Xiao-Lin Zhou

Unobtrusive Sensing and Wearable Devices for Health Informatics

The aging population, prevalence of chronic diseases, and outbreaks of infectious diseases are some of the major challenges of our present-day society. To address these unmet healthcare needs, especially for the early prediction and treatment of major diseases, health informatics, which deals with the acquisition, transmission, processing, storage, retrieval, and use of health information, has emerged as an active area of interdisciplinary research. In particular, acquisition of health-related information by unobtrusive sensing and wearable technologies is considered as a cornerstone in health informatics. Sensors can be weaved or integrated into clothing, accessories, and the living environment, such that health information can be acquired seamlessly and pervasively in daily living. Sensors can even be designed as stick-on electronic tattoos or directly printed onto human skin to enable long-term health monitoring. This paper aims to provide an overview of four emerging unobtrusive and wearable technologies, which are essential to the realization of pervasive health information acquisition, including: 1) unobtrusive sensing methods, 2) smart textile technology, 3) flexible-stretchable-printable electronics, and 4) sensor fusion, and then to identify some future directions of research.

Automatic online detection of atrial fibrillation based on symbolic dynamics and Shannon entropy

BackgroundAtrial fibrillation (AF) is the most common and debilitating abnormalities of the arrhythmias worldwide, with a major impact on morbidity and mortality. The detection of AF becomes crucial in preventing both acute and chronic cardiac rhythm disorders.ObjectiveOur objective is to devise a method for real-time, automated detection of AF episodes in electrocardiograms (ECGs). This method utilizes RR intervals, and it involves several basic operations of nonlinear/linear integer filters, symbolic dynamics and the calculation of Shannon entropy. Using novel recursive algorithms, online analytical processing of this method can be achieved.ResultsFour publicly-accessible sets of clinical data (Long-Term AF, MIT-BIH AF, MIT-BIH Arrhythmia, and MIT-BIH Normal Sinus Rhythm Databases) were selected for investigation. The first database is used as a training set; in accordance with the receiver operating characteristic (ROC) curve, the best performance using this method was achieved at the discrimination threshold of 0.353: the sensitivity (Se), specificity (Sp), positive predictive value (PPV) and overall accuracy (ACC) were 96.72%, 95.07%, 96.61% and 96.05%, respectively. The other three databases are used as testing sets. Using the obtained threshold value (i.e., 0.353), for the second set, the obtained parameters were 96.89%, 98.25%, 97.62% and 97.67%, respectively; for the third database, these parameters were 97.33%, 90.78%, 55.29% and 91.46%, respectively; finally, for the fourth set, the Sp was 98.28%. The existing methods were also employed for comparison.ConclusionsOverall, in contrast to the other available techniques, the test results indicate that the newly developed approach outperforms traditional methods using these databases under assessed various experimental situations, and suggest our technique could be of practical use for clinicians in the future.

Extraction of heart rate variability from smartphone photoplethysmograms.

Heart rate variability (HRV) is a useful clinical tool for autonomic function assessment and cardiovascular diseases diagnosis. It is traditionally calculated from a dedicated medical electrocardiograph (ECG). In this paper, we demonstrate that HRV can also be extracted from photoplethysmograms (PPG) obtained by the camera of a smartphone. Sixteen HRV parameters, including time-domain, frequency-domain, and nonlinear parameters, were calculated from PPG captured by a smartphone for 30 healthy subjects and were compared with those derived from ECG. The statistical results showed that 14 parameters (AVNN, SDNN, CV, RMSSD, SDSD, TP, VLF, LF, HF, LF/HF, nLF, nHF, SD1, and SD2) from PPG were highly correlated (r > 0.7, P < 0.001) with those from ECG, and 7 parameters (AVNN, TP, VLF, LF, HF, nLF, and nHF) from PPG were in good agreement with those from ECG within the acceptable limits. In addition, five different algorithms to detect the characteristic points of PPG wave were also investigated: peak point (PP), valley point (VP), maximum first derivative (M1D), maximum second derivative (M2D), and tangent intersection (TI). The results showed that M2D and TI algorithms had the best performance. These results suggest that the smartphone might be used for HRV measurement.

A Real-Time Atrial Fibrillation Detection Algorithm Based on the Instantaneous State of Heart Rate.

Atrial fibrillation (AF), the most frequent cause of cardioembolic stroke, is increasing in prevalence as the population ages, and presents with a broad spectrum of symptoms and severity. The early identification of AF is an essential part for preventing the possibility of blood clotting and stroke. In this work, a real-time algorithm is proposed for accurately screening AF episodes in electrocardiograms. This method adopts heart rate sequence, and it involves the application of symbolic dynamics and Shannon entropy. Using novel recursive algorithms, a low-computational complexity can be obtained. Four publicly-accessible sets of clinical data (Long-Term AF, MIT-BIH AF, MIT-BIH Arrhythmia, and MIT-BIH Normal Sinus Rhythm Databases) were used for assessment. The first database was selected as a training set; the receiver operating characteristic (ROC) curve was performed, and the best performance was achieved at the threshold of 0.639: the sensitivity (Se), specificity (Sp), positive predictive value (PPV) and overall accuracy (ACC) were 96.14%, 95.73%, 97.03% and 95.97%, respectively. The other three databases were used for independent testing. Using the obtained decision-making threshold (i.e., 0.639), for the second set, the obtained parameters were 97.37%, 98.44%, 97.89% and 97.99%, respectively; for the third database, these parameters were 97.83%, 87.41%, 47.67% and 88.51%, respectively; the Sp was 99.68% for the fourth set. The latest methods were also employed for comparison. Collectively, results presented in this study indicate that the combination of symbolic dynamics and Shannon entropy yields a potent AF detector, and suggest this method could be of practical use in both clinical and out-of-clinical settings.

Challenges and Opportunities in Cardiovascular Health Informatics

Cardiovascular health informatics is a rapidly evolving interdisciplinary field concerning the processing, integration/interpretation, storage, transmission, acquisition, and retrieval of information from cardiovascular systems for the early detection, early prediction, early prevention, early diagnosis, and early treatment of cardiovascular diseases (CVDs). Based on the first authors presentation at the first IEEE Life Sciences Grand Challenges Conference, held on October 4-5, 2012, at the National Academy of Sciences, Washington, DC, USA, this paper, focusing on coronary arteriosclerotic disease, will discuss three significant challenges of cardiovascular health informatics, including: 1) to invent unobtrusive and wearable multiparameter sensors with higher sensitivity for the real-time monitoring of physiological states; 2) to develop fast multimodal imaging technologies with higher resolution for the quantification and better understanding of structure, function, metabolism of cardiovascular systems at the different levels; and 3) to develop novel multiscale information fusion models and strategies with higher accuracy for the personalized predication of the CVDs. At the end of this paper, a summary is given to suggest open discussions on these three and more challenges that face the scientific community in this field in the future.

Cuffless and Continuous Blood Pressure Estimation from the Heart Sound Signals

Cardiovascular disease, like hypertension, is one of the top killers of human life and early detection of cardiovascular disease is of great importance. However, traditional medical devices are often bulky and expensive, and unsuitable for home healthcare. In this paper, we proposed an easy and inexpensive technique to estimate continuous blood pressure from the heart sound signals acquired by the microphone of a smartphone. A cold-pressor experiment was performed in 32 healthy subjects, with a smartphone to acquire heart sound signals and with a commercial device to measure continuous blood pressure. The Fourier spectrum of the second heart sound and the blood pressure were regressed using a support vector machine, and the accuracy of the regression was evaluated using 10-fold cross-validation. Statistical analysis showed that the mean correlation coefficients between the predicted values from the regression model and the measured values from the commercial device were 0.707, 0.712, and 0.748 for systolic, diastolic, and mean blood pressure, respectively, and that the mean errors were less than 5 mmHg, with standard deviations less than 8 mmHg. These results suggest that this technique is of potential use for cuffless and continuous blood pressure monitoring and it has promising application in home healthcare services.

A multidifferentiator-based approach to the reliable determination of T-wave offset in electrocardiograms

The determination of T-wave offset is still a very difficult task in the measurement of the QT interval. Several methods of determining the T-wave offset can be categorized into slope methods, threshold methods, or differential methods. The threshold- and slope-based methods are sensitive to low-frequency noise. The differential methods, in which a single differential operation is usually used for feature extraction, are susceptible to morphological variations in the range of the T-wave offset. In this study, a multidifferential filter comprising a series of simple multiscale differentiators with multiorders is proposed as a feature selector and extractor for T-wave offset in electrocardiograms (ECGs). This newly proposed approach was tested on artificial ECGs (the Conformance Testing Services for Computerized Electrocardiography Test data set: 1919 ECGs were generated with signal-to-noise ratios ranging from 10 to 60 dB, in increments of 0.5 dB, with 172,306 T waves with specified references) simulated at various noise levels and a set of clinical ECGs (3415 ECGs with 14,099 T waves, annotated by 3 cardiologists) and compared with existing detection methods. The accuracies achieved with the proposed approach were -0.269 ± 5.53 and 0.400 ± 9.89 milliseconds for the artificial and clinical ECGs, respectively. These test results indicate that the proposed method outperforms the other methods evaluated on both the artificial and clinical ECGs. The proposed approach is also more suitable for clinical applications in accordance with the performance requirements of the International Electrotechnical Commission.

Investigation of Five Algorithms for Selection of the Optimal Region of Interest in Smartphone Photoplethysmography

Smartphone photoplethysmography is a newly developed technique that can detect several physiological parameters from the photoplethysmographic signal obtained by the built-in camera of a smartphone. It is simple, low-cost, and easy-to-use, with a great potential to be used in remote medicine and home healthcare service. However, the determination of the optimal region of interest (ROI), which is an important issue for extracting photoplethysmographic signals from the camera video, has not been well studied. We herein proposed five algorithms for ROI selection: variance (VAR), spectral energy ratio (SER), template matching (TM), temporal difference (TD), and gradient (GRAD). Their performances were evaluated by a 50-subject experiment comparing the heart rates measured from the electrocardiogram and those from the smartphone using the five algorithms. The results revealed that the TM and the TD algorithms outperformed the other three as they had less standard error of estimate (<1.5 bpm) and smaller limits of agreement (<3 bpm). The TD algorithm was slightly better than the TM algorithm and more suitable for smartphone applications. These results may be helpful to improve the accuracy of the physiological parameters measurement and to make the smartphone photoplethysmography technique more practical.

Time-frequency analysis of heart rate variability during the cold pressor test using a time-varying autoregressive model

Heart rate variability is a useful clinical tool for autonomic function assessment and cardiovascular disease diagnosis. To investigate the dynamic changes of sympathetic and parasympathetic activities during the cold pressor test, we used a time-varying autoregressive model for the time-frequency analysis of heart rate variability in 101 healthy subjects. We found that there were two sympathetic peaks (or two parasympathetic valleys) when the abrupt changes of temperature (ACT) occurred at the beginning and the end of the cold stimulus and that the sympathetic and parasympathetic activities returned to normal in about the last 2 min of the cold stimulus. These findings suggested that the ACT rather than the low temperature was the major cause of the sympathetic excitation and parasympathetic withdrawal. We also found that the onsets of the sympathetic peaks were 4-26 s prior to the ACT and the returns to normal were 54-57 s after the ACT, which could be interpreted as the feedforward and adaptation of the autonomic regulation process in the human body, respectively. These results might be helpful for understanding the regulatory mechanisms of the autonomic system and its effects on the cardiovascular system.

Validation of New and Existing Decision Rules for the Estimation of Beat-to-Beat Pulse Transit Time

Pulse transit time (PTT) is a pivotal marker of vascular stiffness. Because the actual PTT duration in vivo is unknown and the complicated variation in waveform may occur, the robust determination of characteristic point is still a very difficult task in the PTT estimation. Our objective is to devise a method for real-time estimation of PTT duration in pulse wave. It has an ability to reduce the interference caused by both high- and low-frequency noise. The reproducibility and performance of these methods are assessed on both artificial and clinical pulse data. Artificial data are generated to investigate the reproducibility with various signal-to-noise ratios. For all artificial data, the mean biases obtained from all methods are less than 1 ms; collectively, this newly proposed method has minimum standard deviation (SD, <1 ms). A set of data from 33 participants together with the synchronously recorded continuous blood pressure data are used to investigate the correlation coefficient (CC). The statistical analysis shows that our method has maximum values of mean CC (0.5231), sum of CCs (17.26), and median CC (0.5695) and has the minimum SD of CCs (0.1943). Overall, the test results in this study indicate that the newly developed method has advantages over traditional decision rules for the PTT measurement.