Non-linear feature extraction from HRV signal for mortality prediction of ICU cardiovascular patient

Multifractal Heart Rate Value Analysis: A Novel Approach for Diabetic Neuropathy Diagnosis

Type 2 diabetes mellitus (T2DM) is characterized by several complications, such as retinopathy, renal failure, cardiovascular disease, and diabetic neuropathy. Among these, neuropathy is the most severe complication, due to the challenging nature of its early detection. The linear Hearth Rate Variability (HRV) analysis is the most common diagnosis technique for diabetic neuropathy, and it is characterized by the determination of the sympathetic-parasympathetic balance on the peripheral nerves through a linear analysis of the tachogram obtained using photoplethysmography. We aimed to perform a multifractal analysis to identify autonomic neuropathy, which was not yet manifest and not detectable with the linear HRV analysis. We enrolled 10 healthy controls, 10 T2DM-diagnosed patients with not-full-blown neuropathy, and 10 T2DM diagnosed patients with full-blown neuropathy. The tachograms for the HRV analysis were obtained using finger photoplethysmography and a linear and/or multifractal analysis was performed. Our preliminary results showed that the linear analysis could effectively differentiate between healthy patients and T2DM patients with full-blown neuropathy; nevertheless, no differences were revealed comparing the full-blown to not-full-blown neuropathic diabetic patients. Conversely, the multifractal HRV analysis was effective for discriminating between full-blown and not-full-blown neuropathic T2DM patients. The multifractal analysis can represent a powerful strategy to determine neuropathic onset, even without clinical diagnostic evidence.

Uncertainties in the Analysis of Heart Rate Variability: A Systematic Review

Heart rate variability (HRV) is an important metric with a variety of applications in clinical situations such as cardiovascular diseases, diabetes mellitus, and mental health. HRV data can be potentially obtained from electrocardiography and photoplethysmography signals, then computational techniques such as signal filtering and data segmentation are used to process the sampled data for calculating HRV measures. However, uncertainties arising from data acquisition, computational models, and physiological factors can lead to degraded signal quality and affect HRV analysis. Therefore, it is crucial to address these uncertainties and develop advanced models for HRV analysis. Although several reviews of HRV analysis exist, they primarily focus on clinical applications, trends in HRV methods, or specific aspects of uncertainties such as measurement noise. This paper provides a comprehensive review of uncertainties in HRV analysis, quantifies their impacts, and outlines potential solutions. To the best of our knowledge, this is the first study that presents a holistic review of uncertainties in HRV methods and quantifies their impacts on HRV measures from an engineer's perspective. This review is essential for developing robust and reliable models, and could serve as a valuable future reference in the field, particularly for dealing with uncertainties in HRV analysis.

Epileptic Seizure Detection Using Geometric Features Extracted from SODP Shape of EEG Signals and AsyLnCPSO-GA

Epilepsy is a neurological disorder that is characterized by transient and unexpected electrical disturbance of the brain. Seizure detection by electroencephalogram (EEG) is associated with the primary interest of the evaluation and auxiliary diagnosis of epileptic patients. The aim of this study is to establish a hybrid model with improved particle swarm optimization (PSO) and a genetic algorithm (GA) to determine the optimal combination of features for epileptic seizure detection. First, the second-order difference plot (SODP) method was applied, and ten geometric features of epileptic EEG signals were derived in each frequency band (δ, θ, α and β), forming a high-dimensional feature vector. Secondly, an optimization algorithm, AsyLnCPSO-GA, combining a modified PSO with asynchronous learning factor (AsyLnCPSO) and the genetic algorithm (GA) was proposed for feature selection. Finally, the feature combinations were fed to a naïve Bayesian classifier for epileptic seizure and seizure-free identification. The method proposed in this paper achieved 95.35% classification accuracy with a tenfold cross-validation strategy when the interfrequency bands were crossed, serving as an effective method for epilepsy detection, which could help clinicians to expeditiously diagnose epilepsy based on SODP analysis and an optimization algorithm for feature selection.

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.

Bidimensional and Tridimensional Poincaré Maps in Cardiology: A Multiclass Machine Learning Study

Heart rate is a nonstationary signal and its variation may contain indicators of current disease or warnings about impending cardiac diseases. Hence, heart rate variation analysis has become a noninvasive tool to further study the activities of the autonomic nervous system. In this scenario, the Poincaré plot analysis has proven to be a valuable tool to support cardiac diseases diagnosis. The study’s aim is a preliminary exploration of the feasibility of machine learning to classify subjects belonging to five cardiac states (healthy, hypertension, myocardial infarction, congestive heart failure and heart transplanted) using ten unconventional quantitative parameters extracted from bidimensional and three-dimensional Poincaré maps. Knime Analytic Platform was used to implement several machine learning algorithms: Gradient Boosting, Adaptive Boosting, k-Nearest Neighbor and Naïve Bayes. Accuracy, sensitivity and specificity were computed to assess the performances of the predictive models using the leave-one-out cross-validation. The Synthetic Minority Oversampling technique was previously performed for data augmentation considering the small size of the dataset and the number of features. A feature importance, ranked on the basis of the Information Gain values, was computed. Preliminarily, a univariate statistical analysis was performed through one-way Kruskal Wallis plus post-hoc for all the features. Machine learning analysis achieved interesting results in terms of evaluation metrics, such as demonstrated by Adaptive Boosting and k-Nearest Neighbor (accuracies greater than 90%). Gradient Boosting and k-Nearest Neighbor reached even 100% score in sensitivity and specificity, respectively. The most important features according to information gain are in line with the results obtained from the statistical analysis confirming their predictive power. The study shows the proposed combination of unconventional features extracted from Poincaré maps and well-known machine learning algorithms represents a valuable approach to automatically classify patients with different cardiac diseases. Future investigations on enriched datasets will further confirm the potential application of this methodology in diagnostic.

Effectiveness of Different Physiotherapy Protocols in Children in the Intensive Care Unit: A Randomized Clinical Trial

PURPOSE

This study aimed to investigate the effectiveness of different physical therapy protocols on the autonomic modulation of heart rate, time of invasive mechanical ventilation (IMV), and length of hospital stay.

METHODS

This was a randomized clinical study with 20 children on IMV in an intensive care unit (ICU), between July 2018 and September 2019. The control group (n = 10) performed the hospital's physical therapy protocol and the experimental group (n = 10) performed the physical therapy protocol based on physical exercise.

RESULTS

Higher values of heart rate variability were found in the experimental group, both in individual and intergroup analyses. There was a significant reduction in the time of IMV and ICU stay.

CONCLUSION

There was an improvement in heart rate variability, reduced time on mechanical ventilation and length of stay in the ICU in individuals who performed the study protocol.

Atrial Fibrillation Prediction from Critically Ill Sepsis Patients

Sepsis is defined by life-threatening organ dysfunction during infection and is the leading cause of death in hospitals. During sepsis, there is a high risk that new onset of atrial fibrillation (AF) can occur, which is associated with significant morbidity and mortality. Consequently, early prediction of AF during sepsis would allow testing of interventions in the intensive care unit (ICU) to prevent AF and its severe complications. In this paper, we present a novel automated AF prediction algorithm for critically ill sepsis patients using electrocardiogram (ECG) signals. From the heart rate signal collected from 5-min ECG, feature extraction is performed using the traditional time, frequency, and nonlinear domain methods. Moreover, variable frequency complex demodulation and tunable Q-factor wavelet-transform-based time-frequency methods are applied to extract novel features from the heart rate signal. Using a selected feature subset, several machine learning classifiers, including support vector machine (SVM) and random forest (RF), were trained using only the 2001 Computers in Cardiology data set. For testing the proposed method, 50 critically ill ICU subjects from the Medical Information Mart for Intensive Care (MIMIC) III database were used in this study. Using distinct and independent testing data from MIMIC III, the SVM achieved 80% sensitivity, 100% specificity, 90% accuracy, 100% positive predictive value, and 83.33% negative predictive value for predicting AF immediately prior to the onset of AF, while the RF achieved 88% AF prediction accuracy. When we analyzed how much in advance we can predict AF events in critically ill sepsis patients, the algorithm achieved 80% accuracy for predicting AF events 10 min early. Our algorithm outperformed a state-of-the-art method for predicting AF in ICU patients, further demonstrating the efficacy of our proposed method. The annotations of patients' AF transition information will be made publicly available for other investigators. Our algorithm to predict AF onset is applicable for any ECG modality including patch electrodes and wearables, including Holter, loop recorder, and implantable devices.

The prediction of mortality influential variables in an intensive care unit: a case study

The intensive care units (ICUs) are among the most expensive and essential parts of all hospitals for extremely ill patients. This study aims to predict mortality and explore the crucial factors affecting it. Generally, in the health care systems, having a fast and precise ICU mortality prediction for patients plays a key role in care quality, resulting in reduced costs and improved survival chances of the patients. In this study, we used a medical dataset, including patients' demographic details, underlying diseases, laboratory disorder, and LOS. Since accurate estimates are required to have optimal results, various data pre-processings as the initial steps are used here. Besides, machine learning models are employed to predict the risk of mortality ICU discharge. For AdaBoost model, these measures are considered AUC= 0.966, sensitivity (recall) = 87.88%, Kappa=0.859, F-measure = 89.23% making it, AdaBoost, accounts for the highest rate. Our model outperforms other comparison models by using various scenarios of data processing. The obtained results demonstrate that the high mortality can be caused by underlying diseases such as diabetes mellitus and high blood pressure, moderate Pulmonary Embolism Wells Score risk, platelet blood count less than 100000 (mcl), hypertension (HTN), high level of Bilirubin, smoking, and GCS level between 6 and 9.

Heart rhythm complexity as predictors for the prognosis of end-stage renal disease patients undergoing hemodialysis

BACKGROUND

Heart rhythm complexity, a measure of heart rate dynamics and a risk predictor in various clinical diseases, has not been systematically studied in patients with end-stage renal disease. The aim of this study is to investigate the heart rhythm complexity and its prognostic value for mortality in end-stage renal disease patients undergoing hemodialysis.

METHODS

To assess heart rhythm complexity and conventional heart rate variability measures, 4-h continuous electrocardiography for a retrospective cohort of 202 ostensibly healthy control subjects and 51 hemodialysis patients with end-stage renal disease were analyzed. Heart rhythm complexity was quantified by the complexity index from the measurement of the multiscale entropy profile.

RESULTS

During a follow-up of 13 months, 8 people died in the patient group. Values of either traditional heart rate variability measurements or complexity indices were found significantly lower in patients than those in healthy controls. In addition, the complexity indices (Area 1-5, Area 6-15 and Area 6-20) in the mortality group were significantly lower than those in the survival group, while there were no significant differences in traditional heart rate variability parameters between the two groups. In receiver operating characteristic curve analysis, Area 6-20 (AUC = 0.895, p < 0.001) showed the strongest predictive power between mortality and survival groups.

CONCLUSION

The results suggest that heart rhythm complexity is impaired for patients with end-stage renal disease. Furthermore, the complexity index of heart rate variability quantified by multiscale entropy may be a powerful independent predictor of mortality in end-stage renal disease patients undergoing hemodialysis.

Variation of the T-wave peak-end interval and heart rate variability values in healthy males and females at various hours of the same day, and relationship of them

BACKGROUND

The prolongation of repolarization time between the myocardial epicardium and endocardial cells is closely related to malignant ventricular arrhythmias. The purpose of our study was to compare repolarization markers, namely, T-wave peak-end interval (Tp-e), QT, corrected QT (QTc), Tp-e/QT, Tp-e/corrected QT (QTc), and Heart Rate Variability (HRV) values in healthy men and women and to investigate their daily variations.

METHODS

A total of 74 male and 78 female participants, being a government employee, and having no health problems, were included in the two study groups (males and females). A 24-hour, 12-lead Holter monitoring was performed on the volunteers. Then, the Tp-e interval and QT interval were measured on recordings. cTp-e and QTc were calculated by the use of Bazzet's formula.

RESULTS

There was no statistically significant difference between the groups in the cTp-e interval at 07.00 pm; however, it was significantly lower in the female group as compared with the male group at 07.00 am and 01.00 pm. It was significantly higher in the female group at 01.00 am compared with the male group. There were statistically significant moderate negative correlations between Tp-e intervals and a standard deviation of between two normal beats interval (SDNN) values at various hours of the same day.

CONCLUSION

There were statistically significant differences in terms of Tp-e and cTp-e intervals at various hours of the same day in both groups. In addition, there were statistically significant moderate negative correlations between Tp-e intervals and SDNN at various hours of the same day.

A NOVEL METHOD TO ISCHEMIC HEART DISEASE DETECTION BASED ON NON-INVASIVE ECG IMAGING

Electrocardiogram (ECG) signals containing very important information about the cardiac are one of the most common tools for physicians in the diagnosis of various types of cardiac diseases. Low accuracy in positioning, limitation of time accuracy, the similarity of signals between some diseases and normal signals and probability of missing some aspect of data are the defect aspects of this method. Importance of cardiac signals and defects of current methods in diagnosis show the need of substituting a new method to show the activity of cardiac. One of the most dangerous defections is ischemia, which corrects and on time diagnose could avoid the latter effect of it. Each of common methods for diagnosis of this illness has their own advantages and disadvantages. In this paper, we consider describing a non-invasive method for ischemic episode detection based on mapping of ECG signals. With this method, we can present the signals with virtual colors and facilitate the diagnosis of ischemic disease. So, a new method of 12-lead cardiac presentation is described that in fact present the 12-lead signals in two images. The result of this paper will present the indicators of sensitivity, specificity and accuracy in the context of disease diagnosis. This paper proposed a novel ECG imaging algorithm for classifying the normal and ischemic signals and 95.35% specificity, 96.79% sensitivity and 95.76% accuracy were achieved which are very much promising compared to the other methods and doctor’s accuracy.

Recognition of Lung Volume Condition based on Phase Space Mapping Using Electrical Impedance Tomography

The purpose of this paper is to identify differences between abnormal and normal lung signals gathered by an EIT device, which is a new, non-invasive system that seeks the electrical conductivity and permittivity inside a body. Lung performances in patients are investigated using Phase Space Mapping technique on Electrical EIT signals. The database used in this paper contains 82 registered records of 52 individuals with proper lung volume. The results of this paper show that as the delay parameter (τ) increases, the SD1 parameter of phase space mapping indicates a significant difference between normal and abnormal lung volumes. The value of the SD1 parameter with τ = 6 in the case that the lung volume is in a normal condition is 342.57 ± 32.75 while it is 156.71 ± 26.01 in non-optimal mode. This method can be used to identify the patients' lung volumes with chronic respiratory illnesses and is an accurate assessment of the diverse methods to treat respiratory system illnesses in addition to saving various therapeutic costs and dangerous consequences that are likely to occur by using improper treatment methods. It can also reduce the required treatment durations.

Twenty-four-hour continuous and remote monitoring of respiratory rate using a medical radar system for the early detection of pneumonia in symptomatic elderly bedridden hospitalized patients

Respiratory rate is often measured manually and discontinuously by counting of chest wall movements in routine clinical practice. We introduce a novel approach to investigate respiration dynamics using a noncontact medical radar system for identifying patient at risk of infection. The system enables early detection of pneumonia in bedridden hospitalized patients.

Device-measured physical activity data for classification of patients with ventricular arrhythmia events: A pilot investigation

Low levels of physical activity are associated with increased mortality risk, especially in cardiac patients, but most studies are based on self-report. Cardiac implantable electronic devices (CIEDs) offer an opportunity to collect data for longer periods of time. However, there is limited agreement on the best approaches for quantification of activity measures due to the time series nature of the data. We examined physical activity time series data from 235 subjects with CIEDs and at least 365 days of uninterrupted measures. Summary statistics for raw daily physical activity (minutes/day), including statistical moments (e.g., mean, standard deviation, skewness, kurtosis), time series regression coefficients, frequency domain components, and forecasted predicted values, were calculated for each individual, and used to predict occurrence of ventricular tachycardia (VT) events as recorded by the device. In unsupervised analyses using principal component analysis, we found that while certain features tended to cluster near each other, most provided a reasonable spread across activity space without a large degree of redundancy. In supervised analyses, we found several features that were associated with the outcome (P < 0.05) in univariable and multivariable approaches, but few were consistent across models. Using a machine-learning approach in which the data was split into training and testing sets, and models ranging in complexity from simple univariable logistic regression to ensemble decision trees were fit, there was no improvement in classification of risk over naïve methods for any approach. Although standard approaches identified summary features of physical activity data that were correlated with risk of VT, machine-learning approaches found that none of these features provided an improvement in classification. Future studies are needed to explore and validate methods for feature extraction and machine learning in classification of VT risk based on device-measured activity.

Presenting an efficient approach based on novel mapping for mortality prediction in intensive care unit cardiovascular patients

Intensive care unit (ICU) experienced and skillful people in this field should be employed because the equipment, facilities, and admitted patients have more special conditions than other departments. Our goal provides the best quality according to the condition each patient and prevent many unnecessary costs for preventive treatment. In this paper, the proposed system will first receive the patient's vital signs, which are recorded by the ICU monitoring. After the necessary processing, in case of observing changes in the normal state, risk alarms are transmitted to the nursing station so that nurses become aware of this condition and take all equipment to return the patient to normal condition and prevent his death. The applied graph in this study examines patients at any moment and displays the patient's future condition in a schematic manner after precise analyses. In this algorithm, after calculating the R-R intervals in the electrocardiogram signal, RRIs are thrown into a risk plot (RP) by a projectile. Given the amount of projectile RRI, one of the stairs can host that amount. After a few moments by springs embedded under the stairs, the drain of RRIs is done by the kinetic energy stored in the springs towards the valley of life. If the accumulation of quantities in a stair is too much, the spring will not be able to project those RRIs. By examining this situation, we will introduce an index to determine the risk of death for all patients. The results of this paper show that when a person is in normal condition, there is no density in a certain stair and the ball or the projected RRIs are not limited to a stair. In general, the results of this paper show that the lower amount of RRI dispersion in the RP leads to greater risk of entry into the death range and as this amount decrease, an immediate consideration is required. In conclusion, if the precise prediction of the future condition of ICU patients is available to nurses and doctors, more facilities and equipment could be provided to save their lives. •We focused on nonlinear methods with new aspects to extract mentioned dynamics.•This method can reduce the number of ICU nurses and give the special facilities for high-risk patients.•Our results confirm that it is possible to predict mortality based on the dynamical characteristics of HRV.

Assessing mood symptoms through heartbeat dynamics: An HRV study on cardiosurgical patients

BACKGROUND

Heart Rate Variability (HRV) is reduced both in depression and in coronary heart disease (CHD) suggesting common pathophysiological mechanisms for the two disorders. Within CHD, cardiac surgery patients (CSP) with postoperative depression are at greater risk of adverse cardiac events. Therefore, CSP would especially benefit from depression early diagnosis. Here we tested whether HRV-multi-feature analysis discriminates CSP with or without depression and provides an effective estimation of symptoms severity.

METHODS

Thirty-one patients admitted to cardiac rehabilitation after first-time cardiac surgery were recruited. Depressive symptoms were assessed with the Center for Epidemiologic Studies Depression Scale (CES-D). HRV features in time, frequency, and nonlinear domains were extracted from 5-min-ECG recordings at rest and used as predictors of "least absolute shrinkage and selection" (LASSO) operator regression model to estimate patients' CES-D score and to predict depressive state.

RESULTS

The model significantly predicted the CES-D score in all subjects (the total explained variance of CES-D score was 89.93%). Also it discriminated depressed and non-depressed CSP with 86.75% accuracy. Seven of the ten most informative metrics belonged to non-linear-domain.

LIMITATIONS

A higher number of patients evaluated also with a structured clinical interview would help to generalize the present findings.

DISCUSSION

To our knowledge this is the first study using a multi-feature approach to evaluate depression in CSP. The high informative power of HRV-nonlinear metrics suggests their possible pathophysiological role both in depression and in CHD. The high-accuracy of the algorithm at single-subject level opens to its translational use as screening tool in clinical practice.