiety and child anxiety levels, indicating that maternal anxiety during pregnancy affects the development of the autonomic nervous system with long term effects on child emotional regulation. The results suggest that the high frequency portion of the HRV power spectrum should be assessed in a multidimensional model of fetal programming and subsequent mental health risk of the child.

Download Full-text

290 Depression, anxiety, and resting heart rate variability during sleep in a sample of active duty service members

SLEEP ◽

10.1093/sleep/zsab072.289 ◽

2021 ◽

Vol 44 (Supplement_2) ◽

pp. A116-A116

Author(s):

Nita Shattuck ◽

Panagiotis Matsangas ◽

Joshua Boyle

Keyword(s):

Heart Rate ◽

Heart Rate Variability ◽

Trait Anxiety ◽

State Anxiety ◽

Active Duty ◽

Service Members ◽

Resting Heart Rate ◽

Depression And Anxiety ◽

Anxiety Levels ◽

Resting Heart Rate Variability

Abstract Introduction Depression and anxiety are among the most prevalent mental health outcomes in the military population with rates ranging between 11% and 15% in Army active duty service members (ADSMs). Oftentimes both maladies are comorbid with insomnia and other sleep-related disorders. We explored the association between self-reported depression and anxiety levels and resting heart rate variability (HRV) metrics during sleep using a wearable device, the Oura ring. Methods We conducted a longitudinal, naturalistic assessment of fit-for-duty ADSMs (N=44; 21-40 years of age, 38 males) attending the Naval Postgraduate School. Depression was assessed by the Beck Depression Inventory; anxiety was assessed by the State-Trait Anxiety Inventory. HRV (average nightly HRV and average nightly HRVmaximal during sleep) was assessed with the Oura devices during a period of MD=8 days (range 8–18). Results The median BDI score was 5.50 (IQR=9.50; range 0–23). Most participants had minimal depression (36, 81.8%) with seven (16.9%) having mild depression and one (2.27%) moderate depression. The median state anxiety score was 29.5 (IQR=16.8; range 20 – 56), whereas the median trait anxiety score was 31.0 (IQR=15.8; range 21–56). Correlation analysis (Spearman’s rho) showed that lower depression and anxiety scores were associated with higher nightly HRV during sleep. Specifically, average nightly HRV was correlated with BDI scores (rho=-0.384, p=0.010), state anxiety scores (rho=-0.343, p=0.023), and trait anxiety (rho=-0.356, p=0.018). Average nightly HRVmaximal was negatively correlated with BDI scores (rho=-0.435, p=0.003), state anxiety scores (rho=-0.339, p=0.024), and trait anxiety (rho=-0.339, p=0.025). Conclusion Our findings suggest that HRV during sleep is associated with self-reported depression and anxiety levels in this sample of ADSMs. Further research is needed to assess the utility and limitations of the Oura devices to collect data in field settings. Support (if any):

Download Full-text

A comparative study of anxiety levels and its relation with heart rate variability (HRV) indices in adolescents with type 1 diabetes mellitus.

Medeniyet Medical Journal ◽

10.5222/mmj.2018.13334 ◽

2018 ◽

Author(s):

Musharaf Bashir ◽

Himani Ahluwalia ◽

Sheikh Imran Sayeed ◽

Raj Kapoor

Keyword(s):

Diabetes Mellitus ◽

Heart Rate ◽

Heart Rate Variability ◽

Type 1 Diabetes ◽

Comparative Study ◽

Type 1 Diabetes Mellitus ◽

Anxiety Levels

Download Full-text

Psychological training in progressive muscular relaxation: Effects on anxiety levels and heart rate variability (HRV)

PsycEXTRA Dataset ◽

10.1037/e548052012-565 ◽

2007 ◽

Author(s):

M. Ocana ◽

E. Parrado ◽

M. Valero ◽

J. Ramos ◽

M. A. Garcia ◽

...

Keyword(s):

Heart Rate ◽

Heart Rate Variability ◽

Muscular Relaxation ◽

Relaxation Effects ◽

Psychological Training ◽

Anxiety Levels

Download Full-text

Abstract P93: Heart Rate Variability Analysis using Wavelet Transform to Predict Hemorrhage Severity

Circulation ◽

10.1161/circ.118.suppl_18.s_1465-b ◽

2008 ◽

Vol 118 (suppl_18) ◽

Author(s):

Soo-Yeon Ji ◽

Kevin Ward ◽

Kathy Ryan ◽

Kayvan Najarian

Keyword(s):

Machine Learning ◽

Heart Rate ◽

Heart Rate Variability ◽

Blood Loss ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Human Model ◽

Discrete Wavelet ◽

Lower Body ◽

Volume Loss

Introduction: The Pulse Initiative on resuscitation identified the need to develop biosensing for detection of critical limitations of blood flow. The ability to rapidly detect the severity of hemorrhage based on heart rate has been limited. Use of heart rate variability (HRV) is problematic. We used a number of new defined ECG features based on discrete wavelet transformation (DWT) that may be used to estimate blood loss severity. The features are defined based on the energy of detail coefficients of Daubecies DWT. Methods: The performance of DWT was tested using ECG data from a human model of hemorrhage using lower body negative pressure (LBNP). LBNP consisted of a 5-minute rest period (0 mm Hg) followed by 5 minutes of chamber decompression of the lower body to −15, −30, −45, and −60 mm Hg and additional increments of −10 mm Hg every 5 minutes until the onset of cardiovascular collapse. These levels were divided into 3 classes (mild: −15 to −30 mmHg; moderate: −45 to −60 mmHg; severe: over −60 mmHg). These levels correspond to estimated blood losses of 400 –550 cc, 500 –1000 cc and greater than 1000 cc respectively. The ECG DWT features of subjects were used for classification of each ECG recording during volume loss levels. Before classification in order to eliminate redundancy among the features, principal component analysis is applied to the feature set. Machine learning algorithms (SVM, AdaBoost, C4.5) were then applied to analyze the processed features and predict the severity of blood loss. Results: A 219 sample set was used to classify groups by using machine learning algorithms with 10-fold cross validation. C4.5 outperformed other algorithms with a prediction accuracy of 74.4%. The average precision and recall (sensitivity) for the three classes were 77.4% and 76.1%, respectively. In particular, 30 out of 39 cases in the severe class were correctly classified by C4.5. These results required sampling rates of only 125 Hz. Conclusion: This is the first reported use of an ECG analysis method to classify volume loss. The DWT method described may have the ability to rapidly determine the degree of volume loss from hemorrhage providing for more rapid triage and decision making. This may be particularly helpful for remote monitoring of war fighters or for mass casualty care.

Download Full-text