Albert Pla

eXiT*CBR: A framework for case-based medical diagnosis development and experimentation

OBJECTIVE Medical applications have special features (interpretation of results in medical metrics, experiment reproducibility and dealing with complex data) that require the development of particular tools. The eXiT*CBR framework is proposed to support the development of and experimentation with new case-based reasoning (CBR) systems for medical diagnosis. METHOD Our framework offers a modular, heterogeneous environment that combines different CBR techniques for different application requirements. The graphical user interface allows easy navigation through a set of experiments that are pre-visualized as plots (receiver operator characteristics (ROC) and accuracy curves). This user-friendly navigation allows easy analysis and replication of experiments. Used as a plug-in on the same interface, eXiT*CBR can work with any data mining technique such as determining feature relevance. RESULTS The results show that eXiT*CBR is a user-friendly tool that facilitates medical users to utilize CBR methods to determine diagnoses in the field of breast cancer, dealing with different patterns implicit in the data. CONCLUSIONS Although several tools have been developed to facilitate the rapid construction of prototypes, none of them has taken into account the particularities of medical applications as an appropriate interface to medical users. eXiT*CBR aims to fill this gap. It uses CBR methods and common medical visualization tools, such as ROC plots, that facilitate the interpretation of the results. The navigation capabilities of this tool allow the tuning of different CBR parameters using experimental results. In addition, the tool allows experiment reproducibility.

eXiT*CBR.v2: Distributed case-based reasoning tool for medical prognosis

In this work we propose a user-friendly medically oriented tool for prognosis development systems and experimentation under a case-based reasoning methodology. The tool enables health care collaboration practice to be mapped in cases where different doctors share their expertise, for example, or where medical committee composed of specialists from different fields work together to achieve a final prognosis. Each agent with a different piece of knowledge classifies the given cases through metrics designed for this purpose. Since multiple solutions for the same case are useless, agents collaborate among themselves in order to achieve a final decision through a coordinated schema. For this purpose, the tool provides a weighted voting schema and an evolutionary algorithm (genetic algorithm) to learn robust weights. Moreover, to test the experiments, the tool includes stratified cross-validation methods which take the collaborative environment into account. In this paper the different collaborative facilities offered by the tool are described. A sample usage of the tool is also provided.

Modeling Reuse on Case-Based Reasoning with Application to Breast Cancer Diagnosis

In the recent years, there has been an increasing interest on the use of case-based reasoning (CBR) in Medicine. CBR is characterized by four phases: retrieve, reuse, revise and retain. The first and last phases have received a lot of attention by the researchers, while the reuse phase is still in its infancy. The reuse phase involves a multi-facet problem which includes dealing with the closeness to the decision threshold used to determine similar cases, among other issues. In this paper, we propose a new reuse method whose decision variable is based on the similarity ratio. We have applied the method and tested in a breast cancer diagnosis database.

Multi-attribute auctions with different types of attributes: Enacting properties in multi-attribute auctions

Abstract Multi-attribute auctions allow agents to sell and purchase goods and services taking into account more attributes than just price (e.g. service time, tolerances, qualities, etc.). In this paper we analyze attributes involved during the auction process and propose to classify them between verifiable attributes, unverifiable attributes and auctioneer provided attributes. According to this classification we present VMA2, a new Vickrey-based reverse multi-attribute auction mechanism, which takes into account the different types of attributes involved in the auction and allows the auction customization in order to suit the auctioneer needs. On the one hand, the use of auctioneer provided attributes enables the inclusion of different auction concepts, such as social welfare, trust or robustness whilst, on the other hand, the use of verifiable attributes guarantee truthful bidding. The paper exemplifies the behavior of VMA2 describing how an egalitarian allocation can be achieved. The mechanism is then tested in a simulated manufacturing environment and compared with other existing auction allocation methods.

Multi-dimensional fairness for auction-based resource allocation

Multi-attribute resource allocation problems involve the allocation of resources on the basis of several attributes, therefore, the definition of a fairness method for this kind of auctions should be formulated from a multi-dimensional perspective. Under such point of view, fairness should take into account all the attributes involved in the allocation problem, since focusing on just a single attribute may compromise the allocations regarding the remainder attributes (e.g. incurring in delayed or bad quality tasks). In this paper, we present a multi-dimensional fairness approach based on priorities. For that purpose, a recurrent auction scenario is assumed, in which the auctioneer keeps track of winner and losers. From that information, the priority methods are defined based on the lost auctions number, the number of consecutive loses, and the fitness of their loser bids. Moreover, some methods contain a probabilistic parameter that enables handling wealth ranking disorders due to fairness. We test our approach in real-data based simulator which emulates an industrial production environment where several resource providers compete to perform different tasks. The results pointed that multi-dimensional fairness incentives agents to remain in the market whilst it improves the equity of the wealth distribution without compromising the quality of the allocation attributes.

Multi criteria operators for multi-attribute auctions

Multi-attribute auctions allow agents to sell and purchase goods and services taking into account more attributes besides the price (e.g. service time, tolerances, qualities, etc.). The coexistence of different attributes in the auction mechanism increases the difficulty of determining the winner and its payment. multi-criteria functions can be used to deal with the problem of determining the auction winner. However, in order to make the payment possible, multi criteria functions must fulfill certain conditions. In this paper we discuss which properties must satisfy a multi-criteria function so it can be used to determine the winner of a multi-attribute auction and we experimentally show how the valuation function choice conditions the behavior of the auction mechanism.

Service workflow monitoring through complex event processing

This paper presents an approach for service monitoring through workflow modeling and complex event processing. Workflows allow the representation of services process interactions while complex event processing (CEP) is a concept for event driven architectures which offers an alternative solution for monitoring and supervision. In this paper we propose a methodology to combine both technologies where CEP is used to monitor workflows and to predict possible delays. A case study on medical equipment maintenance business is shown.

Medical equipment maintenance support with service-oriented multi-agent services

Service oriented architectures (SOA) have emerged as an approach to handle the complexity of enterprise interoperability. Recently, multi-agent systems have been promoted as a technique to deal with cooperation issues involved in SOA. This cooperation is particularly important in several application domains, in which different companies are involved in a concrete service deployment. Agents, among other issues, offer the possibility to decide, if more than one option is available, providing flexibility and robustness. In this paper, we describe the agent-based cooperation process we have followed to enable partners cooperation in an equipment maintenance workflow. The use of ontologies and relationships with standards is highlighted. The approach is illustrated in an hospital scenario considered in the AIMES project.

Boosting CBR Agents with Genetic Algorithms

In this paper we present a distributed system in which several case-based reasoning (CBR) agents cooperate under a boosting schema. Each CBR agent knows part of the cases (a subset of the available attributes) and is trained with a subset of the available cases (so not all the agents know the same cases). The solution of the system is then computed by means of a weighted average of the solutions provided by the CBR agents. Weights are actively learnt by a genetic algorithm. The system has been applied to a breast cancer application domain. The results show that with our methodology we can improve the results obtained with a case base in which attributes have been manually selected by physicians, saving physicians work in future.

Context-Aware Case-Based Reasoning

In the recent years, there has been an increasing interest in ubiquitous computing. This paradigm is based on the idea that software should act according to the context where it is executed in what is known as context-awareness. The goal of this paper is to integrate context-awareness into case-based reasoning (CBR). To this end we propose thee methods which condition the retrieval and the reuse of information in CBR depending on the context of the query case. The methodology is tested using a breast-cancer diagnose database enriched with geospatial context. Results show that context-awareness can improve CBR.