We describe a conceptual architecture and software implementation specific to the task of interpretation, summarization, visualization, explanation, and interactive exploration of time-oriented clinical data and the multiple levels of meaningful concepts that can be abstracted from these data. We build on our work on abstraction of timeoriented clinical data using a knowledge base, acquired from clinical experts, of temporal properties of the data. We call the new framework KNAVE (Knowledge-based Navigation of Abstractions for Visualization and Explanation). The visualization and exploration operators, whose semantics are domain independent, access the domain-specific knowledge base. Exploration exploits key relations (e.g., the abstraction hierarchy) in each clinical domain. Preliminary assessment of the prototype with several clinical users has been encouraging. The KNAVE methodology has broad ramifications for reducing the load that large numbers of time-oriented clinical data put on practicing physicians.

We describe a new conceptual methodology and related computational architecture called Knowledge-based Navigation of Abstractions for Visualization and Explanation (KNAVE). KNAVE is a domain-independent framework specific to the task of interpretation, summarization, visualization, explanation, and interactive exploration, in a context-sensitive manner, of time-oriented raw data and the multiple levels of higher-level, interval-based concepts that can be abstracted from these data. The KNAVE domain-independent exploration operators are based on the relations defined in the knowledge-based temporal-abstraction problem-solving method, which is used to abstract the data, and thus can directly use the domain-specific knowledge base on which that method relies. Thus, the domain-specific semantics are driving the domain-independent visualization and exploration processes, and the data is viewed through a filter of domain-specific knowledge. By accessing the domain-specific temporal-abstraction knowledge base and the domain-specific time-oriented database, the KNAVE modules enable users to query for domain-specific temporal abstractions and to change the focus of the visualization, thus reusing for a different task (visualization and exploration) the same domain model acquired for abstraction purposes. We focus here on the methodology, but also describe a preliminary evaluation of the KNAVE prototype in a medical domain. Our experiment incorporated seven users, a large medical patient record, and three complex temporal queries, typical of guideline-based care, that the users were required to answer and/or explore. The results of the preliminary experiment have been encouraging. The new methodology has potentially broad implications for planning, monitoring, explanation, and in...

this paper, we survey a wide range of research in temporal representation and reasoning, without committing ourselves to the point of view of any speci c application

Abstract. Many clinical domains involve the collection of different types and substantial numbers of data over time. This is especially true when monitoring chronic patients. It is highly desirable to assist human users (e.g., clinicians, researchers), or decision support applications (e.g., diagnosis, therapy, quality assessment), who need to interpret large amounts of time-oriented data by providing a useful method for querying not only raw data, but also its abstractions. A temporal-abstraction database mediator is a modular approach designed for answering abstract, time-oriented queries. Our approach focuses on the integration of multiple time-oriented data sources, domain-specific knowledge sources, and computation services. The mediator mediates abstract time-oriented queries from any application to the appropriate distributed components that can answer these queries. We describe a highly modular, distributed implementation of the temporal database mediator architecture in the medical domain, and provide insights regarding the effective implementation and application of such an architecture.

Both clinical management of patients and clinical research are essentially time-oriented endeavors. In this paper, I emphasize the crucial role of temporal-reasoning and temporal-maintenance tasks for modern medical information and decision support systems. Both tasks are important for management of clinical data, but the first is often approached mainly through artificial-intelligence methodologies, while the other is usually investigated by the database community. However, both tasks require careful consideration of common theoretical issues, such as the structure of time. In addition, common to both of these research areas are tasks such as temporal abstraction and management of variable temporal granularity. Finally, both tasks are highly relevant for applications such as patient monitoring, support to application of therapy guidelines, assessment of the quality of guideline application, and visualization and exploration of time-oriented biomedical data. I propose that integration of the two areas should be a major research and development goal. I demonstrate one integration approach by presenting a new architecture, a temporal mediator, which combines temporal reasoning and temporal maintenance, and integrates the management of clinical databases and medical knowledge bases. I present and discuss examples of using the temporal mediator for several of the application areas mentioned. I conclude by reemphasizing the importance of effective knowledge representation, knowledge reuse, and knowledge sharing methods to medical decision support systems in general, and to time-oriented systems in particular.

Keywords: temporal reasoning, temporal maintenance, temporal databases, temporal abstraction, clinical data, medical informatics.

It is almost impossible to try to represent and analyze clinical data in the absence of a temporal dimension. The temporal aspect is especially important when automated decision support is used for patient care over substantial periods. This paper emphasizes the crucial role that tasks of temporal reasoning and temporal maintenance play in modern medical information and decision support systems; it also discusses the implications of providing automated support to clinicians who must perform such tasks as part of broader clinical tasks (for example, monitoring and therapy). Temporal reasoning tasks mainly involve intelligent analysis of time-oriented clinical data, and temporal maintenance tasks focus on effective storage and retrieval of these data. Both types of tasks, however, are highly relevant for such applications as patient monitoring,

Extensive amounts of knowledge and data stored in medical databases require the development of specialized tools for storing and accessing of data, data analysis, and effective use of stored knowledge and data. This paper focuses on methods and tools for intelligent data analysis, aimed at narrowing the increasing gap between data gathering and data comprehension. The paper sketches the history of research that led to the development of current intelligent data analysis techniques, discusses the need for intelligent data analysis in medicine, and proposes a classification of intelligent data analysis methods. The scope of the paper covers temporal data abstraction methods and data mining methods. A selection of methods is presented and illustrated in medical problem domains. Presently data abstraction and data mining are attracting considerable research interest. However the two technologies, in spite of the fact that they share their central objective, namely the intelligen...

Il mondo piatto e un mondo in cui il tempo scorre scandito da un unico orologio, in un'unica direzione, orizzontale. Un po' noioso, direte voi. Gli abitanti di questo mondo possono muoversi nel futuro, e, quelli piu furbi, anche nel passato. Il futuro non ha fine, il passato ha invece un inizio, uno zero (ma qualcuno non ci crede). Tutto qui.

We use a constraint-based language to specify periodic temporal patterns. Our language is intended to be simple to use, while allowing a wide variety of patterns to be expressed. The language solves problems such as (1) how to use calendarbased constraints to define repetition of a periodic event, (2) what temporal relations must exist between consecutive repeats of a pattern, and (3) how expressivity is limited if the same temporal relations must hold between each pair of intervals in the pattern. This language has been implemented in a temporal-abstraction system called Rsum, and researchers have used it in a graphical knowledge-acquisition tool to acquire domain-specific knowledge from experts about patterns to be found in large databases. We summarize the results of preliminary experiments using the patternspecification and pattern-detection tools on data on patients who have cancer and were seen at the University of Chicago bone-marrow--transplantation center.