Automatic electrocardiogram (ECG) beat classification is essential to timely diagnosis of dangerous heart conditions. Specifically, accurate detection of premature ventricular contractions (PVCs) is imperative to prepare for the possible onset of life-threatening arrhythmias. Although many groups have developed highly accurate algorithms for detecting PVC beats, results have generally been limited to relatively small data sets. Additionally, many of the highest classification accuracies (> 90%) have been achieved in experiments where training and testing sets overlapped significantly. Expanding the overall data set greatly reduces overall accuracy due to significant variation in ECG morphology among different patients. As a result, we believe that morphological information must be coupled with timing information, which is more constant among patients, in order to achieve high classification accuracy for larger data sets. With this approach, we combined wavelet-transformed ECG waves with timing information as our feature set for classification. We used select waveforms of 18 files of the MIT/BIH arrhythmia database, which provides an annotated collection of normal and arrhythmic beats, for training our neural-network classifier. We then tested the classifier on these 18 training files as well as 22 other files from the database. The accuracy was 95.16% over 93,281 beats from all 40 files, and 96.82% over the 22 files outside the training set in differentiating normal, PVC, and other beats.

The ballistocardiogram (BCG) measures the reaction of the body to cardiac ejection forces, and is an effective, non-invasive means of evaluating cardiovascular function. A simple, robust method is presented for acquiring high-quality, repeatable BCG signals from a modified, commercially available scale. The measured BCG waveforms for all subjects qualitatively matched values in the existing literature and physiologic expectations in terms of timing and IJ amplitude. Additionally, the BCG IJ amplitude was shown to be correlated with diastolic filling time for a subject with premature atrial contractions, demonstrating the sensitivity of the apparatus to beat-by-beat hemodynamic changes. The signal-to-noise ratio (SNR) of the BCG was estimated using two methods, and the average SNR over all subjects was greater than 12 for both estimates. The BCG measurement was shown to be repeatable over 50 recordings taken from the same subject over a three week period. This approach could allow patients at home to monitor trends in cardiovascular health.

The field of ballistocardiography seems to be enjoying a recent resurgence, most notably through the development of novel technologies and signal processing methods for measurement and analysis. After the method almost vanished in the late 80’s and 90’s, it is reasonable to wonder what is different this time, and if the technique has now more chances of becoming what its pioneer always wanted – a widespread clinical tool. This paper is an effort to compare and contrast this novel wave of research (notably in the context of the authors’ own work). It also suggests that the new approaches have several key differences with past embodiments that place them in a good position to address some specific issues such as cardiac resynchronization therapy device optimization or congestive heart failure monitoring. This optimism is largely fed by the recent technological advances enabling the measurement of the BCG unobtrusively, frequently, at home or in a hospital, and by a re-focus on monitoring and trending applications.

Analyzing systolic time intervals-specifically the preejection-period (PEP)-is widely accepted as one of the few methods for the noninvasive assessment of cardiac contractility. In this paper, we investigated the ballistocardiogram (BCG) as a way to noninvasively measure myocardial contractility when combined with the ECG. Specifically, we derived a parameter from the BCG and ECG that we hypothesized would be highly correlated to PEP. This is the time delay between the J-wave peak of the BCG and the R-wave of the ECG, which we refer to as the RJ interval. The RJ interval was correlated to PEP (r(2) = 0.86) for 2126 heartbeats across ten subjects, with a y-intercept of 138 ms and slope of 1.05. This suggests that the RJ interval can be reliably used as a noninvasive assessment of cardiac contractility.

Seismocardiography (SCG) is a non-invasive measurement of the vibrations of the chest caused by the heartbeat. SCG signals can be measured using a miniature accelerometer attached to the chest, and are thus well-suited for unobtrusive and long-term patient monitoring. Additionally, SCG contains information relating to both cardiovascular and respiratory systems. In this work, algorithms were developed for extracting three respiration-dependent features of the SCG signal: intensity modulation, timing interval changes within each heartbeat, and timing interval changes between successive heartbeats. Simultaneously with a reference respiration belt, SCG signals were measured from 20 healthy subjects and a respiration rate was estimated using each of the three SCG features and the reference signal. The agreement between each of the three accelerometer-derived respiration rate measurements was computed with respect to the respiration rate derived from the reference respiration belt. The respiration rate obtained from the intensity modulation in the SCG signal was found to be in closest agreement with the respiration rate obtained from the reference respiration belt: the bias was found to be 0.06 breaths per minute with a 95% confidence interval of -0.99 to 1.11 breaths per minute. The limits of agreement between the respiration rates estimated using SCG (intensity modulation) and the reference were within the clinically relevant ranges given in existing literature, demonstrating that SCG could be used for both cardiovascular and respiratory monitoring. Furthermore, phases of each of the three SCG parameters were investigated at four instances of a respiration cycle-start inspiration, peak inspiration, start expiration, and peak expiration-and during breath hold (apnea). The phases of the three SCG parameters observed during the respiration cycle were congruent with existing literature and physiologically expected trends.