Joanna Fursse
Brunel University London
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Joanna Fursse.
Information Sciences | 2015
George Lamprinakos; Stefan Asanin; Tobias Brodén; Andrea Prestileo; Joanna Fursse; Konstantinos A. Papadopoulos; Dimitra I. Kaklamani; Iakovos S. Venieris
Software platforms focused on the healthcare monitoring sector have recently attained a great penetration in the ICT market and they certainly constitute a key contributor to the improvement of the elderly peoples quality of life and the reduction of healthcare costs. It is of great importance that the platform allows for the simultaneous health, mental and psychological status evaluation of an elderly person. However, the integration of vital signs monitoring (Telehealth) with behavioral analysis based on home care sensors (Telecare) has not yet been established at a large scale. We describe the design and implementation of such platform that enables the deployment of services to follow-up the patients health status based on a set of monitored parameters per disease and to profile users habits and diagnose deviations from their usual activities. A key aspect of the platform is its Service Oriented Architecture middleware that collects data from heterogeneous Telecare and Telehealth gateways and provides the upper service layers with a unified and standards compliant message. In this way, an integrated view of Telehealth and Telecare data and alerts is made possible into a backend Web Portal where clinicians and operators have access to.
Journal of Telemedicine and Telecare | 2008
Joanna Fursse; Malcolm Clarke; Russell W. Jones; Sneh Khemka; Genevieve Findlay
Summary We have investigated the use of telemonitoring in three long-term conditions: chronic heart failure (CHF), type 2 diabetes and essential hypertension. Participants were provided with a home telemonitoring unit for a 12-week period and entered physiological data each day. The data were sent automatically via the participants telephone line to a server and could be viewed via a web browser. An intervention algorithm was developed to improve the accuracy with which patients requiring intervention were recognized compared to existing systems based on a simple threshold. Thirty patients completed the 12-week trial. One patient dropped out, giving data on 29 patients (mean age 70 years, 17 women). The algorithm prompted a clinical intervention in 11 patients (38%). The average time that elapsed before the first intervention was 47 days (SD 21). Primarily the interventions (72%) resulted in changes to medication and health advice. The results suggest that four weeks is sufficient time in which to recognize the need to intervene clinically and that in 12 weeks it is possible to effect a change towards a target.
BMC Medical Informatics and Decision Making | 2014
Joost de Folter; Hulya Gokalp; Joanna Fursse; Urvashi Sharma; Malcolm Clarke
BackgroundChanges in daily habits can provide important information regarding the overall health status of an individual. This research aimed to determine how meaningful information may be extracted from limited sensor data and transformed to provide clear visualization for the clinicians who must use and interact with the data and make judgments on the condition of patients. We ascertained that a number of insightful features related to habits and physical condition could be determined from usage and motion sensor data.MethodsOur approach to the design of the visualization follows User Centered Design, specifically, defining requirements, designing corresponding visualizations and finally evaluating results. This cycle was iterated three times.ResultsThe User Centered Design method was successfully employed to converge to a design that met the main objective of this study. The resulting visualizations of relevant features that were extracted from the sensor data were considered highly effective and intuitive to the clinicians and were considered suitable for monitoring the behavior patterns of patients.ConclusionsWe observed important differences in the approach and attitude of the researchers and clinicians. Whereas the researchers would prefer to have as many features and information as possible in each visualization, the clinicians would prefer clarity and simplicity, often each visualization having only a single feature, with several visualizations per page. In addition, concepts considered intuitive to the researchers were not always to the clinicians.
Journal of Diabetes and Its Complications | 2015
Vincenzo Lagani; Franco Chiarugi; Dimitris Manousos; Vivek Verma; Joanna Fursse; Kostas Marias; Ioannis Tsamardinos
AIM We present a computerized system for the assessment of the long-term risk of developing diabetes-related complications. METHODS The core of the system consists of a set of predictive models, developed through a data-mining/machine-learning approach, which are able to evaluate individual patient profiles and provide personalized risk assessments. Missing data is a common issue in (electronic) patient records, thus the models are paired with a module for the intelligent management of missing information. RESULTS The system has been deployed and made publicly available as Web service, and it has been fully integrated within the diabetes-management platform developed by the European project REACTION. Preliminary usability tests showed that the clinicians judged the models useful for risk assessment and for communicating the risk to the patient. Furthermore, the system performs as well as the United Kingdom Prospective Diabetes Study (UKPDS) Risk Engine when both systems are tested on an independent cohort of UK diabetes patients. CONCLUSIONS Our work provides a working example of risk-stratification tool that is (a) specific for diabetes patients, (b) able to handle several different diabetes related complications, (c) performing as well as the widely known UKPDS Risk Engine on an external validation cohort.
IEEE Journal of Biomedical and Health Informatics | 2016
Malcolm Clarke; Hulya Gokalp; Joanna Fursse; Russell W. Jones
This study presents a novel dynamic threshold algorithm that is applied to daily self-measured SpO2 data for management of chronic obstructive pulmonary disease (COPD) patients in remote patient monitoring to improve accuracy of detection of exacerbation. Conventional approaches based on a fixed threshold applied to a single SpO2 reading to detect deterioration in patient condition are known to have poor accuracy and result in high false alarm rates. This study develops and evaluates use of a dynamic threshold algorithm to reduce false alarm rates. Daily data from four COPD patients with a record of clinical interventions during the period were selected for analysis. We model the SpO2 timeseries data as a combination of a trend and a stochastic component (residual). We estimate the long-term trend using a locally weighed least-squares (low-pass) filter over a long-term processing window. Results show that the time evolution of the long-term trend indicated exacerbation with improved accuracy compared to a fixed threshold in our study population. Deterioration in the condition of a patient also resulted in an increase in the standard deviation of the residual (σres), from 2% or less when the patient is in a healthy condition to 4% or more when condition deteriorates. Statistical analysis of the residuals showed they had a normal distribution when the condition of the patient was stable but had a long tail on the lower side during deterioration.
international conference on wireless mobile communication and healthcare | 2012
Ioannis Karatzanis; Vasilis Kontogiannis; Emmanouil G. Spanakis; Franco Chiarugi; Joanna Fursse; Russell W. Jones
Type 2 diabetes is increasing worldwide. When compared with other chronic diseases, deaths due directly to type 2 diabetes are less. The problem though, is the mortality rates caused by the consequences of type 2 diabetes; complications that represent a major health burden which may destabilise health economies. Recognised complications are: cardiovascular disease, peripheral vascular disease, renal failure, retinal eye disease, and neuropathy leading to high levels of morbidity and mortality from heart attack, foot ulceration and leg amputation, stroke, renal failure, and blindness. Better care of type 2 diabetes and early recognition and treatment of its complications reduce levels of morbidity and mortality. There is a need to support the diabetic patient in achieving effective glucose control and life-style changes leading to improved nutrition and healthy levels of physical activity, and to early recognize and treat complications. To make this possible and efficient, a patient portal has been developed, as part of the REACTION platform, which supports interactions between the diabetic patient and both their professional and non-professional carers. Introducing the patient portal and the REACTION platform to real-life healthcare systems will empower patients more by increasing their ability to self-manage, improve the quality of their life and the overall management of their diabetes, reduce the risk of developing complications and lessen their use of health services.
e health and bioengineering conference | 2013
Dimitris Manousos; Franco Chiarugi; Vasilis Kontogiannis; Ioannis Karatzanis; Angelina Kouroubali; Emmanouil G. Spanakis; Kostas Marias; Joanna Fursse; Shona Thomson; Russell W. Jones; Vivek Verma; Malcolm Clarke
Like several other chronic diseases the proper and effective management of diabetes requires the full involvement of patients and informal caregivers by implementing self care for personal health maintenance with treatment of diabetes and prevention of complications. Patient empowerment is a necessary pre-requisite of effective disease self-management. Self-management can help people with chronic diseases to remain in the workforce and active members of their community. Programs on chronic disease self-management teach and support patients to identify warning symptoms, measure and evaluate vital signs, decide the most suitable treatment for them, and take medications. In the context of the REACTION project, a diabetes management platform for patients in rural areas was designed and developed. In this paper we present the patient portal, the methodology adopted for the technology evaluation and our preliminary results after an extensive field test on citizens with diabetes.
2014 IEEE Healthcare Innovation Conference (HIC) | 2014
Malcolm Clarke; Joanna Fursse; Hulya Gokalp; Urvashi Sharma; Russell W. Jones
An increasingly aging population is presenting greater prevalence of people with diabetes, co-morbidities and the complications. Moreover, poor management of diabetes increases risk of complications. There is need to monitor these patients more closely to ensure optimum management. However current management is based on simple clinic based blood pressure and HbA1c readings, which prove insensitive to detect problems of lifestyle and habits. We therefore developed a platform that could be deployed to all diabetes patients to take daily blood pressure and blood glucose measurements that were sent automatically to the clinician. Data was reviewed after a two week monitoring period. Those that were deemed well controlled were asked to return the devices, which were cycled to the next patient. Others were asked to make an appointment with the clinician for review. 37% of patients required intervention. When stratified for risk using parameters from the EPR we found the greatest change in HbA1c in the low risk group, with the high risk group having little change. The greatest problem was denial in the recently diagnosed and lapse in others, resulting in poor adherence to medication and lifestyle.
medical informatics europe | 2008
Joanna Fursse; Malcolm Clarke; Russell W. Jones; Sneh Khemka; Genevieve Findlay
International Journal of Integrated Care | 2013
Joanna Fursse; Georgios Lamprinakos; Konstantinos A. Papadopoulos; Russell W. Jones; Malcolm Clarke; Nicole Jones; Andreas Kapsalis; Dimitra I. Kaklamani; Sotirios Patsilinakos; Iakovos S. Venieris; Shona Thomson