Search

Clinical decision support systems are interactive software systems designed to assist clinicians with decision making tasks, such as determining a diagnosis or recommending a treatment for a patient. Clinical decision support systems are a widely researched topic in the Computer Science community but their inner workings are less well understood by and known to clinicians. In this article we provide a brief explanation of clinical decision support systems and provide some examples of real world systems. We also describe some of the challenges to implementing these systems in clinical environments and posit some of the reasons for limited adoption of decision support systems in practice. We aim to engage clinicians in the development of decision support system that can meaningfully help with their decision making tasks and open up a discussion about the future of automated clinical decision support as a part of healthcare delivery.

This paper discusses issues relating to the development and evaluation of the next generation of computerised control systems in healthcare delivery. It will be argued that further increases in the cost-effectiveness of healthcare delivery and the successful implementation of organisational learning models of healthcare can best be achieved if computer systems are developed which go beyond the data management functions that typify current systems. It is further argued that the evaluation parameters of such systems are more fundamental and wide reaching than those normally employed.

This Methodolical Review describes how health geomatics can improve our understanding of the important relationship between location and health, and thus assist us in Public Health tasks like disease prevention, and also in better healthcare service planning. The reader is first introduced to health geography and its two main divisions, disease ecology and healthcare delivery, followed by an overview of the basic concepts and principles of health geomatics. Topics covered include geographical information systems (GIS), GIS modeling, and GIS-related technologies (remote sensing and the global positioning system). We also present a number of real-life health geomatics applications and projects, with pointers to further studies and resources. Finally, we discuss the barriers facing the adoption of GIS technology in the health sector, including data availability/quality issues. The authors believe that we still need to combat many cultural and organizational barriers, including "spatial illiteracy" among healthcare workers, while making the tools cheaper and easier to learn and use, before health geomatics can become a mainstream technology in the health sector like today's spreadsheets and databases.

This paper describes a model of carbon dioxide (CO 2 ) transport in the blood. Equations are used to represent the flow of CO 2 between tissues, blood and lung alveoli, and the chemistry associated with CO 2 buffering. The dynamic model is used to represent the effects of hypo-and hyper-ventilation on end tidal CO 2 concentration (FEC0 2 ). Time constants describing the response to perturbation and equilibrium concentrations of FECO 2 are shown to be consistent with those reported in the literature

Safety and reliability of advice from new computer systems should be confirmed before embarking on prospective hospital trials. This process of preliminary testing is termed 'validation'. Though it forms a fundamental stage in system development, few standards exist for choosing and implementing tests. In the present paper, a validation methodology is developed in the domain of diabetes and intended for general use in chronic health management. It is based on a peer review protocol and incorporates empirical measures indicating: applicability of results to the real environment; variation among doctors; comparisons between doctors' and computer advice; and relative merits of different computer algorithms.

The complexities of the dynamic processes and their control associated with biological and ecological systems offer many challenges for the control engineer. Over the past decades the application of dynamic modelling and control has aided understanding of their complexities. At the same time using such complex systems as test-beds for new control methods has highlighted their limitations (e.g. in relation to system identification) and has thus acted as a catalyst for methodological advance. This paper continues the theme of exploring opportunities and achievements in applying modelling and control in the bio- and ecological domains.

We present a multi-modal reasoning (MMR) methodology that integrates case-based reasoning (CBR), rule-based reasoning (RBR) and model-based reasoning (MBR), meant to provide physicians with a reliable decision support tool in the context of type 1 diabetes mellitus management. In particular, we have implemented a decision support system that is able to jointly exploit a probabilistic model of the glucose-insulin system at the steady state, a RBR system for suggestion generation and a CBR system for patient's profiling. The integration of the CBR, RBR and MBR paradigms allows for an optimized exploitation of all the available information, and for the definition of a therapy properly tailored to the patient's needs, overcoming the single approaches limitations. The system has been tested both on simulated and on real patients' data.

HealthCyberMap (http://healthcybermap.semanticweb.org/) aims at mapping Internet health information resources in novel ways for enhanced retrieval and navigation. This is achieved by collecting appropriate resource metadata in an unambiguous form that preserves semantics.We modelled a qualified Dublin Core (DC) metadata set ontology with extra elements for resource quality and geographical provenance in Prot g -2000. A metadata collection form helps acquiring resource instance data within Prot g . The DC subject field is populated with UMLS terms directly imported from UMLS Knowledge Source Server using UMLS tab, a Prot g -2000 plug-in. The project is saved in RDFS/RDF.The ontology and associated form serve as a free tool for building and maintaining an RDF medical resource metadata base. The UMLS tab enables browsing and searching for concepts that best describe a resource, and importing them to DC subject fields. The resultant metadata base can be used with a search and inference engine, and have textual and/or visual navigation interface(s) applied to it, to ultimately build a medical Semantic Web portal. Different ways of exploiting Prot g -2000 RDF output are discussed.By making the context and semantics of resources, not merely their raw text and formatting, amenable to computer 'understanding,' we can build a Semantic Web that is more useful to humans than the current Web. This requires proper use of metadata and ontologies. Clinical codes can reliably describe the subjects of medical resources, establish the semantic relationships (as defined by underlying coding scheme) between related resources, and automate their topical categorisation.

A prototype computer system utilising a model of carbohydrate metabolism linked to an expert system is described. The prototype which integrates quantitative and qualitative computational methodologies can be used to predict blood glucose profiles and adjust insulin doses in insulin-dependent (type I) diabetic subjects. A feedback loop insulin-dosage optimisation procedure which allows quantitative advice to be generated is also described. Possible clinical applications for the system, which is intended for educational use and clinically as a research tool to try and attain normoglycaemia, are discussed.

Computational modelling is becoming of increasing importance in assisting with, and enhancing, the processes of decision-making in clinical medicine and in health care delivery, processes which depend upon the effective interpretation of data yielded by measurement practice. Using conceptual models of health care delivery, a framework can be established within which the role of specific computational modelling paradigms can be clearly identified. Some of the methodological issues which underpin computer modelling are considered across the range of realizations (mathematical, logical, statistical and graphical) that find application in the clinical and health care domains. Examples are given of both quantitative modelling and qualitative model-based reasoning as important adjuncts to measurement practice.

HealthCyberMap http://healthcybermap.semanticweb.org aims at mapping parts of health information cyberspace in novel ways to deliver a semantically superior user experience. This is achieved through "intelligent" categorisation and interactive hypermedia visualisation of health resources using metadata, clinical codes and GIS. HealthCyberMap is an ArcView 3.1 project. WebView, the Internet extension to ArcView, publishes HealthCyberMap ArcView Views as Web client-side imagemaps. The basic WebView set-up does not support any GIS database connection, and published Web maps become disconnected from the original project. A dedicated Internet map server would be the best way to serve HealthCyberMap database-driven interactive Web maps, but is an expensive and complex solution to acquire, run and maintain. This paper describes HealthCyberMap simple, low-cost method for "patching" WebView to serve hypermaps with dynamic database drill-down functionality on the Web. The proposed solution is currently used for publishing HealthCyberMap GIS-generated navigational information maps on the Web while maintaining their links with the underlying resource metadata base. The authors believe their map serving approach as adopted in HealthCyberMap has been very successful, especially in cases when only map attribute data change without a corresponding effect on map appearance. It should be also possible to use the same solution to publish other interactive GIS-driven maps on the Web, e.g., maps of real world health problems.

Leucine production rate, metabolic clearance rate and oxidation rate were measured in 10 Type 1 (insulin-dependent) diabetic patients after 24 h insulin withdrawal, conventional insulin therapy and an overnight insulin infusion to maintain normoglycaemia, and in 10 control subjects. In the insulin-withdrawn patients, leucine concentration (259 +/- 17 mumol/l), production rate (2.65 +/- 0.29 mumol . min-1 . kg-1) and oxidation rate (0.69 +/- 0.10 mumol . min-1 . kg-1) were significantly greater (p less than 0.001; p less than 0.05; p less than 0.005 respectively) than corresponding values in control subjects (127 +/- 6; 1.81 +/- 0.12; 0.19 +/- 0.02). Following conventional insulin therapy, leucine concentration (162 +/- 12 mumol/l) and oxidation rate (0.43 +/- 0.05 mumol . min-1 . kg-1) were lower than after insulin withdrawal but were still significantly greater than in control subjects (p less than 0.05; p less than 0.005). Although leucine concentration, production rate and metabolic clearance rate were normal after an overnight insulin infusion, leucine oxidation rate was still greater than normal (0.34 +/- 0.06 mumol . min-1 . kg-1; p less than 0.05). These results suggest that increased leucine concentration in insulin deficiency is due to elevated leucine production rate caused by increased proteolysis, and that leucine concentration is restored to normal by insulin treatment.

In this paper, a number of models which have been developed for studying fluid-electrolyte equilibrium and imbalance is presented. Two levels of dynamics and control are considered corresponding to the physiological processes and the incorporation of such processes within the clinical dynamics of patient care. The large-scale simulations presented are used mainly for hypothesis testing or giving insight into the complex physiological dynamics, whereas the clinical models, which are smaller, are used for parameter estimation and predicting the evolving patient state. Computer simulation is central to these model developments in generating time responses for model identification, validation, and prediction. The paper examines the possible clinical application of the various models in the management of fluid-electrolyte disorders and indicates that features of each of them, integrated into a single implementation, could provide a system of practical clinical value.

A simple model of the distribution and metabolism of insulin in vivo has been evaluated using data from insulin infusion into a group of normal subjects. The major rate-limiting step for access to degradation pathways is assumed to consist of binding of the ligand to a single population of insulin receptor sites, except that provision is made for the possibility of linear non-receptor-mediated degradation and for the phenomenon of negative cooperativity. The model has been shown to accommodate the non-linearity of insulin metabolism, allows, evaluation of receptor association and dissociation constants and provides for the first time an estimate of total accessible receptor number in the intact organism. For normal fasting man the model predicts 1.00 +/- 0.05 nmol accessible binding sites/kg (mean +/- SD).

The paper reviews the various control mechanisms to be found in chemical reactions occurring in man. The concept of compartmental analysis is discussed and the unit processes of biochemistry are considered, e.g. enzymic reactions, expanding systems, transport systems. Modelling techniques are discussed with particular reference to plasma protein metabolism and bilirubin metabolism.