Search

Blood pressure (BP) is an important clinical vital sign that varies from beat-to-beat. Nevertheless, these variations cannot be captured by the conventional cuff-based BP monitors. This study proposes and evaluates novel cuffless frameworks to continuously estimate the 10-beat averaged systolic BP (SBP) and diastolic BP (DBP) during dynamic exercise by fusing information from multiple biosensors using five machine learning algorithms. Over 100 thousand beats of data were collected from 62 subjects (aged 59 ± 10 years), each underwent a maximal exercise stress test. The average length of recording for each subject was 35 minutes. The BP ranges were 75-280 mmHg for SBP and 36-157 mmHg for DBP respectively. Multiple physiological parameters were measured continuously and used as inputs to five machine learning algorithms for estimating the 10-beat SBP and DBP averages before, during and after the cycling exercise. The mean absolute error (MAE) of Gaussian process regression (GPR) model was 4.8 mmHg and 3.4 mmHg for SBP and DBP, respectively. The MAE of multiple linear regression (MLR), regression tree (RT), ensemble of trees (ETs), and support vector machine (SVM) models varied from 6.1 mmHg to 17.6 mmHg and from 4.0 mmHg to 9.7 mmHg for SBP and DBP, respectively. The GPR model outperformed the other four models and showed promising results in estimating the 10-beat averages of both SBP and DBP without a cuff in a general elderly population under dynamic conditions.

Estimating hospital mortality of patients is important in assisting clinicians to make decisions and hospital providers to allocate resources. This paper proposed a multi-task recurrent neural network with attention mechanisms to predict patients' hospital mortality, using reconstruction of patients' physiological time series as an auxiliary task. Experiments were conducted on a large public electronic health record database, i.e., MIMIC-III. Fifteen physiological measurements during the first 24 h of critical care were used to predict death before hospital discharge. Compared with the conventional simplified acute physiology score (SAPS-II), the proposed multi-task learning model achieved better sensitivity (0.503 ± 0.020 versus 0.365 ± 0.021), when predictions were made based on the same 24-h observation period. The multi-task learning model is recommended to be updated daily with at least a 6-h observation period, in order for it to perform similarly or better than the SAPS-II. In the future, the need for intervention can be considered as another task to further optimize the performance of the multi-task learning model.

Pulse arrival time (PAT) has been broadly investigated for its potential for cuffless blood pressure (BP) estimation and ease of measurement by wearable devices. It is also of great significance to explore whether PAT conveys complementary information to BP for vascular health assessment. In this paper, the differences between the 24-h ambulatory BP and wearable-based PAT were compared among 12 young normotensives and 15 elderly hypertensives in terms of the mean and coefficients of variation (CoVs). The correlations of the nocturnal normalized PAT (n-PAT) and BP with two arterial stiffness-related parameters (i.e., the intrinsic elastic modulus E0 and the vascular modulation factor α) estimated by a proposed model-based method were also compared. The results showed that the inter-subject variances of the nocturnal average n-PAT were significantly different between the hypertensives and the normotensives (P

A computer-aided detection (CAD) tool for locating and detecting polyps can help reduce the chance of missing polyps during colonoscopy. Nevertheless, state-of-the-art algorithms were either computationally complex or suffered from low sensitivity and therefore unsuitable to be used in real clinical setting. In this paper, a novel regression-based Convolutional Neural Network (CNN) pipeline is presented for polyp detection during colonoscopy. The proposed pipeline was constructed in two parts: 1) to learn the spatial features of colorectal polyps, a fast object detection algorithm named ResYOLO was pre-trained with a large non-medical image database and further fine-tuned with colonoscopic images extracted from videos; and 2) temporal information was incorporated via a tracker named Efficient Convolution Operators (ECO) for refining the detection results given by ResYOLO. Evaluated on 17,574 frames extracted from 18 endoscopic videos of the AsuMayoDB, the proposed method was able to detect frames with polyps with a precision of 88.6%, recall of 71.6% and processing speed of 6.5 frames per second, i.e. the method can accurately locate polyps in more frames and at a faster speed compared to existing methods. In conclusion, the proposed method has great potential to be used to assist endoscopists in tracking polyps during colonoscopy.

An automatic colonic polyp localization algorithm named RYCO is developed to tackle the challenges of precise polyp location indication together with fast processing time when general limited and accessible computation resource is given.

Electromagnetic Navigation Systems (eMNS) can be used to control a variety of multiscale devices within the human body for remote surgery. Accurate modeling of the magnetic fields generated by the electromagnets of an eMNS is crucial for the precise control of these devices. Existing methods assume a linear behavior of these systems, leading to significant modeling errors within nonlinear regions exhibited at higher magnetic fields, preventing these systems from operating at full capacity. In this paper, we use a random forest (RF) and an artificial neural network (ANN) to model the nonlinear behavior of the magnetic fields generated by an eMNS. Both machine learning methods outperformed the state-of-the-art linear multipole electromagnet model (MPEM). The RF and the ANN model reduced the root mean squared error (RMSE) of the MPEM when predicting the field magnitude by approximately 40% and 87%, respectively, over the entire current range of the eMNS. At high current regions, especially between 30 and 35 A, the field-magnitude RMSE improvement of the ANN model over the MPEM was 37 mT, equivalent to 90% error reduction. This study demonstrates the feasibility of using machine learning to model an eMNS for medical applications, and its ability to account for complex nonlinear behavior at high currents. The use of machine learning thus shows promise in developing accurate field predicting models, and ultimately improving surgical procedures that use magnetic navigation. © 2020 IEEE., 2020 IEEE International Conference on Robotics and Automation (ICRA), ISBN:978-1-7281-7395-5, ISBN:978-1-7281-7394-8, ISBN:978-1-7281-7396-2

We have designed a deep-learning model, an “Artificial Intelligent Endoscopist (a.k.a. AI-doscopist)”, to localise colonic neoplasia during colonoscopy. This study aims to evaluate the agreement between endoscopists and AI-doscopist for colorectal neoplasm localisation. AI-doscopist was pre-trained by 1.2 million non-medical images and fine-tuned by 291,090 colonoscopy and non-medical images. The colonoscopy images were obtained from six databases, where the colonoscopy images were classified into 13 categories and the polyps’ locations were marked image-by-image by the smallest bounding boxes. Seven categories of non-medical images, which were believed to share some common features with colorectal polyps, were downloaded from an online search engine. Written informed consent were obtained from 144 patients who underwent colonoscopy and their full colonoscopy videos were prospectively recorded for evaluation. A total of 128 suspicious lesions were resected or biopsied for histological confirmation. When evaluated image-by-image on the 144 full colonoscopies, the specificity of AI-doscopist was 93.3%. AI-doscopist were able to localise 124 out of 128 polyps (polyp-based sensitivity = 96.9%). Furthermore, after reviewing the suspected regions highlighted by AI-doscopist in a 102-patient cohort, an endoscopist has high confidence in recognizing four missed polyps in three patients who were not diagnosed with any lesion during their original colonoscopies. In summary, AI-doscopist can localise 96.9% of the polyps resected by the endoscopists. If AI-doscopist were to be used in real-time, it can potentially assist endoscopists in detecting one more patient with polyp in every 20–33 colonoscopies.

Objective: Wireless capsule endoscope (WCE) is a revolutionary approach to diagnose small bowel pathologies. Currently available WCEs are mostly passive devices with image capturing function only, while on-going efforts have been placed on robotizing WCEs or to enhance them with therapeutic functions. In this paper, the authors present a novel inflatable WCE for haemostasis in the gastrointestinal (GI) tracts by balloon tamponade effect. Methods: The proposed wireless capsule consists of a balloon that can be inflated using the endothermic reaction of acid and base. When the balloon reached a precalculated pressure level, it is able to stop at a bleeding site in the bowel, and achieve haemostasis by tamponade effect. The prototype is 14 mm in diameter, with three sections of 13, 35, and 12 mm in length, respectively. The three sections are linked together with flexible joints and enclosed in a silicone balloon. The prototypes were tested in ex vivo porcine intestine models. Results: In the ten ex vivo trials conducted, the inflatable wireless capsule achieved average balloon pressure of 46.0 mmHg and withstood average maximum longitudinal pulling force at 1.46 N. An in vivo study was carried out as a proof-of-concept for treating bleeding in a porcine model. The proposed inflatable WCE succeeded in the animal test by controlling haemostasis within 5 min. No rebleeding was observed in the next 20 min. Conclusion: The results suggested that the inflatable capsule with a real-time bleeding detection algorithm can be implemented. Moreover, the proposed inflatable WCE prototype can achieve haemorrhage control in the lower GI. Significance: To our best knowledge, this is the first study that demonstrated the potential to treat GI haemorrhage by an inflatable WCE. The proposed capsule enables the development of a closed-loop system based on a body sensor network to provide early treatment of GI bleeding for p-medicine.

Colorectal cancer (CRC) is a leading cause of cancer deaths worldwide. Although polypectomy at early stage reduces CRC incidence, 90% of the polyps are small and diminutive, where removal of them poses risks to patients that may outweigh the benefits. Correctly detecting and predicting polyp type during colonoscopy allows endoscopists to resect and discard the tissue without submitting it for histology, saving time, and costs. Nevertheless, human visual observation of early stage polyps varies. Therefore, this paper aims at developing a fully automatic algorithm to detect and classify hyperplastic and adenomatous colorectal polyps. Adenomatous polyps should be removed, whereas distal diminutive hyperplastic polyps are considered clinically insignificant and may be left in situ . A novel transfer learning application is proposed utilizing features learned from big nonmedical datasets with 1.4-2.5 million images using deep convolutional neural network. The endoscopic images we collected for experiment were taken under random lighting conditions, zooming and optical magnification, including 1104 endoscopic nonpolyp images taken under both white-light and narrowband imaging (NBI) endoscopy and 826 NBI endoscopic polyp images, of which 263 images were hyperplasia and 563 were adenoma as confirmed by histology. The proposed method identified polyp images from nonpolyp images in the beginning followed by predicting the polyp histology. When compared with visual inspection by endoscopists, the results of this study show that the proposed method has similar precision (87.3% versus 86.4%) but a higher recall rate (87.6% versus 77.0%) and a higher accuracy (85.9% versus 74.3%). In conclusion, automatic algorithms can assist endoscopists in identifying polyps that are adenomatous but have been incorrectly judged as hyperplasia and, therefore, enable timely resection of these polyps at an early stage before they develop into invasive cancer.

Endoscopic submucosal dissection (ESD) is an effective and less invasive treatment for early gastric and colorectal cancers. Nevertheless, performing ESD through a flexible endoscope is technically challenging due to the limited controllability of the endoscopic instruments. Therefore, a surgical robotic system with high dexterity and better ergonomics is much needed. A master–slave dual-arm robot with customizing workspace for ESD is proposed for this study. The design is such that the procedure is completed without the need for changing the instrument. Our robot is mainly driven by tendon–sheath (TS) mechanism. Modeling and use of a controller for elongation compensation of tendon due to friction to increase position control accuracy are presented. Experiment shows that the controller greatly enhances the controllability of the robot. We have demonstrated that the design of the robot arm allows it to lift up to 48 g, which is sufficient for ESD. Six subjects, including three endoscopists and upper gastrointestinal surgeons, were invited to evaluate the system in an ex vivo experiment. Experienced surgeons were able to complete a dissection within 30 min. We have demonstrated a prototype robot that can facilitate the ESD procedure with bimanual tissue dissection. The system is competent to remove a lesion area precisely. Further studies are needed to evaluate the system in vivo .

This paper aims to develop an objective index for anxiety based on features derived from electroencephalogram (EEG) and photoplethysmogram (PPG) collected from wearable headset and glasses. The 20 subjects were asked to ride at his most comfortable speed in Task 1 and ride while imagining competing with another person in Task 2. A Competitive State Anxiety Inventory-2 questionnaire was conducted before each task to evaluate the anxiety level of each participant. Various features were extracted from EEG and PPG. The results of this paper showed that the mean value and average power of alpha band wavelet coefficients and that of beta band are highly correlated with the anxiety level ( $r=-0.49$ and −0.58, $p for alpha band, and $r=-0.51$ and −0.58, $p for beta band, respectively). Features extracted from partial autocorrelation of EEG showed moderate correlation with the anxiety level. Mean pulse rate also acts as a potential anxiety marker for individualized anxiety measurement. Using both EEG and PPG features, the classification accuracy of three-level anxiety by principle component analysis and $k$ -nearest neighbors can achieve 62.5% across subjects. To conclude, wearable sensors have the potential to be used for assessing anxiety level objectively and unobtrusively to facilitate on-site sports performance enhancement and mental-stress-related studies.

Noninvasive and real-time cuffless blood pressure (BP) measurement realizes the idea of unobtrusive and continuous BP monitoring which is essential for diagnosis and prevention of cardiovascular diseases associated with hypertension. In this paper, a wearable sensor patch system that integrates flexible piezoresistive sensor (FPS) and epidermal electrocardiogram (ECG) sensors for cuffless BP measurement is presented. By developing parametric models on the FPS sensing mechanism and optimizing operational conditions, a highly stable epidermal pulse monitoring method is established and beat-to-beat BP measurement from the ECG and epidermal pulse signals is demonstrated. In particular, this study highlights the compromise between sensor sensitivity and signal stability. As compared with the current optical-based cuffless BP measurement devices, the sensing patch requires much lower power consumption (3 nW) and is capable of detecting subtle physiological signal variations, e.g., pre and postexercises, thus providing a promising solution for low-power, real-time, and home-based BP monitoring.

Algorithms for localising colorectal polyps have been studied extensively; however, they were often trained and tested using the same database. In this study, we present a new application of a unified and real-time object detector based on You-Only-Look-Once (YOLO) convolutional neural network (CNN) for localizing polyps with bounding boxes in endoscopic images. The model was first pre-trained with non-medical images and then fine-tuned with colonoscopic images from three different databases, including an image set we collected from 106 patients using narrow-band (NB) imaging endoscopy. YOLO was tested on 196 white light (WL) images of an independent public database. YOLO achieved a precision of 79.3% and sensitivity of 68.3% with time efficiency of 0.06 sec/frame in the localization task when trained by augmented images from multiple WL databases. In conclusion, YOLO has great potential to be used to assist endoscopists in localising colorectal polyps during endoscopy. CNN features of WL and NB endoscopic images are different and should be considered separately. A large-scale database that covers different scenarios, imaging modalities and scales is lacking but crucial in order to bring this research into reality.

Current markers for heart failure (HF) diagnosis and prognosis are mainly for the evaluation of cardiac functions. Since previous studies have reported that HF patients demonstrated abnormal vascular responses to external stimuli, it is speculated that vascular tone, a measure of activation level of vascular wall, may be able to reflect these abnormalities to assist HF detection. Nevertheless, vascular tone is difficult to be objectively quantified using existing tools. In this study, a vascular tone index was estimated from noninvasive blood pressure and pulse transit time measurements using system identification technique. This method was evaluated in 35 subjects (10 healthy, 13 with HF risk factors and 12 HF patients) in a regular maximal exercise test. It was found that the vascular tone index significantly increased by 24.4 ± 26.6% (p

Body sensors are now commonly used as ingestible, wearable and implantable devices for clinical diagnosis and continuous physiological monitoring. Nevertheless, they usually have limited resources. Recent advancements in technologies provide a possible solution to mitigate the resource limitation of these devices by connecting them with mobile devices and cloud services. To evaluate the feasibility of the cloud-enabled body sensor networks, this paper presents simulation results on testing the feasibility of 24-hour operating time and concurrent user support for the cloud-enabled applications.

24-h blood pressure (BP) has significant prognostic value for cardiovascular risk screening, but the present BP devices are mainly cuff-based, which are unsuitable for long-term BP measurement, especially during nighttime. In this paper, we developed an armband wearable pulse transit time (PTT) system for 24-h cuff-less BP measurement and evaluated it in an unattended out-of-laboratory setting. Ten healthy young subjects participated in this ambulatory study, where PTT was measured at 30-min interval by this wearable system and the reference BP was measured by a standard oscillometric ambulatory BP monitor. Due to the misalignment of BP and PTT on their recording time caused by the different measurement principles of the two BP devices, a new estimation method has been proposed: transients in PTT were removed from the raw data by defined criteria, and then evenly interpolated, low-pass filtered, and resampled to synchronize at the time when BP was recorded. The results show that with the proposed method, the correlation between PTT and systolic BP (SBP) during nighttime with dynamic range of 21.8 ± 14.2 mmHg has improved from −0.50 ± 0.24 to −0.62 ± 0.20 $(p , and the difference between the estimated and reference SBP has improved from 0.7 ± 10.7 to 2.8 ± 8.2 mmHg with root mean square error reduced from 10.7 to 8.7 mmHg. In addition, the correlation between a very low frequency component of SBP and PTT obtained from the proposed method during nighttime is −0.80 ± 0.10 and the difference is 2.4 ± 5.7 mmHg for a dynamic BP range of 13.5 ± 8.0 mmHg. It is therefore concluded from this study that the proposed wearable system has great potential to be used for overnight SBP monitoring, especially to measure the averaged SBP over a long period.

Ambulatory blood pressure monitoring (ABPM) has become an essential tool in the diagnosis and management of hypertension. Current standard ABPM devices use an oscillometric cuff-based method which can cause physical discomfort to the patients with repeated inflations and deflations, especially during nighttime leading to sleep disturbance. The ability to measure ambulatory BP accurately and comfortably without a cuff would be attractive. This study validated the accuracy of a cuff-less approach for ABPM using pulse arrival time (PAT) measurements on both healthy and hypertensive subjects for potential use in hypertensive management, which is the first of its kind. The wearable cuff-less device was evaluated against a standard cuff-based device on 24 subjects of which 15 have known hypertension. BP measurements were taken from each subject over a 24-h period by the cuff-less and cuff-based devices every 15 to 30 minutes during daily activities. Mean BP of each subject during daytime, nighttime and over 24-h were calculated. Agreement between mean nighttime systolic BP (SBP) and diastolic (DBP) measured by the two devices evaluated using Bland-Altman plot were ?1.4 ± 6.6 and 0.4 ± 6.7 mmHg, respectively. Receiver operator characteristics (ROC) statistics was used to assess the diagnostic accuracy of the cuff-less approach in the detection of BP above the hypertension threshold during nighttime (>120/70 mmHg). The area under ROC curves were 0.975/0.79 for nighttime. The results suggest that PAT-based approach is accurate and promising for ABPM without the issue of sleep disturbances associated with cuff-based devices.

Mobile health (mHealth) is an emerging concept which refers to the combinational use of mobile computing, communication technologies, and medical sensors for healthcare [1]. In addition to the passive provision of health-related information via mobile platforms, its scope also extends to more active applications such as disease management, medical prognosis, diagnosis, and even treatment. A typical mHealth system is characterized by its features of mobility, wireless connectivity, location independence, and timely responsewhich together provide seamless and personalized healthcare.

Time–frequency (T–F) analysis is often used to study the non-stationary cardiovascular oscillations such as heart rate and blood pressure variabilities in dynamic situations. This study intends to use the T–F recursive autoregressive technique to investigate variability in pulse transit time (PTT), which is a cardiovascular parameter of emerging interest due to its potential to estimate blood pressure non-invasively, continuously and without a cuff. Recent studies suggest that PTT is not only related to systolic blood pressure (SBP) but also to heart rate. Therefore, in this study, variability of PTT is analyzed together with the variabilities of R–R interval (RRI) from electrocardiogram and beat-to-beat SBP on 9 normotensive subjects before and shortly after three successive bouts of treadmill exercise. The results showed that both low frequency (LF) and high frequency (HF) components were found in the spectra of RRI, SBP and PTT in the 5-min recordings collected before and after exercise. Compared to the baseline, a decrease in the power of the HF component of RRI followed by an increase in its LF component indicated firstly a vagal withdrawal and then sympathetic activity enhancement after successive bouts of exercise. On the other hand, although changes in the LF and HF components of PTT were more similar to those of SBP than of RRI, the LF/HF ratio of SBP was almost 4 times higher than that of PTT. Based on the results, it is therefore suggested that the relationship between SBP and PTT is frequency-dependent.

Due to the increasingly aging population, there is a rising demand for assistive living technologies for the elderly to ensure their health and well-being. The elderly are mostly chronic patients who require frequent check-ups of multiple vital signs, some of which (e.g., blood pressure and blood glucose) vary greatly according to the daily activities that the elderly are involved in. Therefore, the development of novel wearable intelligent systems to effectively monitor the vital signs continuously over a 24 hour period is in some cases crucial for understanding the progression of chronic symptoms in the elderly. In this paper, recent development of Wearable Intelligent Systems for e-Health (WISEs) is reviewed, including breakthrough technologies and technical challenges that remain to be solved. A novel application of wearable technologies for transient cardiovascular monitoring during water drinking is also reported. In particular, our latest results found that heart rate increased by 9 bpm (P

Body area networks (BANs) are emerging as one of the main research trends in recent years, particularly in the area of personal health monitoring. Since health data are private and sensitive information, the security of data transmission within a BAN becomes a critical issue that requires immediate attention. In this paper, we attempt to examine possible attacks of the resource-constrained BANs and present state-of-the-art communication protocols, cryptographic methods, and key management schemes that are useful for BANs security. We will also discuss the problems of existing solutions and possible future research directions on security for BANs. A novel biometric method that utilizes the biological channels (biochannels) to assist secure information transmission within a BAN will also be highlighted and discussed.