This dissertation investigates the very important and current problem of modelling human expertise. This is an apparent issue in any computer system emulating human decision making. It is prominent in Clinical Decision Support Systems (CDSS) due to the complexity of the induction process and the vast number of parameters in most cases. Other issues such as human error and missing or incomplete data present further challenges. In this thesis, the Galatean Risk Screening Tool (GRiST) is used as an example of modelling clinical expertise and parameter elicitation. The tool is a mental health clinical record management system with a top layer of decision support capabilities. It is currently being deployed by several NHS mental health trusts across the UK. The aim of the research is to investigate the problem of parameter elicitation by inducing them from real clinical data rather than from the human experts who provided the decision model. The induced parameters provide an insight into both the data relationships and how experts make decisions themselves. The outcomes help further understand human decision making and, in particular, help GRiST provide more accurate emulations of risk judgements. Although the algorithms and methods presented in this dissertation are applied to GRiST, they can be adopted for other human knowledge engineering domains.

The patient health record is an essential information source for the management and delivery of patient care services. Paper-based records are problematic with issues such as illegibility, missing data, double data entry and difficulty with information retrieval. With the advent of the Health Insurance Portability and Accountability Act (HIPAA) the Kingdom of Saudi Arabia introduces as part of healthcare reform, the Electronic Health Record (EHR) has been introduced in order to enhance accountability and efficiency. The King Faisal Specialist Hospital & Research Centre (KFSH&RC) was the first organization to implement the EHR. However, to date, the actual impact of ERR within KFSH &RC has not been explored or studied. Therefore, the aim of this study was explore and analyse the issues surrounding the implementation and impact of EHR. The study will also evaluate the role of senior managers towards the EHR planning. Qualitative research was chosen using interpretative phenomenology as the selected methodology. Information for the study was collected using semistructured interviews with four senior managers and six patients. Three focus group interviews were also conducted with six healthcare provider middle managers in each group. The total sample was twenty eight participants. Interpretative Phenomenological Analysis and an update DeLone & McLean and Petter IS Success Models were used as the theoretical framework for analysis. The study identified three categories of impact including positive and negative issues which impacted upon staff, patients, and KFSH&RC organization. The most frequently mentioned benefits were quick data retrieval, ease and speed of data input, ease of access, improved format and content of records, enhanced communication with external healthcare providers (i.e. nurses and physicians), more infotmation about patients, better communication among internal staff, and increased patient safety. Negative issues were related to the role of senior managers and inadequate training for healthcare providers, ignorance of the patient's voice, lack of initiate cultural change and the absence of pre-post test tools to measure the outcome of healthcare quality. The quality of the system related to slowness and shutdown plus organizational difficulties related to different software platforms. Those negative impacts discouraged staff members from using the system but the overall benefits led to a smooth organizational transition to EHR. All patients were satisfied with this transition.

Driven by growing real-world application 'such as healthcare challenges, accelerometry-based activity recognition has been widely studied as a potential context-aware subsystem for the future pervasive healthcare system. Reliable, accurate recognition and energy efficiency to enable long-term and non-intrusiveness activity monitoring are the key issues for practical use in healthcare applications. A great number of activity recognition systems have been proposed focusing on sensor node design and recognition algorithm development to achieve good classification performance, while the trade-offs between recognition accuracy and energy efficiency has not been investigated in depth. This research investigates this issue by comparing on-node and off-node activity recognition schemes through a practical development. The main contribution of this research is concluded as follows. Firstly, the trade-offs between classification accuracy and energy efficiency is raised as the key issue in sensor based activity recognition system to tackle the real world application challenges. Then this research presents a systematic, empirical design process for optimizing an activity recognition system with respect to the above issue. Such design process involves defining application, designing hardware platform, developing classification recognition algorithm, energy consumption modelling and real system performance evaluation. On-node and off-node classification schemes are the two design philosophies which are compared in this process. This research performs the first step to strike the energy-accuracy trade-offs in body sensor based activity recognition system. The future work should be generalised in two ways. First, different design schemes between the two extreme design philosophies are to be analysed. Then, more classification algorithms should be investigated.

Background: The concept of informed consent is one that is not clearly elucidated. Prior to any invasive procedure, surgeons have a legal obligation to inform patients about the procedure. Traditionally, this has involved a discussion with a surgeon , occasionally supplemented by written leaflet information directed at the specific procedure. Objective: The main objective was to create, develop and evaluate an interactive upper limb surgery website with an anatomical three dimensional visualisation model. The purpose of this was to compare the use and effectiveness of an oral consultation alone and an oral consultation with a web-based visualisation package on the rate of information retention in patients undergoing carpal tunnel decompression. Methods: This was a prospective study with 50 participants who underwent a standard oral consultation. Detailed information was given about the indication, the probable complications and the details of the forthcoming carpal tunnel decompression procedure. There was a post consultation questionnaire measuring information retention of the standard risks of carpal tunnel decompression. This was then followed with a visualisation intervention (standardised information supported by an interactive three dimensional hand website and carpal tunnel model). Information retention was measured following the exposure to the multimedia package. The main outcome measure was patient's immediate information retention of the risks of surgery. Results: Patients who had the oral consultation and visualisation had higher information retention of the risks of surgery. Conclusions: Using an interactive computerised hand surgery visualisation model increased the information retention of the patients. The presentation of the visualised information in the Visualisation Group did not require significantly more time than the standard consultation. Discussion: Patients want more information and greater involvement in decisions about their treatment according to The Healthcare Commission Survey results from 2004 - 2010. The results of the survey reveal that patients are being discharged without enough information. Risks, benefits and expected outcomes of treatments still need to be communicated better to patients. Given the substantial increase in recent years of medico-legal claims against surgeons in the United Kingdom with Plastic Surgery traditionally one of the most vulnerable, computerised visualisation may provide a means of improving the consent process thereby decreasing litigation,

No description available.

No description available.

The demand and utilisation of telemedicine-based care is increasingly in demand due to the highly amplified number of populations striving towards a country life and remote location living style. Additionally, the financial climate, limited resources and the constantly growing population around the globe have prompted an interest from various governing bodies to reform and seek alternative methods for delivering high quality health care. The technological advancements and the increase of communication innovations have made telemedicine a promising solution for many issues faced by the current health care systems. Musculoskeletal (MSK) issues and injuries often present the largest number of cases amongst General Practitioners COPs) which tend to need monitoring after any surgical intervention or rehabilitation process. Yet the gait analysis of each patient is time-consuming and costly if the patients are located away from the medical and city centres. The technological innovations in motion-capture (Mo-Cap) systems have made it possible to acquire and collect complex motion data for biomechanics of musculoskeletal (MSK) structures. Yet the requirement of specialised costly equipment, professional setup, training and allocation of a dedicated large space rendered these techniques ideal only for a laboratory environment. Such laboratories are most commonly situated at a designated facility which requires the patients to travel to and from it routinely. Due to the limitation of such facilities, patients living in isolated and rural areas have limited or no access to this triage. Contemporary technological breakthroughs, related to cameras, projectors and videogames fuelled the development of cost-efficient, consumer-based peripherals offering Markerless motion capture techniques. Off-the-shelf devices such as Microsoft "Kinect" could be utilised efficiently for a fraction of the typical Mo-Cap suites price with insignificant difference in the tracking quality for the majority of the tracking activities. Mass developments of videogames, Virtual Reality (VR) and 3D programs have made it possible for 3D engines to be utilised across various industries as common platforms for real-time visualisation purposes. This has prompted medical information to be presented in a much-improved manner by the use of photorealistic 3D models and user-friendly interfaces. Early attempts to utilise 3D medical data-set in real-time environments have been limited or designed for a set purpose. Several systems have been designed for educational rationale and even contain visually appealing 3D data-sets but are velY restrictive in their functionality. Although they may illustrate details of human anatomy and provide users with enriched content and information, the restrictive system design renders them unsuccessful for adaptation and cannot be employed for gait analysis, rehabilitation and diagnosis purposes. Other systems have been designed for gait analysis and rehabilitation purposes and have been employed by the industry in various disciplines. Such systems are designed to work with high-end expensive tracking hardware, only support specific file formats and lack detailed visually appealing 3D content for the user. Furthermore they do not support off-the-shelf devices such as Microsoft "Kinect" therefore cannot be used in conjunction with such devices. However there have been some initial amateur attempts to perform gait analysis using off-the-shelf devices. But they are very limited with complex customised interfaces, have very limited functionality and an inaccurate visualisation and representation of the human anatomy. Due to these limitations a telemedicine based system has not been implemented in the past.

This research details the use of Open Design to enable participation in the conceptualisation, design and development of medical products for those who are excluded by their chronic health condition. The research was directed according to the Action Research methodology outlined by Checkland & Holwell (1998); Action Research being highlighted by Archer (1995) as a method compatible for practice-led design research. Open design directed the design practice, which consisted of a long case study spanning 18 months from February 2012, through to July 2013. This case study, dubbed AIR involved the creation of a bespoke online social network, recruitment of people living with cystic fibrosis, and the facilitation of collaborative design work resulting in prototype medical devices based on the lived experience of the participants. The work involves research into design within health as the context for this research. In order to place design in this wider context, it has been tempting to adopt the mantle Evidence Based Design (Evans, 2010) - however in this research the position of design as phronesis, in a similar manner to health practice (Montgomery, 2005) is adopted. This allows for an alignment of the work done in both fields, without the problematic associations with an evidence hierarchy (Gaver & Bowers, 2012; Holmes, Murray, Perron, & Rail, 2006).The contribution to knowledge is an Open Medical Products Methodology, consisting of the artefacts supporting the evidence of the methodology's ability to foster genuine participation amongst those who are excluded from traditional participatory design. The artefacts constituting this submission are this thesis, the reflective log kept during the research (Appendix A), the prototypes from the collaborative research (Appendix B), and the online social network that contained the work (AIR1). The Open Medical Products Methodology is expected to be of interest primarily to designers of medical products, design management and policymakers, although Open Design as a product methodology has appeal to other sectors and the future work into standardisation, regulation, distributed manufacture and recruitment detailed at the conclusion of this thesis has application broader than the medical field.

No description available.

This research critically analyses the different types of clinical data representation used in modelling Clinical Information Systems (CIS) and their limitations. It identifies space complexity, information overload, performance degradation, erroneous data retrieval and transmission as some of the main challenges caused by inappropriate data representation. Literature reviewed, indicated that object-oriented Health Level 7 (HL7), Entity Attribute Value (EAV), Advanced ERD with XML, and ERD –FOL (First Order Logic) are some of the contemporary methods used in modelling and optimising CIS. However, these approaches do not address the space complexity and information overload issues because of the multi-dimensional, complex large-scale nature of clinical datasets. Therefore, this research proposes a unique framework that uses object-oriented (UML) technique and combinatorial multiple attribute utility theory (CMAUT) as a new clinical data re-representation. In the CMAUT framework, the human organs, their multiple attributes and relationships are modelled using classes. The attributes of each organ class are written as logical expressions using CMAUT concepts, which are linked to each other with logical connectors AND for complementary organs such as cardiovascular and OR for substitutable organs like kidneys. The logical expressions are converted into mathematical format, which serves as the utility objective function that is optimised using linear programming method subject to a set of constraint matrix. The constraint matrix is generated by transforming the multiple attributes in the CMAUT expressions into algebraic expressions by applying an algorithm that uses unit matrix and Raman transformation table. The output of the framework gives a set of attribute values, which optimal value maximises the overall utility of the objective function in the combinatorial organs. The algorithm maps the resultant attribute values to the appropriate attributes of the organs to determine the optimal amount of data required to be retrieved for primary health care investigation. The framework retrieves and transmits only needed data for investigation thus reducing the information overload and space complexity in the CIS. The framework was implemented using the MATLAB software and validated with clinical data from the cardiovascular disease survey in England report. Functionality test conducted, revealed that for complementary organs the space complexity is θ (n + 1) using the framework and θ (2n) without the framework. Substitutable organs gave an exponential expansion of θ (2n) in both cases. Simulation conducted showed that the mean size of the data retrieved for investigation using the framework is 463.5 bytes as compared to 1216.6 bytes without it. Statistical tests carried out using the output data from the framework gave a p-value of 0.000. Hence the hypothesis that the amount of data required for primary care health investigation can be reduced when the clinical data is re-represented with UML/CMAUT and optimised using LP based algorithm is statistically significant. For hypertension disease, by converting the optimal values from the framework into percentages give results similar to the percentage risk of the user been hypertensive. The output values were benchmarked against Framingham web based heart risk calculators and statistically analysed. Hence, the novelty of the framework is that it can be used for optimising CIS, as a multi-attribute decision tool and as an epidemiological prediction model for detecting high blood pressure diseases.