Mobile Decision Support Research Articles

Mobile decision support for transplantation patient data

In high-critical medical fields instant information delivery is essential. Task-flow analyses within the transplantation unit of the Technische Universität München revealed that valuable time could be saved in pre-transplantation management being able to retrieve data of organ receivers ubiquitously. Inspired by this clinical scenario, a mobile application was designed and implemented providing surgeons with decision-relevant information on potential organ receivers. It assists them in considering the prospects of forthcoming organ transplantations and facilitates decision making and documentation with regard to high security demands. The described system services three organ receiver lists and is used by the surgeons in every transplantation procedure. After a 6-month period of clinical usage, the system has been evaluated in terms of handling, clinical benefit and total time savings. Intuitive, ubiquitous access to decision-relevant patient data and authenticated documentation were the major improvements with average total time savings of 50 min in comparison to the old system.

THE DEVELOPMENT OF A MOBILE DECISION SUPPORT SYSTEM

The emergence of mobile computing environments brings out various changes in the requirements and applications involving distributed data and has made the traditional Intelligent Decision Support System (IDSS) architectures based on the client/server model ineffective in mobile computing environments. This paper discusses the deficiencies of the current IDSS architectures based on data warehouse, on-line analysis processing (OLAP), model base (MB) and knowledge based (KB) technologies. By adopting the agent technology, the paper extends the IDSS system architecture to the Mobile Decision Support System (MDSS) architecture. The logical structure and the application architecture of the MDSS and the mechanisms and implementation strategies of the User Access Agent System, a major component of the MDSS, are described in this paper.

An architecture for the deployment of mobile decision support systems

The widespread use of mobile computing devices offers the opportunity of supplying decision support systems, targeted at specific situations and operated at the point of decision. Unfortunately, the computing environment within which such systems are deployed is radically different from the environments in which decision procedures are most easily designed. We summarise experience in reconciling these differences, using a general architecture but working in a specific domain (forest management). This required us to reconcile the constraints of the mobile computing device (limited resources, small touch-screen, support for procedural programming languages only) with the ability to rapidly select and configure different decision procedures for deployment in differing management conditions. We managed to reconcile these conflicting demands by taking advantage of the restricted forms of inference needed in the domain, making it possible to combine declarative and procedural aspects of the problem in a reliable way.

The Roles of an Intelligent Mobile Decision Support System in the Clinical Workflow

This paper presents an approach to clinical decision support by handheld computers. In the past there has been a shift of paradigm away from stand-alone, black-box problem solving systems to assisting tools for medical decision support. The paper describes the functional role of a mobile, decision supporting device in the clinical workflow. In a case study an application for therapy planning in paediatrics is presented. As a primary concern the integration of the system in the clinical decision process is analysed. Aspects of a lean and modular knowledge representation are described. The system has been implemented on a PalmPilot.

Pen-based, mobile decision support in healthcare

The use of computers has become well established throughout the business enterprise; but computer usage within the health care sector has lagged, particularly for automation of interactions between individual clinicians and their patients. A number of factors have contributed to this including difficulties in representing medical knowledge in computer-processible formats, the limited application of standards for data recording and transmission, and problems in human-computer interaction.A major obstacle to the use of computers in medicine has been the stationary nature of desktop computers. Most clinicians are mobile knowledge workers who need access to information across a wide variety of settings: in offices, exam rooms, emergency departments, hospitals, nursing homes and at home. Within each setting, there is concern that a large box on the consultation desk may interfere with communication between clinicians and patients. Moreover, many physicians do not have keyboard skills. Even for those who can type, keyboard data entry---concomitant with interviewing and examination-- is difficult. To overcome these obstacles, our group at the Yale Center for Medical Informatics has developed systems that operate on small, mobile platforms and accept pen-based data entry.We recognized early on that systems would have to be integrated tightly with clinical workflow and provide benefits to offset the inconvenience associated with their use. Clinical workflow refers to the complex interacting tasks performed by clinicians as they go about their daily work and to the corresponding information flows that are generated. A particular interest has been in providing clinical decision support at the point-of-care. We have extracted knowledge from evidence-based clinical practice guidelines and embedded it in mobile, pen-based systems that inform decision making by clinicians.