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.

The complexity of the discharge planning process is such that it is often difficult to achieve in a totally efficient and effective manner. In this paper a systems approach is adopted in analysing the discharge planning process in a general surgical ward in order to understand better the nature of this complexity. Adopting a soft systems methodology it is shown that the major issues to be addressed relate to the need for a more seamless service provision and more effective utilisation of resources. Conceptual models are formulated which enable comparison to be made between current provision and the issues that need to be addressed. This in turn results in the creation of an agenda of items for change, from cultural, organisational and technological perspectives, which can be considered in terms of their feasibility and desirability. Key proposals highlighted, so as to improve discharge planning, include: the need for greater co-operation between the many healthcare professions involved; the adoption, particularly on the part of nursing staff, of a more holistic approach with regard to the needs of their patients; enhancing the utilisation of nursing staff; and moving towards a greater adoption of information and communication technologies as a means of achieving more effective communication. More generally, the paper provides an example of the role that soft systems analysis can play as an aid in dealing with the complexities of healthcare processes and their management.

Effective management of diabetes mellitus requires the processing and interpretation of blood glucose, insulin and other lifestyle data. This paper presents a web-based diabetes management system (DiabNet), developed to provide instant access to the electronic diabetes database and real-time information for healthcare professionals in order to facilitate their decision-making. DiabNet offers innovative online diabetes management involving online appointment and consultation. It integrates portable glucometer, handheld computer, mobile phone and Internet access as a combined telecommunication and mobile computing solution for diabetes management. Active Server Pages (ASP) embedded with advanced ActiveX controls and VBScript were programmed to allow remote data upload, retrieval and interpretation. This intelligent system can be personalized to the needs of the individual patient, incorporating appropriate historic trends in blood glucose data and with the potential for including an adaptive capability. Internet-based learning features, together with a video teleconferencing component make the DiabNet website an informative platform for teleconsultation. Security steps have also been taken to protect sensitive patient information and the authentication of registered user.

Recent advances in information and communication technology allow the design and testing of new models of diabetes management, which are able to provide assistance to patients regardless of their distance from the health care providers. The M2DM project, funded by the European Commission, has the specific aim to investigate the potential of novel telemedicine services in diabetes management. A multi-access system based on the integration of Web access, telephone access through interactive voice response systems, and the use of palmtops and smart modems for data downloading has been implemented. The system is based on a technological platform that allows a tight integration between the access modalities through a middle layer called the multi-access organizer. Particular attention has been devoted to the design of the evaluation scheme for the system: A randomized controlled study has been defined, with clinical, organizational, economic, usability, and users' satisfaction outcomes. The evaluation of the system started in January 2002. The system is currently used by 67 patients and seven health care providers in five medical centers across Europe. After 6 months of usage of the system no major technical problems have been encountered, and the majority of patients are using the Web and data downloading modalities with a satisfactory frequency. From a clinical viewpoint, the hemoglobin A1c (HbA1c) of both active patients and controls decreased, and the variance of HbA1c in active patients is significantly lower than the control ones. The M2DM system allows for the implementation of an easy-to-use, user-tailored telemedicine system for diabetes management. The first clinical results are encouraging and seem to substantiate the hypothesis of its clinical effectiveness.

A telemedicine system for home haemodialysis was designed using a systems approach and a feedback model to produce the hardware and software specifications. Preliminary clinical trials at four European locations involved 29 patients and 305 sessions of haemodialysis. The evaluation included an evaluability assessment and formative evaluation. Central to the methodology was the detailed specification of a stakeholder/evaluation criterion matrix. Preliminary results indicated that the telemedicine system was capable of satisfying the requirements of formative evaluation as a precursor to evaluating its overall worth.

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.