Interactive tele-radiological segmentation systems for treatment and diagnosis.

Telehealth is the exchange of health information and the provision of health care services through electronic information and communications technology, where participants are separated by geographic, time, social and cultural barriers. The shift of telemedicine from desktop platforms to wireless and mobile technologies is likely to have a significant impact on healthcare in the future. It is therefore crucial to develop a general information exchange e-medical system to enables its users to perform online and offline medical consultations through diagnosis. During the medical diagnosis, image analysis techniques combined with doctor's opinions could be useful for final medical decisions. Quantitative analysis of digital images requires detection and segmentation of the borders of the object of interest. In medical images, segmentation has traditionally been done by human experts. Even with the aid of image processing software (computer-assisted segmentation tools), manual segmentation of 2D and 3D CT images is tedious, time-consuming, and thus impractical, especially in cases where a large number of objects must be specified. Substantial computational and storage requirements become especially acute when object orientation and scale have to be considered. Therefore automated or semi-automated segmentation techniques are essential if these software applications are ever to gain widespread clinical use. The main purpose of this work is to analyze segmentation techniques for the definition of anatomical structures under telemedical systems.

Estimating the success of e-health collaborative services: the THEMIS framework.

This study proposes a prototype framework (THEMIS) for estimating algebraically the success (S) of the electronic health collaborative services (e-HCS) and examines two hypotheses: first, that the S estimation of an e-HCS, developed by a third-party vendor, demands a 'shrunk formative model' and second that causal relationships between the involved dimensions (FFP, CO, COSTS) do exist, and their parameters affect the S - from weakly to strongly and vice-versa. A formative model was shrunk to generate three causal dimensions ('Collaborators Objections', 'Costs', 'Fitness for Purpose'). Then, the new framework (THEMIS) was enriched with a causal loop diagram, a prototype scoring method, (termed 'polarisation method') and 42 questions. In order to investigate the feasibility of the THEMIS framework, we estimated the S of 15 e-HCSs and the algebraic outcomes (E(S)) were compared - one by one - with usage categories produced by a commercial software. Our findings supported the initial hypotheses. The S was estimated with accuracy; for the e-HCSs with a weak E(S) the commercial software verified that they remained idle several times during the 11-month evaluation period, whereas the e-HCS with a strong E(S) the commercial software verified that they were used frequently. Frameworks, such as the one proposed, which are based on both qualitative and quantitative methods, may provide significant support on the S estimation field.

Portable biomedical devices: a critical issue during telecare services design.

OBJECTIVES: The selection of a portable biomedical device (PBD) is a key issue regarding telecare service design. The objective of this study is to investigate the accuracy parameters of a PBD under different settings and levels. METHODS AND MATERIALS: By using a commercial PBD, trials were performed in a referral cardiology center and on the Olympia Explorer of the Royal Olympia Cruises, and the Superfast XII of Superfast Ferries. Data were collected (February 2004 - June 2006) by performing: (1) 'in hospital' standalone trials; (2) 'in hospital' comparative trials; and (3) 'on board' trials. Semistructured interviews were also conducted with several subjects, their cardiologists and crewmembers. RESULTS: We investigated the accuracy parameters, namely the data precision (DP), the peripheral modules reliability (PMR) and the data transmission quality (DTQ). Although the outcomes of the comparative trials, via a statistical method verifying the DP (more than 95%), the trials 'on board' and 'in hospital' revealed a number of critical variables for the PMR and DTQ parameters. CONCLUSION: Telecare services design has accuracy parameter investigation needs. These parameters should be investigated simultaneously, while a compromise between them can act as a driving force to the telecare services success. The compromise is achieved by a smooth fit between DP and PMR with this fit varying within settings and levels.

Tracing and cataloguing knowledge in an e-health cardiology environment.

In an e-health cardiology environment, the current knowledge engineering systems can support two knowledge processes; the knowledge tracing, and the knowledge cataloguing. We have developed an n-tier system capable of supporting these processes by enabling human collaboration in each phase along with, a prototype scalable knowledge engineering tactic. A knowledge graph is used as a dynamic information structure. Biosignal data (values of HR, QRS, and ST variables) from 86 patients were used; two general practitioners defined and updated the patients' clinical management protocols; and feedback was inserted retrospectively. Several calibration tests were also performed. The system succeeded in formulating three knowledge catalogues per patient, namely, the "patient in life", the "patient in time", and the "patient in action". For each patient the clinically accepted normal limits of each variable were predicted with an accuracy of approximately 95%. The patients' risk-levels were identified accurately, and in turn, the errors were reduced. The data and the expert-oriented feedback were also time-stamped correctly and synchronized under a common time-framework. Knowledge processes optimization necessitates human collaboration and scalable knowledge engineering tactics. Experts should be responsible for resenting or rejecting a process if it downgrades the provided healthcare quality.

Designing and redesigning medical telecare services: a forces-oriented model.

OBJECTIVES: Medical telecare services' designing and redesigning still remains a challenging issue since it often depends on how a number of socio-technological issues are framed. This work has two key objectives; the former is to theoretically analyze the nature of a telecare environment by developing a model that reveals potential areas of analysis and the latter is to support designing and redesigning medical telecare services by formulating a strategy as well as a number of 'state of the art' guidelines. METHODS: We have extended Leavitt's diamond to develop a model capable of accurately reflecting the telecare environment building dimensions as well as their interactions. This model depends on the i) technology, ii) collaborators, iii) tasks, iv) structure, v) social forces, and the vi) procedure dimensions. Taking this model as a core element we have proposed a service designing and redesigning strategy formulating, in parallel, six scalable dimension-oriented guidelines. RESULT: During the two-year period (2003-2005) an enormous amount of data was collected (by active participating in two EU projects, by conducting semistructured interviews, by performing onsite observations as well as by reviewing 78 previous projects) and classified, structuring six guidelines. These guidelines can be considered as the 'state of the art' to support future services' design and redesign. CONCLUSIONS: This work considering the telecare environment as a multi-dimensional, operational organization has put the focus on accurate telecare services' design and redesign. The parameters are not limited, by any means, and are drawn from experience of designing services in a variety of telecare domains. The optimal parameter combination must be chosen according to the aim of each telecare procedure. Further research is needed to determine the minimum parameters to support telecare service design.