Background Atrial fibrillation (AF) is a common and dangerous paroxysmal rhythm abnormality. Smartphones are increasingly used for mobile health applications by older patients at risk for AF and may be useful for AF screening. Objectives To test whether an enhanced smartphone app for AF detection can discriminate between sinus rhythm (SR), AF, premature atrial contractions (PACs) and premature ventricular contractions (PVCs). Methods We analyzed 219 2-minute pulse recordings from 121 participants with AF (n=98), PACs (n=15), or PVCs (n=15) using an iPhone 4S. We obtained pulsatile time series recordings in 91 participants after successful cardioversion to sinus rhythm from pre-existing AF. The PULSESMART app conducted pulse analysis using 3 methods [Root Mean Square of Successive RR Differences; Shannon Entropy; Poincare plot]. We examined the sensitivity, specificity, and predictive accuracy of the app for AF, PAC, and PVC discrimination from sinus rhythm using the 12-lead EKG or 3-lead telemetry as the gold standard. We also administered a brief usability questionnaire to a subgroup (n=65) of app users. Results The smartphone-based app demonstrated excellent sensitivity (0.970), specificity (0.935), and accuracy (0.951) for real-time identification of an irregular pulse during AF. The app also showed good accuracy for PAC (0.955) and PVC discrimination (0.960). The vast majority of surveyed app users (83%) reported that it was “useful” and “not complex” to use. Conclusions A smartphone app can accurately discriminate pulse recordings during AF from sinus rhythm, PACs, and PVCs.

We hypothesize that our smartphone-based arrhythmia discrimination algorithm with data acquisition approach reliably differentiates between normal sinus rhythm (NSR), atrial fibrillation (AF), premature ventricular contractions (PVCs) and premature atrial contraction (PACs) in a diverse group of patients having these common arrhythmias. We combine root mean square of successive RR differences and Shannon entropy with Poincare plot (or turning point ratio method) and pulse rise and fall times to increase the sensitivity of AF discrimination and add new capabilities of PVC and PAC identification. To investigate the capability of the smartphone-based algorithm for arrhythmia discrimination, 99 subjects, including 88 study participants with AF at baseline and in NSR after electrical cardioversion, as well as seven participants with PACs and four with PVCs were recruited. Using a smartphone, we collected 2-min pulsatile time series from each recruited subject. This clinical application results show that the proposed method detects NSR with specificity of 0.9886, and discriminates PVCs and PACs from AF with sensitivities of 0.9684 and 0.9783, respectively.

Motion and noise artifacts (MNA) are a serious obstacle in utilizing photoplethysmogram (PPG) signals for real-time monitoring of vital signs. We present a MNA detection method which can provide a clean vs. corrupted decision on each successive PPG segment. For motion artifact detection, we compute four time-domain parameters: (1) standard deviation of peak-to-peak intervals (2) standard deviation of peak-to-peak amplitudes (3) standard deviation of systolic and diastolic interval ratios, and (4) mean standard deviation of pulse shape. We have adopted a support vector machine (SVM) which takes these parameters from clean and corrupted PPG signals and builds a decision boundary to classify them. We apply several distinct features of the PPG data to enhance classification performance. The algorithm we developed was verified on PPG data segments recorded by simulation, laboratory-controlled and walking/stair-climbing experiments, respectively, and we compared several well-established MNA detection methods to our proposed algorithm. All compared detection algorithms were evaluated in terms of motion artifact detection accuracy, heart rate (HR) error, and oxygen saturation (SpO2) error. For laboratory controlled finger, forehead recorded PPG data and daily-activity movement data, our proposed algorithm gives 94.4, 93.4, and 93.7% accuracies, respectively. Significant reductions in HR and SpO2 errors (2.3 bpm and 2.7%) were noted when the artifacts that were identified by SVM-MNA were removed from the original signal than without (17.3 bpm and 5.4%). The accuracy and error values of our proposed method were significantly higher and lower, respectively, than all other detection methods. Another advantage of our method is its ability to provide highly accurate onset and offset detection times of MNAs. This capability is important for an automated approach to signal reconstruction of only those data points that need to be reconstructed, which is the subject of the companion paper to this article. Finally, our MNA detection algorithm is real-time realizable as the computational speed on the 7-s PPG data segment was found to be only 7 ms with a Matlab code.

Motion and noise artifacts (MNAs) impose limits on the usability of the photoplethysmogram (PPG), particularly in the context of ambulatory monitoring. MNAs can distort PPG, causing erroneous estimation of physiological parameters such as heart rate (HR) and arterial oxygen saturation (SpO2). In this study, we present a novel approach, "TifMA," based on using the time-frequency spectrum of PPG to first detect the MNA-corrupted data and next discard the nonusable part of the corrupted data. The term "nonusable" refers to segments of PPG data from which the HR signal cannot be recovered accurately. Two sequential classification procedures were included in the TifMA algorithm. The first classifier distinguishes between MNA-corrupted and MNA-free PPG data. Once a segment of data is deemed MNA-corrupted, the next classifier determines whether the HR can be recovered from the corrupted segment or not. A support vector machine (SVM) classifier was used to build a decision boundary for the first classification task using data segments from a training dataset. Features from time-frequency spectra of PPG were extracted to build the detection model. Five datasets were considered for evaluating TifMA performance: (1) and (2) were laboratory-controlled PPG recordings from forehead and finger pulse oximeter sensors with subjects making random movements, (3) and (4) were actual patient PPG recordings from UMass Memorial Medical Center with random free movements and (5) was a laboratory-controlled PPG recording dataset measured at the forehead while the subjects ran on a treadmill. The first dataset was used to analyze the noise sensitivity of the algorithm. Datasets 2-4 were used to evaluate the MNA detection phase of the algorithm. The results from the first phase of the algorithm (MNA detection) were compared to results from three existing MNA detection algorithms: the Hjorth, kurtosis-Shannon entropy, and time-domain variability-SVM approaches. This last is an approach recently developed in our laboratory. The proposed TifMA algorithm consistently provided higher detection rates than the other three methods, with accuracies greater than 95% for all data. Moreover, our algorithm was able to pinpoint the start and end times of the MNA with an error of less than 1 s in duration, whereas the next-best algorithm had a detection error of more than 2.2 s. The final, most challenging, dataset was collected to verify the performance of the algorithm in discriminating between corrupted data that were usable for accurate HR estimations and data that were nonusable. It was found that on average 48% of the data segments were found to have MNA, and of these, 38% could be used to provide reliable HR estimation.

This paper proposes a novel structural health monitoring framework for damage detection of smart structures. The framework is developed through the integration of the discrete wavelet transform, an autoregressive (AR) model, damage-sensitive features, and a support vector machine (SVM). The steps of the method are the following: (1) the wavelet-based AR (WAR) model estimates vibration signals obtained from both the undamaged and damaged smart structures under a variety of random signals; (2) a new damage-sensitive feature is formulated in terms of the AR parameters estimated from the structural velocity responses; and then (3) the SVM is applied to each group of damaged and undamaged data sets in order to optimally separate them into either damaged or healthy groups. To demonstrate the effectiveness of the proposed structural health monitoring framework, a three-story smart building equipped with a magnetorheological (MR) damper under artificial earthquake signals is studied. It is shown from the simulation that the proposed health monitoring scheme is effective in detecting damage of the smart structures in an efficient way.