Evaluating and comparing performance of feature combinations of heart rate variability measures for cardiac rhythm classification

Prototype Learning for Medical Time Series Classification via Human-Machine Collaboration

Deep neural networks must address the dual challenge of delivering high-accuracy predictions and providing user-friendly explanations. While deep models are widely used in the field of time series modeling, deciphering the core principles that govern the models' outputs remains a significant challenge. This is crucial for fostering the development of trusted models and facilitating domain expert validation, thereby empowering users and domain experts to utilize them confidently in high-risk decision-making contexts (e.g., decision-support systems in healthcare). In this work, we put forward a deep prototype learning model that supports interpretable and manipulable modeling and classification of medical time series (i.e., ECG signal). Specifically, we first optimize the representation of single heartbeat data by employing a bidirectional long short-term memory and attention mechanism, and then construct prototypes during the training phase. The final classification outcomes (i.e., normal sinus rhythm, atrial fibrillation, and other rhythm) are determined by comparing the input with the obtained prototypes. Moreover, the proposed model presents a human-machine collaboration mechanism, allowing domain experts to refine the prototypes by integrating their expertise to further enhance the model's performance (contrary to the human-in-the-loop paradigm, where humans primarily act as supervisors or correctors, intervening when required, our approach focuses on a human-machine collaboration, wherein both parties engage as partners, enabling more fluid and integrated interactions). The experimental outcomes presented herein delineate that, within the realm of binary classification tasks-specifically distinguishing between normal sinus rhythm and atrial fibrillation-our proposed model, albeit registering marginally lower performance in comparison to certain established baseline models such as Convolutional Neural Networks (CNNs) and bidirectional long short-term memory with attention mechanisms (Bi-LSTMAttns), evidently surpasses other contemporary state-of-the-art prototype baseline models. Moreover, it demonstrates significantly enhanced performance relative to these prototype baseline models in the context of triple classification tasks, which encompass normal sinus rhythm, atrial fibrillation, and other rhythm classifications. The proposed model manifests a commendable prediction accuracy of 0.8414, coupled with macro precision, recall, and F1-score metrics of 0.8449, 0.8224, and 0.8235, respectively, achieving both high classification accuracy as well as good interpretability.

Statistical and Diagnostic Properties of pRRx Parameters in Atrial Fibrillation Detection

BACKGROUND

We studied the diagnostic properties of the percentage of successive RR intervals differing by at least x ms (pRRx) as functions of the threshold value x in a range of 7 to 195 ms for the differentiation of atrial fibrillation (AF) from sinus rhythm (SR).

METHODS

RR intervals were measured in 60-s electrocardiogram (ECG) segments with either AF (32,141 segments) or SR (32,769 segments) from the publicly available Physionet Long-Term Atrial Fibrillation Database (LTAFDB). For validation, we have used ECGs from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Atrial Fibrillation Database. The pRRx distributions in AF and SR in relation to x were studied by histograms, along with the mutual association by the nonparametric Spearman correlations for all pairs of pRRx, and separately for AF or SR. The optimal cutoff values for all pRRx were determined using the receiver operator curve characteristic. A nonparametric bootstrap with 5000 samples was used to calculate a 95% confidence interval for several classification metrics.

RESULTS

The distributions of pRRx for x in the 7-195 ms range are significantly different in AF than in SR. The sensitivity, specificity, accuracy, and diagnostic odds ratios differ for pRRx, with the highest values for x = 31 ms (pRR31) rather than x = 50 (pRR50), which is most commonly applied in studies on heart rate variability. For the optimal cutoff of pRR31 (68.79%), the sensitivity is 90.42%, specificity 95.37%, and the diagnostic odds ratio is 194.11. Validation with the ECGs from the MIT-BIH Atrial Fibrillation Database confirmed our findings.

CONCLUSIONS

We demonstrate that the diagnostic properties of pRRx depend on x, and pRR31 outperforms pRR50, at least for ECGs of 60-s duration.

Nonlinear model-based cardiac arrhythmia diagnosis using the optimization-based inverse problem solution

This study investigates a nonlinear model-based feature extraction approach for the accurate classification of four types of heartbeats. The features are the morphological parameters of ECG signal derived from the nonlinear ECG model using an optimization-based inverse problem solution. In the model-based methods, high feature extraction time is a crucial issue. In order to reduce the feature extraction time, a new structure was employed in the optimization algorithms. Using the proposed structure has considerably increased the speed of feature extraction. In the following, the effectiveness of two types of optimization methods (genetic algorithm and particle swarm optimization) and the McSharry ECG model has been studied and compared in terms of speed and accuracy of diagnosis. In the classification section, the adaptive neuro-fuzzy inference system and fuzzy c-mean clustering methods, along with the principal component analysis data reduction method, have been utilized. The obtained results reveal that using an adaptive neuro-fuzzy inference system with data obtained from particle swarm optimization will have the shortest process time and the best diagnosis, with a mean accuracy of 99% and a mean sensitivity of 99.11%.

COMPUTER AIDED DIAGNOSIS FOR CARDIOVASCULAR DISEASES BASED ON ECG SIGNALS: A SURVEY

The interpretation of Electroencephalography (ECG) signals is difficult, because even subtle changes in the waveform can indicate a serious heart disease. Furthermore, these waveform changes might not be present all the time. As a consequence, it takes years of training for a medical practitioner to become an expert in ECG-based cardiovascular disease diagnosis. That training is a major investment in a specific skill. Even with expert ability, the signal interpretation takes time. In addition, human interpretation of ECG signals causes interoperator and intraoperator variability. ECG-based Computer-Aided Diagnosis (CAD) holds the promise of improving the diagnosis accuracy and reducing the cost. The same ECG signal will result in the same diagnosis support regardless of time and place. This paper introduces both the techniques used to realize the CAD functionality and the methods used to assess the established functionality. This survey aims to instill trust in CAD of cardiovascular diseases using ECG signals by introducing both a conceptional overview of the system and the necessary assessment methods.

Automatic sleep staging using empirical mode decomposition, discrete wavelet transform, time-domain, and nonlinear dynamics features of heart rate variability signals

The conventional method for sleep staging is to analyze polysomnograms (PSGs) recorded in a sleep lab. The electroencephalogram (EEG) is one of the most important signals in PSGs but recording and analysis of this signal presents a number of technical challenges, especially at home. Instead, electrocardiograms (ECGs) are much easier to record and may offer an attractive alternative for home sleep monitoring. The heart rate variability (HRV) signal proves suitable for automatic sleep staging. Thirty PSGs from the Sleep Heart Health Study (SHHS) database were used. Three feature sets were extracted from 5- and 0.5-min HRV segments: time-domain features, nonlinear-dynamics features and time-frequency features. The latter was achieved by using empirical mode decomposition (EMD) and discrete wavelet transform (DWT) methods. Normalized energies in important frequency bands of HRV signals were computed using time-frequency methods. ANOVA and t-test were used for statistical evaluations. Automatic sleep staging was based on HRV signal features. The ANOVA followed by a post hoc Bonferroni was used for individual feature assessment. Most features were beneficial for sleep staging. A t-test was used to compare the means of extracted features in 5- and 0.5-min HRV segments. The results showed that the extracted features means were statistically similar for a small number of features. A separability measure showed that time-frequency features, especially EMD features, had larger separation than others. There was not a sizable difference in separability of linear features between 5- and 0.5-min HRV segments but separability of nonlinear features, especially EMD features, decreased in 0.5-min HRV segments. HRV signal features were classified by linear discriminant (LD) and quadratic discriminant (QD) methods. Classification results based on features from 5-min segments surpassed those obtained from 0.5-min segments. The best result was obtained from features using 5-min HRV segments classified by the LD classifier. A combination of linear/nonlinear features from HRV signals is effective in automatic sleep staging. Moreover, time-frequency features are more informative than others. In addition, a separability measure and classification results showed that HRV signal features, especially nonlinear features, extracted from 5-min segments are more discriminative than those from 0.5-min segments in automatic sleep staging.