Skip to main content

2008 | Buch

Advanced Computational Intelligence Paradigms in Healthcare - 3

herausgegeben von: Dr. Margarita Sordo, Dr. Sachin Vaidya, Prof. Lakhmi C. Jain

Verlag: Springer Berlin Heidelberg

Buchreihe : Studies in Computational Intelligence

insite
SUCHEN

Über dieses Buch

Advanced Computational Intelligence (CI) paradigms are increasingly used for implementing robust computer applications to foster safety, quality and efficacy in all aspects of healthcare. This research book covers an ample spectrum of the most advanced applications of CI in healthcare.

The first chapter introduces the reader to the field of computational intelligence and its applications in healthcare. In the following chapters, readers will gain an understanding of effective CI methodologies in several important topics including clinical decision support, decision making in medicine effectiveness, cognitive categorizing in medical information system as well as intelligent pervasive healthcare systems, and agent middleware for ubiquitous computing. Two chapters are devoted to imaging applications: detection and classification of microcalcifications in mammograms using evolutionary neural networks, and Bayesian methods for segmentation of medical images. The final chapters cover key aspects of healthcare, including computational intelligence in music processing for blind people and ethical healthcare agents.

This book will be of interest to postgraduate students, professors and practitioners in the areas of intelligent systems and healthcare.

Inhaltsverzeichnis

Frontmatter
1. An Introduction to Computational Intelligence in Healthcare: New Directions
Summary
Computational intelligence paradigms offer tremendous advantages in many areas including healthcare, engineering, science and management. This chapter presents a brief introduction to computational intelligence in healthcare.
M. Sordo, S. Vaidya, L. C. Jain
2. AI in Clinical Decision Support: Applications in Optical Spectroscopy for Cancer Detection and Diagnosis
Summary
Optical approaches have been studied for the detection and diagnosis of epithelial cancer. Due to the biochemical and structural changes that occur in cancerous cells, malignant, benign, and normal tissues have different spectral properties. Artificial intelligence (AI) methods are being explored to detect and diagnose cancer based on optical imaging and spectra. AI is also used to optimize the design of optical spectroscopy and imaging instrumentation. In this chapter, we review the literature on AI applied to optical spectroscopy for cancer detection and diagnosis and present a detailed case study of research on oral cancer diagnosis using polarized light spectra.
Chili-Wen Kan, Linda T. Nieman, Konstantin Sokolov, Mia K. Markey
3. Decision-making Techniques in Ranking of Medicine Effectiveness
Summary
Theoretical fuzzy decision-making models mostly developed by Zadeh, Bellman, Jain and Yager can be adopted as useful tools to estimation of the total effectiveness-utility of a drug when appreciating its positive influence on a collection of symptoms characteristic of a considered diagnosis. The expected effectiveness of the medicine is evaluated by a physician as a verbal expression for each distinct symptom. By converting the words at first to fuzzy sets and then numbers we can regard the effectiveness structures as entries of a utility matrix that constitutes the common basic component of all methods. We involve the matrix in a number of computations due to different decision algorithms to obtain a sequence of tested medicines in conformity with their abilities to soothe the unfavorable impact of symptoms. An adjustment of the large spectrum of applied fuzzy decision-making models to the extraction of the best medicines provides us with some deviations in obtained results but we are thus capable to select this method whose effects closest converge to the physicians’ judgments and expectations.
Elisabeth Rakus-Andersson
4. Cognitive Categorizing in UBIAS Intelligent Medical Information Systems
Summary
This chapter will demonstrate that artificial intelligence methods based on linguistic mechanisms for semantic meaning reasoning can be used to develop new classes of intelligent information systems, and can be applied quite successfully to conduct in-depth meaning analyzes in the presented DSS (Diagnostic Support Systems) information systems as well as in a subclass of intelligent, cognitive systems used to analyze images: UBIAS (Understanding Based Image Analysis Systems). The study will present an IT mechanism for describing the meaning of analyzed objects using selected examples of analyzes of medical images, including those of the spinal cord and bone radiograms. The presented semantic reasoning procedures are based on the cognitive resonance model and have been applied for the job of interpreting the meaning of a selected type of diagnostic images of the central nervous system as well as images of the bone system. The solutions and applications presented here are of a research nature and show the directions in which modern IT systems as well as medical diagnostic support systems expand into the field of automatic, computer meaning interpretation of various patterns acquired in image diagnostics.
Lidia Ogielal, Ryszard Tadeusiewicz, Marek R. Ogiela
5. Intelligent Pervasive Healthcare Systems
Summary
The chapter presents the state of the art in intelligent pervasive healthcare applications and the corresponding enabling technologies. It discusses pervasive healthcare systems in either controlled environments (e.g., health care units or hospitals), or in sites where immediate health support is not possible (i.e. the patient’s home or an urban area). Special focus is raised on intelligent platforms (e.g., agents, context-aware and location-based services, and classification systems) that enable advanced monitoring and interpretation of patient status and environment optimizing the whole medical assessment procedure.
Charalampos Doukas, Ilias Maglogiannis
6. An Agent Middleware for Ubiquitous Computing in Healthcare
Summary
Healthcare environments are characterized by the need for coordination and collaboration among specialists with different areas of expertise, the integration of data from many devices or artifacts and the mobility of hospital staff, patients, documents, and equipment. Ubiquitous computing (ubicomp) enable us to meet these characteristics of medical environment. Ubiquitous computing environments are spaces where computational artifacts are invisible, become present whenever we need them, are adaptive to mobile users, can be enabled by simple and effortless interactions, and act autonomously to support users’ activities. We have proposed using software agents to implement these characteristics of a ubiquitous computing system with the aim of enhancing medical activities. Then, we created the SALSA middleware to facilitate the implementation of these agents for ubiquitous computing systems for healthcare environments. In our approach, autonomous agents can represent users, act as proxies to devices and information resources, or wrap a complex system functionality. The SALSA middleware enables developers to create autonomous agents that react to the contextual elements of the medical environment and that communicate with other agents, users and services available in the environment. We used the SALSA middleware for creating the Context-aware Hospital Information System. This chapter presents the SALSA middleware and how it facilitates the development of ubiquitous computing system for healthcare, in which the main systems components were conceived as autonomous agents.
Marcela D. Rodríguez, Jesús Favela
7. Detection and Classification of Microcalcification Clusters in Mammograms using Evolutionary Neural Networks
Summary
Breast cancer is one of the main causes of death in women and early diagnosis is an important means to reduce the mortality rate. The presence of microcalcification clusters are primary indicators of early stages of malignant types of breast cancer and its detection is important to prevent the disease. This chapter presents a procedure for the classification of microcalcification clusters in mammograms using sequential difference of gaussian filters (DoG) and three evolutionary artificial neural networks (EANNs) compared against a feedforward artificial neural network (ANN) trained with backpropagation. It is shown that the use of genetic algorithms (GAs) for finding the optimal weight set for an ANN, finding an adequate initial weight set before starting a backpropagation training algorithm and designing its architecture and tuning its parameters, results mainly in improvements in over-all accuracy, sensitivity and specificity of an ANN, compared with other networks trained with simple backpropagation.
Rolando R. Hernández-Cisneros, Hugo Terashima-Marín, Santiago E. Conant-Pablos
8. Bayesian Constrained Spectral Method for Segmentation of Noisy Medical Images. Theory and Applications
Summary
The spectral method of medical images segmentation that is constrained by Bayesian inference on initial edge map detection is introduced and characterized. It is followed by discussion of the accuracy of the method, that depends on the noise that affects the data. Gaussian noise model is constructed and a method for noisy data multiscale wavelet decomposition and denoising is applied. The proposed segmentation method is tested for denoised cardiac ultrasonic data and its performance is compared for different noise clipping values. Further applications for multiple multimodal cases are presented showing the universality of the proposed method that is fixable and adaptable to the number of clinical applications. The brief discussion of the future development of the method is provided.
T. Sołtysiński
9. Breaking Accessibility Barriers: Computational Intelligence in Music Processing for Blind People
Summary
A discussion on involvement of knowledge based methods in implementation of user friendly computer programs for disabled people is the goal of this paper. The paper presents a concept of a computer program that is aimed to aid blind people dealing with music and music notation. The concept is solely based on computational intelligence methods involved in implementation of the computer program. The program is build around two research fields: information acquisition and knowledge representation and processing which are still research and technology challenges. Information acquisition module is used for recognizing printed music notation and storing acquired information in computer memory. This module is a kind of the paper-to-memory data flow technology. Acquired music information stored in computer memory is then subjected to mining implicit relations between music data, to creating a space of music information and then to manipulating music information. Storing and manipulating music information is firmly based on knowledge processing methods. The program described in this paper involves techniques of pattern recognition and knowledge representation as well as contemporary programming technologies. It is designed for blind people: music teachers, students, hobbyists, musicians.
Wladyslaw Homenda
10. Ethical Healthcare Agents
Summary
We have combined a bottom-up casuistry approach with a top-down implementation of an ethical theory to develop a system that uses machine-learning to abstract relationships between prima facie ethical duties from cases of particular types of ethical dilemmas where ethicists are in agreement as to the correct action. This system has discovered a novel ethical principle that governs decisions in a particular type of dilemma that involves three potentially conflicting prima facie duties. We describe two prototype systems in the domain of healthcare that use this principle, one that advises human beings as to the ethically correct action in specific cases of this type of dilemma and the other that uses this principle to guide its own behavior, making it what we believe may be the first explicit ethical agent.
Michael Anderson, Susan Leigh Anderson
Metadaten
Titel
Advanced Computational Intelligence Paradigms in Healthcare - 3
herausgegeben von
Dr. Margarita Sordo
Dr. Sachin Vaidya
Prof. Lakhmi C. Jain
Copyright-Jahr
2008
Verlag
Springer Berlin Heidelberg
Electronic ISBN
978-3-540-77662-8
Print ISBN
978-3-540-77661-1
DOI
https://doi.org/10.1007/978-3-540-77662-8

    Marktübersichten

    Die im Laufe eines Jahres in der „adhäsion“ veröffentlichten Marktübersichten helfen Anwendern verschiedenster Branchen, sich einen gezielten Überblick über Lieferantenangebote zu verschaffen.