Using Probabilistic Neural Network to Select a Medical Specialist Agent

The authors aim to design the Multi-agent system, in which the software agents interact with each other to diagnose a disease and decide the treatment plan(s). In this chapter, the authors present a novel approach of applying Probabilistic Neural Network (PNN) to classify the childhood disease and their respective medical specialist. Normally this classification is performed by the pediatricians. The system that has been presented here, imitates the behavior of a pediatrician while selecting super specialist doctor. This decision making mechanism will be embedded in an agent called Intelligent Pediatric Agent. To design the PNN, a database consisting of 104 records has been gathered. It includes 17 different sign symptoms and based on their values, one of the five super specialists is selected. A Back propagation Neural Network (BPNN) has also been designed to compare the results produced by the PNN and it is found that PNN is more promising.

HeCaSe2

Clinical guidelines (CGs) contain a set of directions or principles to assist the healthcare practitioner with patient care decisions about appropriate diagnostic, therapeutic, or other clinical procedures for specific clinical circumstances. It is widely accepted that the adoption of guideline-execution engines in daily practice would improve the patient care, by standardising the care procedures. Guideline-based systems constitute part of a knowledge-based decision support system in order to deliver the right knowledge to the right people in the right form at the right time. The automation of the guideline execution process is a basic step towards its widespread use in medical centres. To achieve this general goal, different topics should be tackled, such as the acquisition of clinical guidelines, its formal verification, and finally its execution. This chapter focuses on the execution of CGs and describes the design and implementation of an agent-based platform in which the actors involved in health care coordinate their activities to perform the complex task of guideline enactment.

Economic Efficiency and the Canadian Health Care System

In this chapter the authors examine the compatibility of the objectives of universality and public funding which are two important pillars of the Canadian healthcare system, with the objectives of cost effectiveness and more generally economic efficiency. The authors note that under some very innocuous conditions, markets and other economic based mechanisms such as second price auctions are characterized by economic efficiency and cost effectiveness. For the particular case of healthcare, some additional features that must be considered in the design of the mechanism are that healthcare services and products are valuable if, when taken together they constitute the components of a needed procedure, and otherwise they are worthless to the individual; and timely completion of procedures is what is valued, delays and waiting not only prolong suffering but may eventually prove to be more costly to the system if the condition worsens. They recommend a market-based mechanism, encompassing these features, that utilizes mobile agents representing patients and their medical needs. In order to incorporate the basic goals of universality and public funding, the agents will participate in virtual auctions using a needs based ranking as the currency for making bids.

Projecting Health Care Factors into Future Outcomes with Agent-Based Modeling

Human behavior is dynamic; it changes and adapts. In this chapter, we describe modeling approaches that consider human behavior as it relates to health care. We present examples the demonstrate how accounting for the social network structure changes the dynamics of infectious disease, how social hierarchy affects the chances of getting HIV, how the use of low dead-space syringe reduces the risk of HIV transmission, and how emergency departments could function more efficiently when real-time activities are simulated. The examples we use build from simple to more complex models and illustrate how agent-based modeling opens new horizons for providing descriptions of complex phenomena that were not possible with traditional statistical or even system dynamics methods. Agent-based modeling can use behavioral data from a cross-sectional representative study and project the behavior into the future so that the risks can be studied in a dynamical/temporal sense, thus combining the advantages of representative cross-sectional and longitudinal studies for the price of increased uncertainty. The authors also discuss data needs and potential future applications for this method.

Building a Health Care Multi-Agent Simulation Sysmte with Role-Based Modeling

Multi-Agent System (MAS) is a suitable programming paradigm for simulating and modeling health care systems and applications, where resources, data, control and services are widely distributed. We have developed a multi-agent software prototype to simulate the activities and roles inside a health care system. The prototype is developed using a framework called Role-based Agent Development Environment (RADE). In this chapter, the authors present an integrated approach for modeling, designing and implementing a multi-agent health care simulation system using RADE. They describe the definition of role classes and agent classes, as well as the automatic agent generation process. The authors illustrate the coordination problem and present a rule-based coordination approach. In the end, they present a runtime scenario of this health care simulation system, which demonstrates that dynamic task allocation can be achieved through the creation of role instances and the mapping from role instances to agents. This scenario also explains how agents coordinate their activities given their local constraints and interdependence among distributed tasks.

Operating Room Simulation and Agent-Based Optimization

Healthcare systems are characterized by uncertainty, variability, complexity, and human roles. Simulation can test scenarios of changes in processes, resources, and schedules without major physical investment or risk. Agent-based technology can model systems with autonomous and interacting activities. This chapter introduces the method of using simulation and agent-based technologies to enable a better understanding of the patient flow to improve the process performance in healthcare. The proposed method is used to identify the existing problem and to evaluate proposed solutions for the problem of the operating room (OR) at Winnipeg Health Sciences Centre. Issues are identified including patient flows, operation schedules, demand and capacity of the system and the configuration of resources required. An optimum scheduling is proposed for the OR operation to shorten the patient waiting time.

Current Practices in Select Healthcare Systems

In this chapter, current practices of healthcare delivery in three economically advanced countries will be reviewed. Is healthcare delivery commensurate with economic prosperity? Countries with technological and economic advantages may be better poised to deliver healthcare efficiently. However, this is not the case in fact. The following review will show that medico-legal and technological prowess may not translate into a healthier life and better healthcare delivery. It will be argued that poor allocation of ample resources is tantamount to resource insufficiency. The chapter will cite anonymous but true cases of patients to illustrate the salient points.

Role of Multi-Agents System in Creation of Collaborative Environments within Mental Health Domain

Mental illness is becoming one of the major problems of our society. The World Health Organization predicted that depression would be the world’s leading cause of disability by 2020. The exact causes of many mental illnesses are still unknown, mainly due to the complex nature of mental health. In this paper, the authors propose a multi-agent system designed to assist in effective and efficient management, retrieval and analysis of mental health information. They utilize the TICSA approach to define different agent Types, their Intelligence, Collaboration paths, address Security problems and Assemble individual agents. They use UML 2.1 Sequence and Composite diagrams to model social and goal-driven nature of the multi-agent system. The proposed multi-agent system has the potential to provide and expose the knowledge that will increase our understanding and control over mental health and help in development of effective prevention and intervention strategies.

Multi-Agent Systems in Developing Countries

Developing countries are faced with many problems and issues related to healthcare service delivery. Many factors contribute to this, such as a lack of adequate medical resources, a shortage of skilled medical professionals, increasing clinical demands due to infectious diseases, limited technological systems and an unreliable telecommunications and electrical infrastructure. However, the potential for multi-agent systems and multi-agent simulations to address some of these issues shows great promise. Multi-agent simulations have already been applied to modeling infectious diseases such as HIV and Avian Flu in the developing world. Furthermore, groups of smart agents, by their very design, can function autonomously and act as a distributed service, which greatly enables them to successfully operate in the kind of environments encountered in developing countries.

A Multi-Agent Simulation of Kidney Function for Medical Education

This chapter describes a multi-agent system to simulate kidney function for the purpose of teaching renal physiology to healthcare students. Renal function is modeled with agents. Agents represent molecules and fluids and the environment represents the structures, membranes and volumes of the nephrons in the kidneys. The agents move dynamically through their environment, responding appropriately depending on their surroundings. The authors describe how this multi-agent system is used in research and teaching medical students about the renal system. Results of heuristic and usability testing by medical students show improved visualization of the function of the renal system and self-confidence in learning renal physiology.