Depression recognition according to heart rate variability using Bayesian Networks

Kuang, Danni; Yang, Rongqian; Chen, Xiuwen; Lao, Guohui; Wu, Fengchun; Xiong, Hui; Lv, Ruixue; Zhang, Lei; Song, Chuanxu; Ou, Shanxing

doi:10.1016/j.jpsychires.2017.09.012

Cited by 41 publications

(24 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The standard deviation of average normal to normal (NN) intervals (SDNN), the root mean square of successive differences (RMSSD), and the percentage of absolute differences in successive NN values greater than 50ms (pNN50) are widely utilized as time-domain HRV indicators. SDNN is known to reflect both sympathetic and parasympathetic functioning, whereas RMSSD and pNN50 are related to parasympathetic functioning ( 20 – 22 ).…”

Section: Heart Rate Variability Parametersmentioning

confidence: 99%

Heart Rate Variability for the Prediction of Treatment Response in Major Depressive Disorder

Choi

Jeon

2020

Front. Psychiatry

View full text Add to dashboard Cite

Major depressive disorder (MDD) is one of the disabling diseases in the worldwide , and known to increase cardiac morbidity and mortality. Therefore, previous studies related heart rate variability (HRV) have been conducted to evaluate and diagnose MDD, and to predict treatment outcomes in patient with MDD. We reviewed extensively on the previous peer-reviewed publications associated with this issue, using Pub-Med. In this review article, we introduce the basic concept of HRV and HRV measures, and present several important findings associated with diagnosis and treatment prediction in MDD with using HRV parameters. Furthermore, we discuss the possible underlying mechanism of this phenomenon, and suggest several considerations for the future research.

show abstract

Section: Heart Rate Variability Parametersmentioning

confidence: 99%

Heart Rate Variability for the Prediction of Treatment Response in Major Depressive Disorder

Choi

Jeon

2020

Front. Psychiatry

View full text Add to dashboard Cite

show abstract

“…Moreover, we investigated the role of parasympathetic dysfunction in subjects with NVAs and found that sympathetic damage may also be a relevant factor for Presence of NVAs. In this study, postural BP change (which represents the extent of sympathetic nerve damage), HRV_deep breathing, and the Valsalva ratio (which represent parasympathetic nerve function) 30,31 were smaller in the group with NVA than in the group without NVAs.…”

Section: Discussionmentioning

confidence: 52%

Nocturnal ventricular arrhythmias are associated with the severity of cardiovascular autonomic neuropathy in type 2 diabetes

Chen

Wang

Zhou

et al. 2019

Journal of Diabetes

View full text Add to dashboard Cite

Background Cardiovascular autonomic neuropathy (CAN) is a risk factor for arrhythmias and adverse cardiovascular events, but the relationship between CAN severity and nocturnal arrhythmias needs to be clarified. This study evaluated the association between nocturnal arrhythmias and CAN severity in patients with type 2 diabetes (T2D). Methods In all, 219 T2D patients were recruited from January 2017 to May 2018. Subjects were classified into no CAN (NCAN), early CAN (ECAN), definite CAN (DCAN), or advanced CAN (ACAN) based on cardiovascular autonomic reflex tests (CARTs). A 24‐hour electrocardiogram was recorded and daytime (0700‐2300 hours) and night‐time (2300‐0700 hours) heartbeats were analyzed separately. Results After adjusting for age, the incidence of ventricular arrhythmias increased with CAN severity at night‐time (18.6%, 29.9%, 36.2%, and 60.0% in the NCAN, ECAN, DCAN, and ACAN groups, respectively; Ptrend = 0.034). Patients with nocturnal ventricular arrhythmias (NVAs) had higher CART scores (2.0 ± 1.0 vs 1.5 ± 0.9; P < 0.001) and lower heart rate variability (HRV) during deep breathing (9.5 ± 5.7 vs 11.6 ± 6.6 b. p. m; P = 0.021), HRV during the Valsalva maneuver (1.2 ± 0.1 vs 1.2 ± 0.2; P = 0.006), and postural blood pressure change (−8.8 ± 15.5 vs −4.1 ± 11.2 mmHg; P = 0.023). Multivariate regression analysis revealed that CAN stage (odds ratio 1.765; 95% confidence interval 1.184‐2.632; P = 0.005) was independently associated with NVAs. Conclusions In T2D, CAN stage was independently associated with the presence of NVAs. Early detection, diagnosis, and treatment of CAN may help predict and prevent adverse cardiovascular events and cardiovascular mortality in diabetes.

show abstract

“…e time domain methods are used to capture the short-, medium-, and long-term variations present in the physiological signals and systems, whereas to capture the dynamics present in different spectra, frequency domain features are computed. ere are literature evidences [32,33] for patients who suffered from different variability dysfunctions [34][35][36][37][38][39][40], including heart rate variability, breathing, depression, pulse variability, insomnia problems, and epilepsy.…”

Section: Bba Linear Methodsmentioning

confidence: 99%

Detecting Congestive Heart Failure by Extracting Multimodal Features and Employing Machine Learning Techniques

Hussain

Awan

Aziz

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

The adaptability of heart to external and internal stimuli is reflected by the heart rate variability (HRV). Reduced HRV can be a predictor of negative cardiovascular outcomes. Based on the nonlinear, nonstationary, and highly complex dynamics of the controlling mechanism of the cardiovascular system, linear HRV measures have limited capability to accurately analyze the underlying dynamics. In this study, we propose an automated system to analyze HRV signals by extracting multimodal features to capture temporal, spectral, and complex dynamics. Robust machine learning techniques, such as support vector machine (SVM) with its kernel (linear, Gaussian, radial base function, and polynomial), decision tree (DT), k-nearest neighbor (KNN), and ensemble classifiers, were employed to evaluate the detection performance. Performance was evaluated in terms of specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC). The highest performance was obtained using SVM linear kernel (TA = 93.1%, AUC = 0.97, 95% CI [lower bound = 0.04, upper bound = 0.89]), followed by ensemble subspace discriminant (TA = 91.4%, AUC = 0.96, 95% CI [lower bound 0.07, upper bound = 0.81]) and SVM medium Gaussian kernel (TA = 90.5%, AUC = 0.95, 95% CI [lower bound = 0.07, upper bound = 0.86]). The results reveal that the proposed approach can provide an effective and computationally efficient tool for automatic detection of congestive heart failure patients.

show abstract

Depression recognition according to heart rate variability using Bayesian Networks

Cited by 41 publications

References 39 publications

Heart Rate Variability for the Prediction of Treatment Response in Major Depressive Disorder

Heart Rate Variability for the Prediction of Treatment Response in Major Depressive Disorder

Nocturnal ventricular arrhythmias are associated with the severity of cardiovascular autonomic neuropathy in type 2 diabetes

Detecting Congestive Heart Failure by Extracting Multimodal Features and Employing Machine Learning Techniques

Contact Info

Product

Resources

About