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.

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.

Ankle-Brachial Pressure Index (ABI), the ratio of ankle blood pressure to arm pressure, has been used to assess the severity of peripheral arterial disease (PAD) and to predict major cardiovascular events. This study proposes three indices which can be readily obtained from electrocardiogram and photoplethysmogram, and studies their correlation with ABI in supine and sitting positions. The proposed indices were derived from pulse arrival time (PAT). Specifically, the ratio of PAT measured from the fingertips to PAT measured from the toes of both sides (PATralio), and the relative bilateral differences in PAT measured from the toes of the legs, normalised by average PAT from the two legs (PATdiff1) and by the minimal PAT from one side (PATdiff2) were calculated. The results showed that PATratlois better correlated with ABI compared to PATdiffland PATdff2. The coefficient of determination (R2) between PATratioand ABI is 0.57 when measured in sitting posture, indicating its potential role as an alternative index of ABI for PAD diagnosis. Compared with ABI, the advantages of PATratioare 1) it can be measured at ease with wearable sensors that are available at a relatively low cost; 2) the PAT-derived indices can be measured in a sitting posture which is more convenient to obtain; and 3) it can potentially provide longer term, continuous monitoring of the vascular function.

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.

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.

Wearable sensors have broad applications in many areas. For biomedical applications, they are being actively adopted for human-machine interactive control or health monitoring purposes. This study gives two examples of applying wearable sensors for these biomedical applications by utilizing information from sensor-human-machine interaction and multi-modal sensing. The first example demonstrated the intuitive control of the motions of surgical robots by human arms and hands movements in free space using electromyogram and acceleration measurements. The other one conducted a 20-hour continuous monitoring of multi-modal physiological signals in real life settings using multiple wearable sensors. After automatically removing the motion artifacts from the ambulatory data, median to strong dependence were found between some common cardiovascular parameters (heart rate and pulse amplitude) and the condition of the subject during measurements (psychological status and physical activity level). This study provides the insight that ambulatory monitoring of physiological variables in daily life settings should be interpreted with cautions, and contextual information are needed to standardize the measurement conditions and to get more accurate and reproducible results for better clinical decisions.

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.

Presents an introductory editorial on the special issue for this issue of the publication which examines the fields of biomedical and health informatics.

The ten papers from this special sectoin were presented at the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’14).

This paper provides an overview of recent developments in big data in the context of biomedical and health informatics. It outlines the key characteristics of big data and how medical and health informatics, translational bioinformatics, sensor informatics, and imaging informatics will benefit from an integrated approach of piecing together different aspects of personalized information from a diverse range of data sources, both structured and unstructured, covering genomics, proteomics, metabolomics, as well as imaging, clinical diagnosis, and long-term continuous physiological sensing of an individual. It is expected that recent advances in big data will expand our knowledge for testing new hypotheses about disease management from diagnosis to prevention to personalized treatment. The rise of big data, however, also raises challenges in terms of privacy, security, data ownership, data stewardship, and governance. This paper discusses some of the existing activities and future opportunities related to big data for health, outlining some of the key underlying issues that need to be tackled.

THIS special issue includes seven interesting articles that tackle some of the existing challenges and design issues related to the use of RF and Communication Technologies for wireless implants. An in-body medical device is a miniature device that is inserted in the human body to collect physiological signals and images or to act like a prosthetic device restoring certain body functions. In order for these devices to communicate with the external world, radio frequency (RF) wireless technologies are often used to maintain their operation for a longer period of time. This is achieved by integrating wireless communication technologies within these devices. In some situations, a body worn device is used to receive the medical information from the devices in the human body and then transmit to remote stations for remote medical monitoring.

Flexible and stretchable sensors have recently emerged as an active area of research for designing wearable, implantable and ingestible systems that allow pervasive and unobtrusive health monitoring in mobile health (m-Health) applications. Nevertheless, there lacks systematical study that compares the performances of these new types of sensors with their conventional counterparts. In this study, we reported the fabrication of serpentine-shape, flexible and stretchable electrodes that can be conformally attached to the skin via a printing-transfer process, and we introduced Area Density (AD) as a key parameter to guide the future design of these sensors. Sensors of AD 10, 20 and 40 percentages were designed and fabricated. The performances of these sensors for capturing one type of electrophysiological signals, i.e. electrocardiogram (ECG), were compared against ECG obtained by conventional gold and stainless steel metal clips. The results of this study found that flexible sensors designed with larger AD resulted in ECG of higher signal-to-noise ratio (SNR). In particular, ECG with SNR comparable to those measured by conventional metal clips (SNR>25dB) can be achieved when this new type of flexible sensors were designed with AD=40%. The results of this study shed light on the design of novel wearable and flexible electrodes, which can be used not only for on-body sensing but also in-body measurement inside the gastrointestinal tract.

Summary form only given. Health informatics deals with the acquisition, transmission, processing, storage, and retrieval of information to enhance the quality and efficiency of healthcare such that it becomes personalized, preventive, predictive, pre-emptive, participatory, pervasive, and precise. A major direction in health informatics is to research and develop technologies that enable the identification of health issues at an early stage. This often requires novel and innovative approaches that can be launched for mass surveillance of a large population. Sensing and analysis of physiological signals remains to be one of the core techniques in clinical screening. Many physiological parameters, such as blood pressure, have been proven to be key risk factors of diseases. With recent advancements in sensors and communication networks, measurement of these parameters does not have to be limited to the short periods an individual spent during ad-hoc infrequent clinic visits. Rather, low-cost sensors can be worn by individuals or integrated into the living environment such that health can be managed unobtrusively for extensively long periods. Substantial technical challenges remain to be solved before these methods can be adopted into routine clinical practice, e.g., to invent new sensing principles enabling the unobtrusive monitoring of physiological and health conditions, to ensure the security and privacy of health information from the sensor to system levels to seamlessly connect the sensors of a user to a body sensor network, as well as to design a framework architecture for the overall e-Health services.

Presents an introduction to this new publication and explains is scope, focus, and planned contents.

Despite enormous efforts to prevent cardiovascular disease (CVD) in the past, it remains the leading cause of death in most countries worldwide. Around two-thirds of these deaths are due to acute events, which frequently occur suddenly and are often fatal before medical care can be given. New strategies for screening and early intervening CVD, in addition to the conventional methods, are therefore needed in order to provide personalized and pervasive healthcare. In this special issue, selected emerging technologies in health informatics for screening and intervening CVDs are reported. These papers include reviews or original contributions on 1) new potential genetic biomarkers for screening CVD outcomes and high-throughput techniques for mining genomic data; 2) new imaging techniques for obtaining faster and higher resolution images of cardiovascular imaging biomarkers such as the cardiac chambers and atherosclerotic plaques in coronary arteries, as well as possible automatic segmentation, identification, or fusion algorithms; 3) new physiological biomarkers and novel wearable and home healthcare technologies for monitoring them in daily lives; 4) new personalized prediction models of plaque formation and progression or CVD outcomes; and 5) quantifiable indices and wearable systems to measure them for early intervention of CVD through lifestyle changes. It is hoped that the proposed technologies and systems covered in this special issue can result in improved CVD management and treatment at the point of need, offering a better quality of life to the patient.

The IEEE Transactions on Information Technology in Biomedicine (T-ITB) will be retitled as the IEEE Journal of Biomedical and Health Informatics (J-BHI) starting in January, 2013. The IEEE Transactions on Information Technology in Biomedicine was launched with four issues per year in 1997. After more than a decade of steady growth, the journal ventured into new challenges: open access of publication and rapid expansion in all health informatics-related fields. In this concluding issue of T-ITB the authors would like to take this opportunity to report briefly some historical retrospectives of journal with known statistics of it and to extend a special appreciation from the current editorial office to readers, authors, reviewers, associate editors, Engineering in Medicine and Biology Society (EMBS) relevant committees, IEEE publication staff, and especially two previous Editors-in-Chief for their great contributions to make the Transactions successful. The launching of the J-BHI as the new title of T-ITB is an outcome of the vision of the EMBS's 2011 Publications Committee. The title change and scope revision were accomplished through more than two years of team efforts by T-ITB Editorial Board, EMBS Executive Office, Publication Committee, and AdCom. In the next editorial to be published on January issue of J-BHI, we will discuss the rationale behind the title change and scope revision as well as the grand challenges in health informatics with future perspectives.

Wireless body sensor network (WBSN), a key building block for m-Health, demands extremely stringent resource constraints and thus lightweight security methods are preferred. To minimize resource consumption, utilizing information already available to a WBSN, particularly common to different sensor nodes of a WBSN, for security purposes becomes an attractive solution. In this paper, we tested the randomness and distinctiveness of the 128-bit biometric binary sequences (BSs) generated from interpulse intervals (IPIs) of 20 healthy subjects as well as 30 patients suffered from myocardial infarction and 34 subjects with other cardiovascular diseases. The encoding time of a biometric BS on a WBSN node is on average 23 ms and memory occupation is 204 bytes for any given IPI sequence. The results from five U.S. National Institute of Standards and Technology statistical tests suggest that random biometric BSs can be generated from both healthy subjects and cardiovascular patients and can potentially be used as authentication identifiers for securing WBSNs. Ultimately, it is preferred that these biometric BSs can be used as encryption keys such that key distribution over the WBSN can be avoided.

The use of sensor networks for healthcare, well-being, and working in extreme environments has long roots in the engineering sector in medicine and biology community. With the maturity of wireless sensor networks, body area networks (BANs), and wireless BANs (WBANs), recent efforts in promoting the concept of body sensor networks (BSNs) aim to move beyond sensor connectivity to adopt a system-level approach to address issues related to biosensor design, interfacing, and embodiment, as well as ultralow-power processing/communication, power scavenging, autonomic sensing, data mining, inferencing, and integrated wireless sensor microsystems. As a result, the system architecture based on WBAN and BSN is becoming a widely accepted method of organization for ambulatory and ubiquitous monitoring systems. This editorial paper presents a snapshot of the current research and emerging applications and addresses some of the challenges and implementation issues.

Using the development of the Cardiovascular Health Informatics and Multimodal E-record (CHIME) as an example, the authors have discussed in this editorial note four goals, each with a corresponding technical challenge in health informatics that needs to be overcome in order to better prevent cardiovascular disease (CVD). With collaborative efforts, it is hoped that these barriers and all those unmentioned can be removed such that the problem of CVD can be relieved. Since CVD and common chronic diseases share a number of risk factors, the experience in the development of CHIME will definitely be valuable in formulating solutions to the crisis created by the ageing population and the prevalence of chronic disease on our health care system. Thus we are looking forward to receiving original contributions to T-ITB in the area of health informatics to expediate progress in this area.

Security of the emerging body sensor network (BSN) in telemedicine applications is a crucial problem because personal medical information must be protected against flaws and misdeeds. The solution is, however, nontrivial because lightweight mechanisms have to be deployed to meet the stringent resource constraints of these networks. It has been suggested that the inherent ability of human body to transfer information is a unique and resource-saving method to secure wireless communications within a BSN. For example, physiological characteristics can be captured by individual sensors of a BSN to generate entity identifiers (EIs) for identifying nodes and even securing keying materials, i.e., by a biometric approach. This study demonstrates the performance analysis of such a biometric trait, i.e., the interpulse intervals (IPIs) of heartbeats that were calculated from electrocardiogram and photoplethysmogram of 99 subjects. Based on the characteristics of IPIs, a lightweight generation scheme of EIs is proposed. Individual randomness and group similarity of the generated EIs are then evaluated. False acceptance rate and false rejection rate are also calculated to measure the effectiveness of the proposed identification system. The results suggest that the readily available IPI information can be a good source for generating EIs among BSN nodes.