Towards Process-of-Care Aware Emergency Department Information Systems

The critical role of emergency departments (EDs) as the first point of contact for ill and injured patients has presented significant challenges for the elicitation of detailed process models. Patient complexity has limited the ability of ED information systems (EDIS) in prediction of patient treatment and patient movement. This article formulates a novel approach to building EDIS Activity Views that paves the way for EDIS that can predict patient workflow. The resulting Activity View pertains to what is being done, rather than what experts think is being done. The approach is based on analysis of data that is routinely recorded during patient treatment. The practical significance of the proposed approach is clinically acceptable, verifiable, and statistically valid process-oriented clusters of ED activities that can be used for targeted process elicitation, thus informing the design of EDIS. Its theoretical significance is in providing the new middle ground between existing soft and computational process elicitation methods.

E-patients Empower Healthcare

E-patients can empower themselves and improve healthcare. In online communities, patients may discuss adverse events that are inadequately addressed in the literature. The author as a patient joined various online patient discussion groups and identified several such adverse events. For each such adverse event, the patient findings, the medical literature, and the implications are noted. Extracts from the literature that were provided to the patients were welcomed by the patients. Possible approaches to financially supporting such activities are sketched.

Intelligent Agent Framework for Secure Patient-Doctor Profiling and Profile Matching

Radio frequency identification (RFID) is a promising technology for improving services and reduction of cost in health care. Accurate almost real time data acquisition and analysis of patient data and the ability to update such a data is a way to improve patients care and reduce cost in health care systems. This article employs wireless radio frequency identification technology to acquire patient data and integrates wireless technology for fast data acquisition and transmission, while maintaining the security and privacy issues. An intelligent agent framework is proposed to assist in managing patients health care data in a hospital environment. A data classification method based on fuzzy logic is proposed and developed to improve the data security and privacy of data collected and propagated.

Information Technology (IT) and the Healthcare Industry

The healthcare industry is under pressure to improve patient safety, operate more efficiently, reduce medical errors, and provide secure access to timely information while controlling costs, protecting patient privacy, and complying with legal guidelines. Analysts, practitioners, patients and others have concerns for the industry. Using the popular strategic analysis tool of strengths, weaknesses, opportunities, and threats analysis (SWOT), facing the healthcare industry and its adoption of information technologies (IT) are presented. Internal strengths supporting further industry investment in IT include improved patient safety, greater operational efficiency, and current investments in IT infrastructure. Internal weaknesses, however, include a lack of information system integration, user resistance to new technologies and processes, and slow adoption of IT. External opportunities including increased use of the Internet, a favorable national environment, and a growing call for industry standards are pressured by threats of legal compliance, loss of patient trust, and high cost of IT.

Envisioning a National e-Medicine Network Architecture in a Developing Country

Poor infrastructures in developing countries such as Ethiopia and much of Sub-Saharan Africa have caused these nations to suffer from lack of efficient and effective delivery of basic and extended medical and healthcare services. Often, such limitation is further accompanied by low patient-doctor ratios, resulting in unwarranted rationing of services. Apparently, e-medicine awareness among both governmental policy makers and private health professionals is motivating the gradual adoption of technological innovations in these countries. It is argued, however, that there still is a gap between current e-medicine efforts in developing countries and the existing connectivity infrastructure leading to faulty, inefficient and expensive designs. The particular case of Ethiopia, one such developing country where e-medicine continues to carry significant promises, is investigated and reported in this article.

Ambient Intelligence and Pervasive Architecture Designed within the EPI-MEDICS Personal ECG Monitor

Recent years have witnessed a growing interest in developing personalized and nonhospital based care systems to improve the management of cardiac care. The EPI-MEDICS project has designed an intelligent, portable Personal ECG Monitor (PEM) embedding an advanced decision making system. We present two of the ambient intelligence models embedded in the PEM: the neural-network based ischemia detection module and the Bayesian-network risk stratification module. Ischemia detection was expanded to take into account the patient ECG, clinical data, and medical history. The neural-network ECG interpretation module and the Bayesian-network risk factors module collaborate through a fuzzy-logic-based layer. We also present two telemedicine solutions that we have designed and in which the PEM is integrated. The first telemedical architecture was created to allow the collection of medical data and their transmission between healthcare providers to get an expert opinion. The second one is intended for improving healthcare in old peoples homes.

TreeWorks

Decision trees are hierarchical, sequential classification structures that recursively partition the set of observations (data) and are used to represent rules underlying the observations. This article describes the development of TreeWorks, a tool that enhances existing decision tree theory and overcomes some of the common limitations such as scalability and the ability to handle large databases. We present a heuristic that allows TreeWorks to cope with observation sets that contain several distinct values of categorical data, as well as the ability to handle very large datasets by overcoming issues with computer main memory. Furthermore, our tool incorporates a number of useful features such as the ability to move data across terminal nodes, allowing for the construction of trees combining statistical accuracy with expert opinion. Finally, we discuss ways that decision trees can be combined with Operational Research health care models, for more effective and efficient planning and management of health care processes.

Application of Unified Modelling Language (UML) to the Modelling of Health Care Systems

The unified modelling language (UML) comprises a set of tools for documenting the analysis of a system. Although UML is generally used to describe and evaluate the functioning of complex systems, the extent of its application to the health care domain is unknown. The purpose of this article is to survey the literature on the application of UML tools to the analysis and modelling of health care systems. We first introduce four of the most common UML diagrammatic tools, namely use case, activity, state, and class diagrams. We use a simplified surgical care service as an example to illustrate the concepts and notation of each diagrammatic tool. We then present the results of the literature survey on the application of UML tools in health care. The survey revealed that although UML tools have been employed in modelling different aspects of health care systems, there is little systematic evidence of the benefits.

Informatics Application Challenges for Managed Care Organizations

Organizations across industry sectors continue to develop data resources and utilize analytic techniques to enhance efficiencies in their operations. One example of this is evident as Managed Care Organizations (MCOs) enhance their care and disease management initiatives through the utilization of population segmentation techniques. This article proposes a classification system for population segmentation techniques for care and disease management and provides an evaluation process for each. The three proposed operational areas for Managed Care Organizations are: 1) Risk Status: early identification of high-risk patients, 2) Treatment Status: compliance with treatment protocols, and 3) Health Status: severity of illness or episodes of care groupings, all of which require particular analytic methodologies to leverage data resources. By applying this classification system an MCO can improve its ability to clarify internal goals for population segmentation, more accurately apply existing analytic methodologies, and produce more appropriate solutions.

Can IT Act as a Catalyst for Change in Hospitals?

This chapter presents a succesful reorganization of a patient care process that was carried out in a middle sized Finnish hospital. The reorganization of the patient care process for joint replacement surgery succeeded in achieving a 50 per cent increase in operations. This study proposes that IT may have an indirect influence on the achievement of goals, such as productivity, as soon as the IT investment has been decided upon; in other words, IT benefits start accruing before the IT component is even in place. This is a new feature to add to the previous definitions, because this particular benefit cannot be logically derived from any of the features of the actual IT system. Paying enough attention to this phenomen at the planning stage can be vital to the success of new IT system investment.