J. Mikael Eklund

Real-time signal processing of accelerometer data for wearable medical patient monitoring devices

Elderly and other people who live at home but required some physical assistance to do so are often more susceptible injury causing falls in and around their place of residence. In the event that a fall does occur, as a direct result of a previous medical condition or the fall itself, these people are typically less likely to be able to seek timely medical help without assistance. The goal of this research is to develop a wearable sensor device that uses an accelerometer for monitoring the movement of the person to detect falls after they have occurred in order to enable timely medical assistance. The data coming from the accelerometer is processed in real-time in the device and sent to a remote monitoring station where operators can attempt to make contact with the person and/or notify medical personnel of the situation. The ADXL330 accelerometer is contained within a Nintendo WiiMote controller, which forms the basis of the wearable medical sensor. The accelerometer data can then be sent via Bluetooth connection and processed by a local gateway processor. If a fall is detected, the gateway will then contact a remote monitoring station, on a cellular network, for example, via satellite, and/or through a hardwired phone or Internet connection. To detect the occurrence of ta fall, the accelerometer data is passed through a matched filter and the data is compared to benchmark analysis data that will define the conditions that represents the occurrence of a fall.

Next generation remote critical care through service-oriented architectures: challenges and opportunities

Health care providers and governments are under pressure to maintain and improve the quality of care to an increasing volume of critical care patients at either end of the life cycle, namely premature and ill term babies together with the elderly. The provision of a service of critical care utilizing real time service-oriented architectures has the potential to enable clinicians to be supported in the care of a greater number patients that are, perhaps more importantly, located elsewhere to their intensive care units. This paper presents a review of recent research in the application of computing and IT to support the service of critical care and determines the trends and challenges for the application of real time service-oriented architectures within the domain. It then presents some case study–based research on the design of a service-oriented architecture-based approach to support two aspects of critical care namely elderly care and neonatal intensive care to provide further context to trends and opportunities.

A method for physiological data transmission and archiving to support the service of critical care using DICOM and HL7

An increasing amount of physiological monitoring data is displayed on medical devices around the world every day. By and large, much of this data is lost beyond hand written annotations. Opportunities exist to utilize this data for improved care of those patients within the NICU and for clinical research. The service oriented architecture paradigm offers a way of thinking of critical care through the provision of services of critical care provided by clinicians where patients may be located within or outside their intensive care unit. A major inhibitor to this becoming reality is the lack of a standard for the representation of physiological data as HL7, for example, does not include definitions for time series data. This research proposes a method to represent, transmit and archive physiological data using DICOM and HL7. To enable this, a DICOM file writer and viewer for the physiological time-series data is proposed to specifically enable the storage requirement for these data. This research is then tested within the context of Neonatal Intensive Care.

Nonlinear Model Predictive Control for Omnidirectional Robot Motion Planning and Tracking With Avoidance of Moving Obstacles

This paper presents a nonlinear model predictive control algorithm for online motion planning and tracking of an omnidirectional autonomous robot. The formalism is based on a Hamiltonian minimization to optimize a control path as evaluated by a cost function. This minimization is constrained by a nonlinear plant model, which confines the solution space to those paths which are physically feasible. The cost function penalizes tracking error, control amplitude, and the presence in a potential field cast by moving obstacles and Boards. An experiment is presented demonstrating the successful navigation of a field of stationary obstacles. Simulations are presented demonstrating that the algorithm enables the robot to react dynamically to moving obstacles.

A framework to model and translate clinical rules to support complex real-time analysis of physiological and clinical data

We present a framework to model and translate clinical rules to support complex real-time analysis of both synchronous physiological data and asynchronous clinical data. The framework is demonstrated through a case study in a neonatal intensive care context showing how a clinical rule for detecting an apnoeic event is modeled across multiple physiological data streams in the Artemis environment, which employs IBMs InfoSphere Streams middleware to support real-time stream processing. Initial clinical hypotheses for apnoea detection are modeled using UML activity diagrams which are subsequently translated into Streams SPADE code to be deployed in Artemis to deliver real-time decision support. Our aim is to provide a Clinical Decision Support System capable of identifying and detecting patterns in physiological data streams indicative of the onset of clinically significant conditions that that may adversely affect health outcomes. Benefits associated with our approach include: 1) reduced time and effort on the clinicians part to assess health data from multiple sources; 2) the ability to allow clinicians to control the rules-engine of Artemis to enhance clinical care within their unique environments; 3) the ability to apply clinical alerts to both synchronous and asynchronous data; and 4) the ability to continuously process data in real-time.

Real-time analysis for nonlinear model predictive control of autonomous vehicles

This paper presents an online Nonlinear Model Predictive Control (NMPC) framework for trajectory tracking of autonomous vehicles. The operating environment is assumed to be unknown with various different types of obstacles. A bicycle model is used for the prediction of the future states in the NMPC framework, and a fully nonlinear CarSim vehicle model is used for the simulations. Real-time analysis is presented for a particular situation and the effect of warm initialization of optimization process on the computation time is elaborated. Simulation results show that the NMPC controller provides satisfactory online tracking performance while satisfying the real-time constraints, and warm initialization reduces the optimizer computational load significantly.

Heart disease classification through HRV analysis using Parallel Cascade Identification and Fast Orthogonal Search

Heart rate variability (HRV) is an established indicator of cardiac health. Recent developments have shown the potential of nonlinear metrics for pattern classification of various heart conditions. Evidence indicates that the combination of multiple linear and nonlinear features leads to increased classification accuracy. In our paper, we demonstrate HRV classification using two dynamic nonlinear techniques called Parallel Cascade Identification (PCI) and Fast Orthogonal Search (FOS). We investigate the use of these two techniques for feature extraction from publicly available Physionet electrocardiogram (ECG) data to differentiate between normal sinus rhythm of the heart and 3 undesired conditions: arrhythmia, supraventricular arrhythmia, and congestive heart failure. Results compare well with previous studies which have used more features over the same dataset. We hypothesize that combining PCI and FOS features with traditional HRV features will show further improvement in classification accuracy and so can assist in real-time patient monitoring.

Obstacle avoidance in real time with Nonlinear Model Predictive Control of autonomous vehicles

A Nonlinear model predictive control (NMPC) for trajectory tracking with the obstacle avoidance of autonomous road vehicles traveling at realistic speeds is presented in this paper, with a focus on the performance of those controllers with respect to the look-ahead horizon of the NMPC. Two different methods of obstacle avoidance are compared and then the NMPC is tested in several simulated but realistic tracking scenarios involving static obstacles on constrained roadways. In order to simplify the vehicle dynamics, a bicycle model is used for the prediction of future vehicle states in the NMPC framework. However, a high-fidelity, nonlinear CarSim vehicle model is used to evaluate the vehicle performance and test the controllers in the simulation results. The CPU time is also analyzed to evaluate these schemes for real-time applications. The results show that the NMPC controller provides satisfactory online tracking performance in a realistic scenario at normal road speeds while still satisfying the real-time constraints. In addition, it is shown that the longer prediction horizons allow for better responses of the controllers, which reduce the deviations while avoiding the obstacles, as compared with shorter horizons.

Toward a Big Data Healthcare Analytics System: A Mathematical Modeling Perspective

High speed physiological data produced by medical devices at intensive care units (ICUs) has all the characteristics of Big Data. The proper use and management of such data can promote the health and reduces mortality and disability rates of critical condition patients. The effective use of Big Data within ICUs has great potential to create new cloud-based health analytics solutions for disease prevention or earlier condition onset detection. The Artemis project aims to achieve the above goals in the area of neonatal intensive care units (NICU). In this paper, we proposed an analytical model for an extended version of Artemis system which is being deployed at SickKids hospital in Toronto. Using the proposed analytical model, we predict the amount of storage, memory and computation power required for Artemis. In addition, important performance metrics such as mean number of patients in the NICU, blocking probability and mean patient residence time for different configurations are obtained. Capacity planning and trade-off analysis would be more accurate and systematic by applying the proposed analytical model in this paper. Numerical results are obtained using real inputs acquired from a pilot deployment of the system at SickKids hospital.

A Rule-Based Temporal Analysis Method for Online Health Analytics and Its Application for Real-Time Detection of Neonatal Spells

Neonatal spells are cardiorespiratory events that occur in newborn infants with variable combinations of cessation of breathing, decrease in blood oxygen saturation and decrease in heart rate. A system using real-time temporal analysis of physiological data streams to accurately detect pauses in breathing and changes in heart rate and oxygen saturation for classifying neonatal spells is described. The system uses a multidimensional online health analytics environment that supports the acquisition, transmission and real-time processing of high volume, high rate data. A family of algorithms has been developed using IBM InfoSphere Streams, a scalable middleware component for analysing multiple streams of data in real-time. Respiratory pauses are identified by accurately detecting breaths and calculating time intervals between breaths. Changes in heart rate and blood oxygen saturation are identified by both threshold breaches and the detection of relative change by assessing a sliding baseline and generating alerts when values fall out of range. Events detected in individual signals are synced together based on timestamps and assessed using a classifier based on clinical rules to determine a classification of neonatal spells. The output of these algorithms has been shown, in a single use case study with 24 hours of patient data, to detect clinically significant events in heart rate, blood oxygen saturation and pauses in breathing. The accuracy for detecting these is 97.8%, 98.3% and 98.9% respectively. The accuracy for determining spells classifications is 98.9%. Future research will focus on the clinical validation of these algorithms.