Multisensor fusion for atrial and ventricular activity detection in coronary care monitoring

Multichannel Esophageal Heart Rate Monitoring of Preterm Infants

OBJECTIVE

Autonomic dysregulation in preterm infants requires continuous monitoring of vital signs such as heart rate over days to months. Unfortunately, common surface electrodes are prone to electrocardiography (ECG) signal artifacts and cause serious skin irritations during long-term use. In contrast, esophageal ECG is known to be very sensitive due to the proximity of electrodes and heart and insensitive to external influences. This study addresses if multichannel esophageal ECG qualifies for heart rate monitoring in preterm infants.

METHODS

We recorded esophageal leads with a multi-electrode gastric feeding tube in a clinical study with 13 neonates and compared the heartbeat detection performance with standard surface leads. A computationally simple and versatile ECG wave detection algorithm was used.

RESULTS

Multichannel esophageal ECG manifested heartbeat sensitivity and positive predictive value greater than 98.5% and significant less false negative (FN) ECG waves as compared to surface ECG due to site-typical electrode motion artifacts. False positive bradycardia as indicated with more than 13 consecutive FN ECG waves was equally expectable in esophageal and surface channels. No adverse events were reported for the multi-electrode gastric feeding tube.

CONCLUSION

Heart rate monitoring of preterm infants with multiple esophageal electrodes is considered as feasible and reliable. Less signal artifacts will improve the detection of bradycardia, which is crucial for immediate interventions, and reduce alarm fatigue.

SIGNIFICANCE

Due to the possibility to integrate the multichannel ECG into a gastric feeding tube and meanwhile omit harmful skin electrodes, the presented system has great potential to facilitate future intensive care of preterm infants.

Early and Late Fusion Machine Learning on Multi-Frequency Electrical Impedance Data to Improve Radiofrequency Ablation Monitoring

Radiofrequency ablation (RFA) is a popular modality for tumor treatment. However, inexpensive real-time monitoring of RFA within multiple tissue types is still an ongoing research topic. The objective of this study is to utilize multi-frequency electrical impedance data within real-time RFA depth estimation through data fusion schemes that include non-linear machine learning (ML) models. Multi-frequency tissue complex electrical impedance measurements are used to provide input data to the data fusion schemes. Our results show that the fusion schemes significantly decrease both the spread of residuals and the mean of the residuals for depth estimation. Thus, data fusion can be a significant tool for use in improving the performance of ML-based monitoring for RFA.

Robust, real-time generic detector based on a multi-feature probabilistic method

Robust, real-time event detection from physiological signals acquired during long-term ambulatory monitoring still represents a major challenge for highly-artifacted signals. In this paper, we propose an original and generic multi-feature probabilistic detector (MFPD) and apply it to real-time QRS complex detection under noisy conditions. The MFPD method calculates a binary Bayesian probability for each derived feature and makes a centralized fusion, using the Kullback-Leibler divergence. The method is evaluated on two ECG databases: 1) the MIT-BIH arrhythmia database from Physionet containing clean ECG signals, 2) a benchmark noisy database created by adding noise recordings of the MIT-BIH noise stress test database, also from Physionet, to the MIT-BIH arrhythmia database. Results are compared with a well-known wavelet-based detector, and two recently published detectors: one based on spatiotemporal characteristic of the QRS complex and the second, as the MFDP, based on feature calculations from the University of New South Wales detector (UNSW). For both benchmark Physionet databases, the proposed MFPD method achieves the lowest standard deviation in sensitivity and positive predictivity (+P) despite its online algorithm architecture. While the statistics are comparable for low-to mildly artifactual ECG signals, the MFPD outperforms reference methods for artifacted ECG with low SNR levels reaching 87.48 ± 14.21% in sensitivity and 89.39 ± 14.67% in +P as compared to 88.30 ± 17.66% and 86.06 ± 19.67% respectively from UNSW, the best performing reference method. With demonstrations on the extensively studied QRS detection problem, we consider that the proposed generic structure of the multi-feature probabilistic detector should offer promising perspectives for long-term monitoring applications for highly-artifacted signals.

Multiple Physiological Signals Fusion Techniques for Improving Heartbeat Detection: A Review

This paper presents a review of the techniques found in the literature that aim to achieve a robust heartbeat detection from fusing multi-modal physiological signals (e.g., electrocardiogram (ECG), blood pressure (BP), artificial blood pressure (ABP), stroke volume (SV), photoplethysmogram (PPG), electroencephalogram (EEG), electromyogram (EMG), and electrooculogram (EOG), among others). Techniques typically employ ECG, BP, and ABP, of which usage has been shown to obtain the best performance under challenging conditions. SV, PPG, EMG, EEG, and EOG signals can help increase performance when included within the fusion. Filtering, signal normalization, and resampling are common preprocessing steps. Delay correction between the heartbeats obtained over some of the physiological signals must also be considered, and signal-quality assessment to retain the best signal/s must be considered as well. Fusion is usually accomplished by exploiting regularities in the RR intervals; by selecting the most promising signal for the detection at every moment; by a voting process; or by performing simultaneous detection and fusion using Bayesian techniques, hidden Markov models, or neural networks. Based on the results of the review, guidelines to facilitate future comparison of the performance of the different proposals are given and promising future lines of research are pointed out.

An optimized lead system for long-term esophageal electrocardiography

Long-term electrocardiography (ECG) featuring adequate atrial and ventricular signal quality is highly desirable. Routinely used surface leads are limited in atrial signal sensitivity and recording capability impeding complete ECG delineation, i.e. in the presence of supraventricular arrhythmias. Long-term esophageal ECG might overcome these limitations but requires a dedicated lead system and recorder design. To this end, we analysed multiple-lead esophageal ECGs with respect to signal quality by describing the ECG waves as a function of the insertion level, interelectrode distance, electrode shape and amplifier's input range. The results derived from clinical data show that two bipolar esophageal leads, an atrial lead with short (15 mm) interelectrode distance and a ventricular lead with long (80 mm) interelectrode distance provide non-inferior ventricular signal strength and superior atrial signal strength compared to standard surface lead II. High atrial signal slope in particular is observed with the atrial esophageal lead. The proposed esophageal lead system in combination with an increased recorder input range of ±20 mV minimizes signal loss due to excessive electrode motion typically observed in esophageal ECGs. The design proposal might help to standardize long-term esophageal ECG registrations and facilitate novel ECG classification systems based on the independent detection of ventricular and atrial electrical activity.

Activity detection in scientific visualization

For large-scale simulations, the data sets are so massive that it is sometimes not feasible to view the data with basic visualization methods, let alone explore all time steps in detail. Automated tools are necessary for knowledge discovery, i.e., to help sift through the data and isolate specific time steps that can then be further explored. Scientists study patterns and interactions and want to know when and where interesting things happen. Activity detection, the detection of specific interactions of objects which span a limited duration of time, has been an active research area in the computer vision community. In this paper, we introduce activity detection to scientific simulations and show how it can be utilized in scientific visualization. We show how activity detection allows a scientist to model an activity and can then validate their hypothesis on the underlying processes. Three case studies are presented.

A NEW APPROACH FOR MULTI-SYSTEM/SENSOR DECISION FUSION BASED ON JOINT MEASURES

This article describes the joint measures method as a new powerful method for the development of a high performance multi-sensor data/image fusion scheme at the decision level. The images are received from distributed multiple sensors, which sense the targets in different spectral bands including visible, infrared, thermal and microwave. At first, we study the decision fusion methods, including voting schemes, rank based algorithm, Bayesian inference, and the Dempster-Shafer method. Then, we extract the mathematical properties of multi-sensor local classification results and use them for modeling of the classifier performances by the two new measures, i.e. the plausibility and correctness. Then we establish the plausibility and correctness distribution vectors and matrices for introducing the two improvements of the Dempster-Shafer method, i.e. the DS (CM) and DS (PM) methods. After that we introduce the joint measures decision fusion method based on using these two measures jointly. The Joint Measures Method (JMM) can deal with any decision fusion problem in the case of uncertain local classifiers results as well as clear local classifiers results. Finally, we deploy the new and previous methods for the fusion of the two different sets of multispectral image classification local results and we also compare their reliabilities, the commission errors and the omission errors. The results obviously show that the DS (PM), DS (CM) and JMM methods which use the special properties of the local classifiers and classes, have much better accuracies and reliabilities than other methods. In addition, we show that the reliability of the JMM is at least 3% higher than all other methods.

Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals

BACKGROUND

Dysphagia assessment involves diagnosis of individual swallows in terms of the depth of airway invasion and degree of bolus clearance. The videofluoroscopic swallowing study is the current gold standard for dysphagia assessment but is time-consuming and costly. An ideal alternative would be an automated abnormal swallow detection methodology based on non-invasive signals.

OBJECTIVE

Building upon promising results from single-axis cervical accelerometry, the objective of this study was to investigate the combination of dual-axis accelerometry and nasal airflow for classification of healthy and abnormal swallows in a patient population with dysphagia.

METHODS

Signals were acquired from 24 adult patients with dysphagia (17.8±8.8 swallows per patient). The abnormality of each swallow was quantified using 4-point videofluoroscopic rating scales for its depth of airway invasion, bolus clearance from the valleculae, and bolus clearance from the pyriform sinuses. For each scale, we endeavored to automatically discriminate between the 2 extreme ratings, yielding 3 separate binary classification problems. Various time, frequency, and time-frequency domain features were extracted. A genetic algorithm was deployed for feature selection. Smoothed bootstrapping was utilized to balance the two classes and provide sufficient training data for a multidimensional feature space.

RESULTS

A Euclidean linear discriminant classifier resulted in a mean adjusted accuracy of 74.7% for the depth of airway invasion rating, whereas Mahalanobis linear discriminant classifiers yielded mean adjusted accuracies of 83.7% and 84.2% for bolus clearance from the valleculae and pyriform sinuses, respectively. The bolus clearance from the valleculae problem required the lowest feature space dimensionality. Wavelet features were found to be most discriminatory.

CONCLUSIONS

This exploratory study confirms that dual-axis accelerometry and nasal airflow signals can be used to discriminate healthy and abnormal swallows from patients with dysphagia. The fact that features from all signal channels contributed discriminatory information suggests that multi-sensor fusion is promising in abnormal swallow detection.

P wave detector with PP rhythm tracking: evaluation in different arrhythmia contexts

Automatic detection of atrial activity (P waves) in an electrocardiogram (ECG) is a crucial task to diagnose the presence of arrhythmias. The P wave is difficult to detect and most of the approaches in the literature have been evaluated on normal sinus rhythms and rarely considered arrhythmia contexts other than atrial flutter and fibrillation. A novel knowledge-based P wave detector algorithm is presented. It is self-adaptive to the patient and able to deal with certain arrhythmias by tracking the PP rhythm. The detector has been tested on 12 records of the MIT-BIH arrhythmia database containing several ventricular and supra-ventricular arrhythmias. On the overall records, the detector demonstrates Se = 96.60% and Pr = 95.46%; for the normal sinus rhythm, it reaches Se = 97.76% and Pr = 96.80% and, in the case of Mobitz type II, it demonstrates Se = 72.79% and Pr = 99.51%. It also shows good performance for trigeminy and bigeminy, and outperforms some more sophisticated techniques. Although the results emphasize the difficulty of P wave detection in difficult arrhythmias (supra and ventricular tachycardias), it shows that domain knowledge can efficiently support signal processing techniques.

Data fusion of multimodal cardiovascular signals

The electrocardiogram (ECG) is a representative signal containing useful information about the condition of the heart. The shape and size of the P-QRS-T wave, the R-R interval etc. may help to identify the nature of disease afflicting the heart. However, human observer can not directly monitor these subtle details. Hence, the fusion of ECG, blood pressure, saturated oxygen content and respiratory data for achieving improved clinical diagnosis of patients in cardiac care units. Therefore, computer based analysis and display, is highly useful in diagnostics. The study demonstrates the feasibility of fuzzy logic based data fusion of the heterogeneous signals for the detection of life threatening states. Important parameters are derived from multimodal data and rule based approaches have been used. Fuzzified region for various abnormality conditions have been obtained which demonstrate the efficacy of the approach in various test cases. Comprehensive pictures showing the condition of the patient in various states will help physician in making a timely assessment in an intensive care set up.

Evaluation of real-time QRS detection algorithms in variable contexts

A method is presented to evaluate the detection performance of real-time QRS detection algorithms to propose a strategy for the adaptive selection of ORS detectors, in variable signal contexts. Signal contexts are defined as different combinations of QRS morphologies and clinical noise. Four QRS detectors are compared in these contexts by means of a multivariate analysis. This evaluation strategy is general and can be easily extended to a larger number of detectors. A set of morphology contexts, corresponding to eight QRS morphologies (normal, PVC, premature atrial beat, paced beat, LBBB, fusion, RBBB, junctional premature beat), was extracted from 17 standard ECG records. For each morphology context, the set of extracted beats, ranging from 30 to 23000, was resampled to generate 50 realisations of 20 concatenated beats. These realisations were then used as input to the QRS detectors, without noise, and with three different types of additive clinical noise (electrode motion artifact, muscle artifact, baseline wander) at three signal-to-noise ratios (5 dB, -5 dB, -15 dB). Performance was assessed by the number of errors, which reflected both false alarms and missed beats. The results show that the evaluated detectors are indeed complementary. For example, the Pan-Tompkins detector is the best in most contexts but the Okada detector generates fewer errors in the presence of electrode motion artifact. These results will be particularly useful to the development of a real-time system that will be able to choose the best ORS detector according to the current context.

Analysis of esophageal atrial recordings through wavelet packets decomposition

In this paper the processing of esophageal atrial electrograms by means of wavelet packets (WP) decomposition is presented. WP is described as a flexible, signal-adaptive, tool, which can be easily tuned to enhance characteristics of esophageal signals. Two aspects are mainly investigated: (i) the possibility to obtain automatic, reliable detection of atrial activation in 24h Holter recordings and (ii) the development of an algorithm for discrimination between atrial flutter (AFLU) and atrial fibrillation (AF) episodes. WP decomposition was used as a framework for pre-processing the esophageal signal and to build a set of orthonormal sub-signals which can be selected and combined according to the signal processing task to be performed: (i) in the detection of atrial activation, sub-band signal characteristics were explored at different scales by using the modulus maxima criteria and (ii) in the discrimination between AFLU and AF the coarser approximation of the esophageal signal was studied by spectral analysis. A reliable detection of atrial activation was obtained (Sensitivity (SE): 99.08%; positive predictability (+P): 98.98%). In addition a quantitative index able to discriminate between AFLU (SE: 97.5%; +P: 98.7%) and AF (SE: 98.7%; +P: 97.5%) episodes was introduced.

Temporal abstraction and inductive logic programming for arrhythmia recognition from electrocardiograms

This paper proposes a novel approach to cardiac arrhythmia recognition from electrocardiograms (ECGs). ECGs record the electrical activity of the heart and are used to diagnose many heart disorders. The numerical ECG is first temporally abstracted into series of time-stamped events. Temporal abstraction makes use of artificial neural networks to extract interesting waves and their features from the input signals. A temporal reasoner called a chronicle recogniser processes such series in order to discover temporal patterns called chronicles which can be related to cardiac arrhythmias. Generally, it is difficult to elicit an accurate set of chronicles from a doctor. Thus, we propose to learn automatically from symbolic ECG examples the chronicles discriminating the arrhythmias belonging to some specific subset. Since temporal relationships are of major importance, inductive logic programming (ILP) is the tool of choice as it enables first-order relational learning. The approach has been evaluated on real ECGs taken from the MIT-BIH database. The performance of the different modules as well as the efficiency of the whole system is presented. The results are rather good and demonstrate that integrating numerical techniques for low level perception and symbolic techniques for high level classification is very valuable.

Model-based interpretation of cardiac beats by evolutionary algorithms: signal and model interaction

This paper presents a new approach for cardiac beat interpretation, based on a direct integration between a model and observed ECG signals. Physiological knowledge is represented by means of a semi-quantitative model of the cardiac electrical activity. The interpretation of cardiac beats is formalized as an optimization problem, by minimizing an error function defined between the model's output and the observations. Evolutionary algorithms (EAs) are used as the search technique in order to obtain the set of model parameters reproducing at best the observed phenomena. Examples of model adaptation to three different kinds of cardiac beats are presented. Preliminary results show the potentiality of this approach to reproduce and explain complex pathological disorders and to better localize their origin.