Skip to main content
main-content

Über dieses Buch

Temporal Information Systems in Medicine introduces the engineering of information systems for medically-related problems and applications. The chapters are organized into four parts; fundamentals, temporal reasoning & maintenance in medicine, time in clinical tasks, and the display of time-oriented clinical information. The chapters are self-contained with pointers to other relevant chapters or sections in this book when necessary. Time is of central importance and is a key component of the engineering process for information systems. This book is designed as a secondary text or reference book for upper -undergraduate level students and graduate level students concentrating on computer science, biomedicine and engineering. Industry professionals and researchers working in health care management, information systems in medicine, medical informatics, database management and AI will also find this book a valuable asset.

Inhaltsverzeichnis

Frontmatter

Chapter 1. The role of Time in Medicine

Abstract
Medical tasks, such as diagnosis and therapy, are by nature complex and not easily amenable to formal approaches. The philosophical question “Is medicine science or art?” is frequently posed to show that expert clinicians often reach correct decisions on the basis of intuition and hindsight rather than scientific facts [22]. Medical knowledge is inherently uncertain and incomplete. Likewise, patient data are often ridden with uncertainty and imprecision, showing serious gaps. In addition, they could be too voluminous and at a level of detail that would prevent direct reasoning by a human mind. The computer-based performance of medical tasks poses many challenges. As such, it is not surprising that AI researchers were intrigued with the automation of medical problem solving from the early days of AI. The technology of expert systems is largely founded on attempts to automate medical expert diagnostic reasoning. For example, most people are familiar with the Stanford experiments of the Heuristic Programming Project resulting in the MYCIN family of rule-based systems [140].
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

Fundamentals

Frontmatter

Chapter 2. Temporal Modeling and Temporal Reasoning

Abstract
In this chapter, the reader is guided through the basic notions of time and temporal information and is presented with some important, general approaches to represent and reason about temporal information. Simple medical examples are used to help the reader to understand the advantages and limitations of the different approaches.
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

Chapter 3. Temporal Databases

Abstract
In this chapter, the reader is acquainted with the basic concepts of temporal databases, i.e. databases that deal explicitly with time-related concepts and information. Examples of clinical data with valid and transaction times are given. A classification of temporal databases according to the supported temporal dimensions is presented. The reader, then, learns how the relational model and the related algebra, calculus, and query languages have been extended to deal with the di_erent time aspects. The presentation then focuses on the main data models employed in the conceptual design, the Entity-Relationship data model and the Object-Oriented data models. The reader learns how to design a temporal database schema by both the standard (atemporal) data models and their corresponding temporally-oriented extensions. Finally, the reader is guided through some basic features of object-oriented query languages and their extensions for temporal information. A section on further topics related to temporal databases sketches some research directions on multimedia and semistructured temporal data.
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

Temporal Reasoning and Maintenance in Medicine

Frontmatter

Chapter 4. Temporal Clinical Databases

Abstract
This chapter introduces the reader to some important issues and topics of temporal clinical databases. More specifically the chapter focuses on modeling and querying issues related to the management of temporal clinical data collected into medical records. The reader, then, learns how some temporal relational and object-oriented models have been suitably defined to deal with the specific temporal aspects of clinical data. The presentation then focuses on some main data models explicitly proposed for managing clinical data with multiple temporal dimensions and with clinical temporal data given at different and mixed granularities/indeterminacies. The reader learns how to design and query a temporal clinical database both by the temporal relational model and by temporal object-oriented data models with the related query languages, respectively. Finally, the reader is guided through some specific aspects of a real temporal clinical database system allowing the management of follow-up patients who underwent cardiac angioplasty.
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

Chapter 5. Abstraction of Time-Oriented Clinical Data

Abstract
The chapter aims to give a comprehensive and critical review of current approaches to the common task of abstraction of time-oriented data in medicine, or temporal abstraction. Temporal-data abstraction constitutes a central requirement that presently receives much and justifiable attention. The role of this process is especially crucial in the context of time-oriented clinical monitoring, therapy planning, and exploration of clinical databases. General theories of time typically used in artificial intelligence do not fully address the requirements for temporal abstraction in medical reasoning (see Chapter 2).
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

Time in Clinical Tasks

Frontmatter

Chapter 6. Time in Clinical Diagnosis

Abstract
This chapter aims to explain how time and temporal reasoning can feature, with critical advantage, in the task of clinical diagnosis. This is largely done through a number of representative clinical diagnostic systems. The discussion focuses on the representation of time with respect to diagnostic knowledge and patient data, and the relevant temporal reasoning. It is assumed that the reader has a reasonable understanding of diagnostic systems, in particular clinical diagnostic systems. However, for the sake of completeness, relevant fundamental notions are overviewed.
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

Chapter 7. Automated Support to Clinical Guidelines and Care Plans

Abstract
Clinical guidelines are a powerful method for standardization and uniform improvement of the quality of medical care. Clinical guidelines are often best viewed as a set of schematic plans, at varying levels of abstraction and detail, for screening, diagnosis, or management of patients who have a particular clinical problem (e.g., fever of unknown origin) or condition (e.g., insulin-dependent diabetes). Clinical guidelines typically represent the consensus of an expert panel or a professional clinical organization, and, as much as possible, are based on the best evidence available. However, unless automated support is provided, guidelines are not easily accessible, nor applicable, at the point of care. As we shall see, reasoning about time-oriented data and actions is essential for guideline-based care.
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

The Display of Time-Oriented Clinical Information

Frontmatter

Chapter 8. Displaying Time-Oriented Clinical Data and Knowledge

Abstract
This chapter introduces the reader to the main topics related to the visualization of temporal clinical information. More specifically, the chapter focuses both on displaying raw temporal clinical data and on displaying more abstract temporal clinical data and temporal clinical knowledge. The reader is first introduced to the main aspects of information visualization in medicine and then to the more specific topics related to the visualization of temporal clinical information. Then, several research methodologies and their respective system prototypes are discussed in detail, to demonstrate the different aspects related to the implementation of advanced visualization systems for medical and clinical information, ranging from the visualization of raw temporal data, and the display of more abstract time-oriented data, to the visual composition of temporal queries, and the visual representation of temporal knowledge. The reader learns how to deal with the design and the evaluation of software systems for the visualization of (possibly) complex temporal clinical information. Finally, the reader is guided through the details of several specific systems, designed and implemented for the purpose of visualization and exploration of different kinds of temporal clinical data and knowledge in di_erent real world clinical settings.
Carlo Combi, Elpida Keravnou-Papailiou, Yuval Shahar

Backmatter

Weitere Informationen