Factors influencing the transferability of medical decision support systems

Transferability is a key issue in the development and implementation of medical decision support systems. Such systems have up to now tended to be confined to the development site. Transferability represents the integrated effect of several more basic attributes of Decision Support Systems. These attributes can be considered to belong to two main groups: those concerned with the Medical Domain (of the system) and those concerned with the Information Technology by which the System functions. Among the Domain issues the most important are: Epidemiology, Terminology and Methodology. Concerning the Information Technology issues the most important are: Knowledge Acquisition and Representation methods, Database design and integration with inference mechanism. The effect of each of the individual factors is considered by illustrations from the literature and by studying the results of recent experiments where databases and decision support systems from different countries are interchanged. This exercise allows some planning in the design of future systems with the aim of improving overall transferability and therefore applicability.     

Malaria elimination: moving forward with spatial decision support systems

Operational challenges facing contemporary malaria elimination have distinct geospatial elements including the need for high-resolution location-based surveillance, targeted prevention and response interventions, and effective delivery of essential services at optimum levels of coverage. Although mapping and geographical reconnaissance (GR) has traditionally played an important role in supporting malaria control and eradication, its full potential as an applied health systems tool has not yet been fully realised. As accessibility to global positioning system (GPS), geographic information system (GIS) and mobile computing technology increases, the role of an integrated spatial decision support system (SDSS) framework for supporting the increased operational demands of malaria elimination requires further exploration, validation and application; particularly in the context of resource-poor settings.     

A wheat canopy model for use in disease management decision support systems

A model is described which predicts those aspects of wheat canopy development and growth which are influential in determining the development of epidemics of foliar pathogens, the efficacy of foliar applied fungicides and the impact of disease on yield; specifically the emergence, expansion and senescence of upper culm leaves in relation to anthesis date. This focus on upper leaves allowed prediction of leaf emergence dates by reference to anthesis, rather than sowing. This avoided the step changes in flag leaf emergence date with temperature, reported with earlier models, without the additional complexity of a stochastic approach. The model is designed to be coupled to models of foliar disease, where the primary effect on yield is via reduction in green canopy area and hence interception of photosynthetically active radiation. Mechanisms were incorporated to allow observations of crop development during the growing season to update state variables and adjust parameters affecting future predictions. The model was calibrated using experimental data, and validated against independent observations of crop development on four wheat cultivars across seven contrasting sites in the UK. Anthesis date and upper culm leaf emergence were always predicted within one week of their observed dates.     

A foliar disease model for use in wheat disease management decision support systems

A model of winter wheat foliar disease is described, parameterised and tested for Septoria tritici (leaf blotch), Puccinia striiformis (yellow rust), Erysiphe graminis (powdery mildew) and Puccinia triticina (brown rust). The model estimates disease‐induced green area loss, and can be coupled with a wheat canopy model, in order to estimate remaining light‐intercepting green tissue and hence the capacity for resource capture. The model differs from those reported by other workers in three respects. First, variables (such as weather, host resistance and inoculum pressure) that affect disease risk are integrated in their effect on disease progress. The agronomic and meteorological data called for are restricted to those commonly available to growers by their own observations and from meteorological service networks. Second, field observations during the growing season can be used both to correct current estimates of disease severity and to modify parameters that determine predicted severity. Third, pathogen growth and symptom expression are modelled to allow the effects of fungicides to be accounted for as protectant activity (reducing infections that occur postapplication) and eradicant activity (reducing growth of presymptomatic infections). The model was tested against data from a wide range of sites and varieties and was shown to predict the expected level of disease sufficiently accurately to support fungicide treatment decisions.     

An engineering approach to modelling, decision support and control for sustainable systems

Engineering research and development contributes to the advance of sustainable agriculture both through innovative methods to manage and control processes, and through quantitative understanding of the operation of practical agricultural systems using decision models. This paper describes how an engineering approach, drawing on mathematical models of systems and processes, contributes new methods that support decision making at all levels from strategy and planning to tactics and real-time control. The ability to describe the system or process by a simple and robust mathematical model is critical, and the outputs range from guidance to policy makers on strategic decisions relating to land use, through intelligent decision support to farmers and on to real-time engineering control of specific processes. Precision in decision making leads to decreased use of inputs, less environmental emissions and enhanced profitability-all essential to sustainable systems.     

Expert systems and the pancreatic cancer problem: decision support in the pre-operative diagnosis

In this paper, after reviewing the main issue in artificial intelligence, decision support systems, medical decision-making, expert systems and some of their applications in medicine, we focus on the diagnostic aspect of pancreatic cancer. We briefly examine the most significant applications both from the oncological and from the diagnostic point of view. We discuss the medical problems mentioning incidence and mortality, aetiological factors and diagnosis, considering the roles of surgery and adjuvant therapies. Finally we justify the decision to develop an expert system in such a medical domain and discuss the SPES (Surgical Pancreatic Expert System) project, its parts dealing with the different medical phases of pancreatic cancer diagnosis and therapy: pre-operative, intra-operative and adjuvant therapies. In particular we discuss diagnostic aspects of pancreatic cancer disease, pointing out the aims of the project, methodologies, tools used and future developments.     

Computerized clinical decision support systems for chronic disease management: A decision-maker-researcher partnership systematic review

Background

The use of computerized clinical decision support systems (CCDSSs) may improve chronic disease management, which requires recurrent visits to multiple health professionals, ongoing disease and treatment monitoring, and patient behavior modification. The objective of this review was to determine if CCDSSs improve the processes of chronic care (such as diagnosis, treatment, and monitoring of disease) and associated patient outcomes (such as effects on biomarkers and clinical exacerbations).

Methods

We conducted a decision-maker-researcher partnership systematic review. We searched MEDLINE, EMBASE, Ovid's EBM Reviews database, Inspec, and reference lists for potentially eligible articles published up to January 2010. We included randomized controlled trials that compared the use of CCDSSs to usual practice or non-CCDSS controls. Trials were eligible if at least one component of the CCDSS was designed to support chronic disease management. We considered studies 'positive' if they showed a statistically significant improvement in at least 50% of relevant outcomes.

Results

Of 55 included trials, 87% (n = 48) measured system impact on the process of care and 52% (n = 25) of those demonstrated statistically significant improvements. Sixty-five percent (36/55) of trials measured impact on, typically, non-major (surrogate) patient outcomes, and 31% (n = 11) of those demonstrated benefits. Factors of interest to decision makers, such as cost, user satisfaction, system interface and feature sets, unique design and deployment characteristics, and effects on user workflow were rarely investigated or reported.

Conclusions

A small majority (just over half) of CCDSSs improved care processes in chronic disease management and some improved patient health. Policy makers, healthcare administrators, and practitioners should be aware that the evidence of CCDSS effectiveness is limited, especially with respect to the small number and size of studies measuring patient outcomes.     

Environmental decision support systems: A new approach to support the operation and maintenance of horizontal subsurface flow constructed wetlands

This paper describes the development and operation of an Environmental Decision Support System (EDSS) to improve the operation and maintenance of horizontal subsurface-flow constructed wetlands (EDSS-maintenance). Constructed wetlands (CWs) allow wastewater treatment in a sustainable manner since they involve low energy consumption, low construction and functioning costs and low environmental impact. However, operation and maintenance activities are essential to guarantee reliability in CWs performance. The definition of operation and maintenance protocols depends on several quantitative and qualitative aspects such as wastewater treatment plant configuration, CW design, influent characteristics, sensitivity of the receiving media, etc. Bearing this in mind and considering the limited technical knowledge about CWs, the need for a new tool to support CW performance is clear. In this sense, EDSSs offer a new approach because they can tackle problems of complex and uncertain systems. The EDSS-maintenance provides operation and maintenance manuals specifically defined for every CW. To achieve it, the required knowledge was implemented within a rule-based system, which forms the backbone of the EDSS. Several features presented in this paper demonstrate how the EDSS-maintenance provides a proper platform to support the necessary collaborative work in the ecological engineering problem of horizontal subsurface flow CWs operation and maintenance.     

Computer-aided decision support in clinical medicine

This paper reviews the problems and prospects involved in providing computer-aided decision support in clinical medicine. First, the evaluation of medical innovation is discussed. It is suggested that there are three criteria by which an innovation may be judged, namely (1) a need for the innovation, (2) the ability of the innovation to fulfil that need and (3) the ability to do so without transgressing practical, ethical or legal boundaries. These problems are addressed in turn. The paper suggests, taking one area of clinical medicine as an example (acute abdominal pain) there is a clear need for decision support — since the area is not handled well by doctors in current practice. Evidence is adduced to suggest that the computer can provide decision support and do so without transgressing professional, ethical or legal boundaries. The obstacles to progress, which stand in the way of widespread implementation are briefly discussed. These are lack of medical terminology, poor man-machine interface and above all a lack of co-ordination. Finally, it is suggested that the most valuable facet of current systems is the discipline and precision in data collection they impose upon practicing doctors.     

Computerized clinical decision support systems for drug prescribing and management: A decision-maker-researcher partnership systematic review

Background

In the past forty years, many gains have been made in our understanding of the concept of research utilization. While numerous studies exist on professional nurses' use of research in practice, no attempt has been made to systematically evaluate and synthesize this body of literature with respect to the extent to which nurses use research in their clinical practice. The objective of this study was to systematically identify and analyze the available evidence related to the extent to which nurses use research findings in practice.

Methods

This study was a systematic review of published and grey literature. The search strategy included 13 online bibliographic databases: Cochrane Database of Systematic Reviews, Cochrane Central Register of Controlled Trials, MEDLINE, CINAHL, EMBASE, HAPI, Web of Science, SCOPUS, OCLC Papers First, OCLC WorldCat, ABI Inform, Sociological Abstracts, and Dissertation Abstracts. The inclusion criteria consisted of primary research reports that assess professional nurses' use of research in practice, written in the English or Scandinavian languages. Extent of research use was determined by assigning research use scores reported in each article to one of four quartiles: low, moderate-low, moderate-high, or high.

Results

Following removal of duplicate citations, a total of 12,418 titles were identified through database searches, of which 133 articles were retrieved. Of the articles retrieved, 55 satisfied the inclusion criteria. The 55 final reports included cross-sectional/survey (n = 51) and quasi-experimental (n = 4) designs. A sensitivity analysis, comparing findings from all reports with those rated moderate (moderate-weak and moderate-strong) and strong quality, did not show significant differences. In a majority of the articles identified (n = 38, 69%), nurses reported moderate-high research use.

Conclusions

According to this review, nurses' reported use of research is moderate-high and has remained relatively consistent over time until the early 2000's. This finding, however, may paint an overly optimistic picture of the extent to which nurses use research in their practice given the methodological problems inherent in the majority of studies. There is a clear need for the development of standard measures of research use and robust well-designed studies examining nurses' use of research and its impact on patient outcomes. The relatively unchanged self-reports of moderate-high research use by nurses is troubling given that over 40 years have elapsed since the first studies in this review were conducted and the increasing emphasis in the past 15 years on evidence-based practice. More troubling is the absence of studies in which attempts are made to assess the effects of varying levels of research use on patient outcomes.     

Dual equipoise shared decision making: definitions for decision and behaviour support interventions

Background

In the experience of health professionals, it appears that interacting with peers in the workplace fosters learning and information sharing. Informal groups and networks present good opportunities for information exchange. Communities of practice (CoPs), which have been described by Wenger and others as a type of informal learning organization, have received increasing attention in the health care sector; however, the lack of uniform operating definitions of CoPs has resulted in considerable variation in the structure and function of these groups, making it difficult to evaluate their effectiveness.

Objective

To critique the evolution of the CoP concept as based on the germinal work by Wenger and colleagues published between 1991 and 2002.

Discussion

CoP was originally developed to provide a template for examining the learning that happens among practitioners in a social environment, but over the years there have been important divergences in the focus of the concept. Lave and Wenger's earliest publication (1991) centred on the interactions between novices and experts, and the process by which newcomers create a professional identity. In the 1998 book, the focus had shifted to personal growth and the trajectory of individuals' participation within a group (i.e., peripheral versus core participation). The focus then changed again in 2002 when CoP was applied as a managerial tool for improving an organization's competitiveness.

Summary

The different interpretations of CoP make it challenging to apply the concept or to take full advantage of the benefits that CoP groups may offer. The tension between satisfying individuals' needs for personal growth and empowerment versus an organization's bottom line is perhaps the most contentious of the issues that make CoPs difficult to cultivate. Since CoP is still an evolving concept, we recommend focusing on optimizing specific characteristics of the concept, such as support for members interacting with each other, sharing knowledge, and building a sense of belonging within networks/teams/groups. Interventions that facilitate relationship building among members and that promote knowledge exchange may be useful for optimizing the function of these groups.     

Advances in medical decision support systems for diagnosis of acute graft-versus-host disease: molecular and computational intelligence joint approaches

Acute graft-versus-host disease (aGVHD) is a serious systemic complication of allogeneic hematopoietic stem cell transplantation (HSCT) causing considerable morbidity and mortality. Acute GVHD occurs when alloreactive donor-derived T cells recognize host-recipient antigens as foreign. These trigger a complex multiphase process that ultimately results in apoptotic injury in target organs. The early events leading to GVHD seem to occur very soon, presumably within hours from the graft infusion. Therefore, when the first signs of aGVHD clinically manifest, the disease has been ongoing for several days at the cellular level, and the inflammatory cytokine cascade is fully activated. So, it comes as no surprise that progress in treatment based on clinical diagnosis of aGVHD has been limited in the past 30 years. It is likely that a pre-emptive strategy using systemic high-dose corticosteroids as early as possible could improve the outcome of aGVHD. Due to the deleterious effects of such treatment particularly in terms of infection risk posed by systemic steroid administration in a population that is already immune-suppressed, it is critical to identify biomarker signatures for approaching this very complex task. Some research groups have begun addressing this issue through molecular and proteomic analyses, combining these approaches with computational intelligence techniques, with the specific aim of facilitating the identification of diagnostic biomarkers in aGVHD. In this review, we focus on the aGVHD scenario and on the more recent state-of-the-art. We also attempt to give an overview of the classical and novel techniques proposed as medical decision support system for the diagnosis of GVHD.     

A decision support tool for integrated fisheries bycatch management

Reviews in Fish Biology and Fisheries - Participatory decision tools enable stakeholders to reconcile conflicting natural resources management objectives. Fisheries targeting highly productive...     

Distributed gene clinical decision support system based on cloud computing

Background

The clinical decision support system can effectively break the limitations of doctors’ knowledge and reduce the possibility of misdiagnosis to enhance health care. The traditional genetic data storage and analysis methods based on stand-alone environment are hard to meet the computational requirements with the rapid genetic data growth for the limited scalability.

Methods

In this paper, we propose a distributed gene clinical decision support system, which is named GCDSS. And a prototype is implemented based on cloud computing technology. At the same time, we present CloudBWA which is a novel distributed read mapping algorithm leveraging batch processing strategy to map reads on Apache Spark.

Results

Experiments show that the distributed gene clinical decision support system GCDSS and the distributed read mapping algorithm CloudBWA have outstanding performance and excellent scalability. Compared with state-of-the-art distributed algorithms, CloudBWA achieves up to 2.63 times speedup over SparkBWA. Compared with stand-alone algorithms, CloudBWA with 16 cores achieves up to 11.59 times speedup over BWA-MEM with 1 core.

Conclusions

GCDSS is a distributed gene clinical decision support system based on cloud computing techniques. In particular, we incorporated a distributed genetic data analysis pipeline framework in the proposed GCDSS system. To boost the data processing of GCDSS, we propose CloudBWA, which is a novel distributed read mapping algorithm to leverage batch processing technique in mapping stage using Apache Spark platform.

     

Review: Artificial liver support systems

Despite recent advances in medical therapy, patients with fulminant hepatic failure (FHF) have a mortality rate approaching 90%. Many patients die because of failure to arrest the progression of cerebral edema. Liver transplantation has improved survival to 65% to 75%. However, there is a shortage of donors and approximately one half of the patients with FHF will die while awaiting liver transplantation. There is thus a need to develop an extracorporeal liver assist system to help keep these patients alive and neurologically intact until either an organ becomes available for transplantation or the native liver recovers from injury. Such a system could also be used during the period of functional recovery from massive liver resection or to assist patients with decompensated chronic liver disease. Over the years, various methods utilizing charcoal and resin hemoperfusion, dialysis, plasma exchange, and other methods of blood detoxification have been developed and tested, but none have gained wide acceptance. This was due to: (i) incomplete understanding of the pathophysiology of liver failure; (ii) lack of accurate methods of assessment, quantitation, and stratification of the degree of liver dysfunction; and (iii) inadequate numbers of prospective controlled clinical trials examining the effects of specific therapeutic modalities. Liver support systems utilizing liver tissue preparations were developed in the 1950s, but it was not until recently that advances in hepatocyte isolation and culture, better understanding of hepatocyte-matrix interactions, and improved hollow-fiber technology have resulted in the development of a new generation of liver assist devices. Some of these devices are currently being tested in the clinical setting. In a preliminary clinical study, we have used a porcine hepatocyte-based liver support system to treat patients with acute liver failure as well as patients with acute exacerbation of chronic liver disease. Patients in the first group, who were candidates for transplantation, were successfully bridged to a transplant with excellent survival. No obvious benefit from bioartifical liver treatments was seen in the second group. It is possible that, in this group, patients will have to be treated earlier and for longer periods of time. Prospective controlled trials will be initiated as soon as the current phase I study is concluded to determine the efficacy of this system in both patients populations. (c) 1996 John Wiley & Sons, Inc.     

Decision support systems for aquaculture licensing

Models used to assess the environmental impacts of aquaculture are becoming increasingly numerous and complicated. It is therefore becoming more and more difficult to present these moiels to non-scientists, even though the ultimate clients of research on aquaculture impacts are administrators and producers who have to deal with ractical considerations and have little time or inclination to deal with the complexities of scientific morfels. The Aquaculture Research Group within the Habitat Ecology Division has therefore been exploring the development of a decision support system (DSS) as a tool for communicating scientific advice to managers, specifically addressing the use of models to evaluate environmental impacts in order to assess whether the licensing of finfish aquaculture sites is likely to lead to degradation of natural marine habitat. The proposed DSS will incorporate simplified versions of several models along with a geographical data base of relevant hydrographic and other environmental information. The user will be able to enter various scenarios in a simple fashion (for example, a mouse can be used to specify site locations) and see an evaluation of the proposal based on several scientific models. Although a computer program cannot be expected to represent more than a fraction of the expertise of real scientists, the DSS approach appears to have several advantages; these include the ability to deliver a degree of expertise in remote and isolated regions, and, perhaps most important, a chance for managers to access scientific resources in a private environment which lets them explore various options without having to justify their eventual actions to scientists who may not fully appreciate all the pressures which bear on their decisions. The material developed so far includes a prototype of the proposed DSS in form of a computer program which demonstrates what the user interface for a working DSf would look like. The program has only a crude graphical user interface and does not actually interact with a real database, but the models are realistic and the output offers a simplified representation of what a real Decision Support System might provide.