Projects


Methods, tools and technologies
ISRAEL   KNAVE-II
Knowledge-based Navigation of Abstractions for Visualization and Explanation
keywords Main objective
Temporal abstraction, information analysis, information visualization, knowledge acquisition, time-oriented clinical data analysis, decision support, model-based interface development, dynamic query, knowledge bases

Development of a tool to support interactive visualization and intelligent exploration of time-oriented clinical data.

summary
KNAVE II is a tool that supports the visualization, summarising, (intelligent) interpretation, explanation and context-sensitive navigation of time-oriented raw clinical data sets and higher-level concepts abstracted from time-oriented data.

Data consists of both raw measured values (i.e., lab tests results) and external interventions (i.e. medications and procedures). A predefined knowledge base is used to interpet raw data. Three types of interpretation are supported: classification of data (i.e., low – normal– high haemoglobin); change of data (i.e., rising – decreasing glucose levels) rate of data change (i.e., slow, fast). In addition, interpretations can be derived from other interpretations, such as bone marrow toxicity, which is defined by the RBC’s and platelets count level. Knowledge base definitions are context-sensitive (i.e. age and gender).

KNAVE II is a module of the IDAN distributed temporal-abstraction mediator which supports access to clinical patient data when a computerised guideline is being enacted.

 bullet   KNAVE-II project (BGU)  bullet   IDAN project [OC]  bullet   Download KNAVE
(University of the Negev)
 bullet   KNAVE project (Stanford)
references

Shahar Y, Goren-Bar D, Boaz D, Tahan G. Distributed, intelligent, interactive visualization and exploration of time-oriented clinical data and their abstractions. Artif Intell Med. 2005 Dec 9;

[PubMed]   []

" OBJECTIVES: We present KNAVE-II, an intelligent interface to a distributed architecture specific to the tasks of query, knowledge-based interpretation, summarization, visualization, interactive exploration of large numbers of distributed time-oriented clinical data, and dynamic sensitivity analysis of these data. KNAVE-II main contributions to the fields of temporal reasoning and intelligent user interfaces are: (1) the capability for interactive computation and visualization of domain specific temporal abstractions, supported by ALMA - a computational engine that applies the domain knowledge base to the clinical time-oriented database. (2) Semantic (ontology-based) navigation and exploration of the data, knowledge, and temporal abstractions, supported by the IDAN mediator, a distributed architecture that enables runtime access to domain-specific knowledge bases that are maintained by expert physicians. METHODS AND MATERIALS: KNAVE-II was designed according to 12 requirements that were defined through iterative cycles of design and user-centered evaluation. The complete architecture has been implemented and evaluated in a cross-over study design that compared the KNAVE-II module versus two existing methods: paper charts and an Excel electronic spreadsheet. A small group of clinicians answered the same queries, using the domain of oncology and a set of 1000 patients followed after bone-marrow transplantation. RESULTS: The results show that users are able to perform medium to hard difficulty level queries faster and more accurately by using KNAVE-II than paper charts and Excel. Moreover, KNAVE-II was ranked first in preference by all users, along all usability dimensions. CONCLUSIONS: Initial evaluation of KNAVE-II and its supporting knowledge based temporal-mediation architecture, by applying it to a large data base of patients monitored several years after bone marrow transplantation (BMT), has produced highly encouraging results. "

Martins SB, Shahar Y, Galperin M et al. Evaluation of KNAVE-II: a tool for intelligent query and exploration of patient data. Medinfo. 2004;11(Pt 1):648-52.

[PubMed]   [Stanford]

" We present the results of a preliminary evaluation of KNAVE-II, a distributed knowledge-based computational framework for visualization, interpretation, and exploration of longitudinal clinical data and of multiple levels of concepts derivable from these data. KNAVE-II uses a distributed architecture to access at run-time clinical time-oriented data, a domain-specific knowledge base containing properties of the clinical data, and a knowledge-based problem-solving method for computing on-the-fly interpretations of these data. The purpose of the evaluation was to compare efficiency and user satisfaction when answering clinical queries of variable complexity about clinical time-oriented data using KNAVE-II, versus using methods available in standard clinical settings: paper chart or electronic spreadsheet (ESS). Subjects answered high-complexity queries significantly faster using KNAVE-II than when using paper or ESS. User satisfaction with KNAVE-II was significantly superior compared to satisfaction using paper or ESS, based on a standard usability scale. Users also explicitly ranked KNAVE-II as superior to paper and the ESS. "

Shahar Y, Goren-Bar D, Galperin M, Boaz D, and Tahan G. KNAVE-II: A distributed architecture for interactive visualization and intelligent exploration of time-oriented clinical data The 7th International Workshop on Intelligent Data Analysis in Medicine and Pharmacology (IDAMAP-2003), pp. 103-110, Protaras, Cyprus, Oct. 2003.

[BGU]   []

Abstract " Interpretation and exploration of longitudinal clinical data is a major part of diagnosis, therapy, quality assessment, and clinical research, particularly for chronic patients. KNAVE-II is an intelligent interface to a distributed architecture specific to the tasks of query, knowledge-based interpretation, summarization, visualization, interactive exploration of large numbers of distributed time-oriented clinical data and dynamic sensitivity analysis of these data. The web-based architecture enables users (e.g., physicians) to query, visualize and explore clinical time-oriented databases. Both, the generation of context-sensitive interpretations (abstractions) of the time-stamped data, as well as the dynamic visual exploration of the raw data and the multiple levels of concepts abstracted from these data, are supported by runtime access to domain-specific knowledge bases, maintained by domain experts. KNAVE-II was designed according to a set of well-defined desiderata. The architecture enables exploration along both absolute (calendar-based) and relative (clinically meaningful) time-lines. The underlying architecture uses standardized vocabularies (such as a controlled dictionary for laboratory tests and physical observations), and predefined mappings to local data sources, for communication among its various components. Thus, the new framework enables users to access and explore multiple remote heterogeneous databases, without explicitly knowing their local structure and vocabulary, through a filter of a set of task-specific knowledge bases. The complete architecture has been implemented and is currently evaluated by expert clinicians in several medical domains, such as oncology, involving monitoring of chronic patients. "
Shahar Y, Boaz D, Tahan G et al. A Web-Based System for Interactive Visualization and Exploration of Time-oriented Clinical Data and Their Abstractions. Proc AMIA Symp. 2003;:1073.

[PubMed]   []

" In this theater-style demonstration, the speakers will demonstrate KNAVE-II, a Web-based distributed system for interactive visualization and exploration of large amounts of time-oriented clinical data from multiple sources, and of clinically meaningful concepts (abstractions) derivable from these data. The KNAVE-II system and its complete underlying architecture provide a solution to the data overload problem. "
Shahar Y, Cheng C. Intelligent visualization and exploration of time-oriented clinical data. Top Health Inf Manage. 1999 Nov;20(2):15-31.

[PubMed]   []

" Physicians and other care providers often need to quickly browse and interpret large numbers of time-oriented clinical data. Reducing the information overload involving such tasks is a major goal for medical information systems. 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 derived from these data. We build on our work on abstraction of time-oriented clinical data using a knowledge base, acquired from expert physicians, of temporal properties of the data. The core module of the new framework is called KNAVE (Knowledge-based Navigation of Abstractions for Visualization and Explanation). Health care providers can manipulate the display though several visualization and exploration operators. These operators have semantics that are domain independent but that are customized automatically for the application by access to the domain-specific knowledge base. The display, which reflects data and derived interpretations in the patient's database, changes when the user explores key relations (e.g., the dependency hierarchy) in the knowledge base of the relevant clinical domain. Preliminary assessment of the initial 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 care providers. "
Cheng, C., Shahar, Y., Puerta, A.R., and Stites, D. P. Navigation and Visualization of Abstractions of Time-Oriented Clinical Data, Fifth International Workshop on Temporal Representation and Reasoning (TIME), 1998, Sanibel Island, Florida

[SMI]    []

" We describe the methodology and architecture of a knowledge-based, interactive visualization system that enables physicians and medical support personnel to draw conclusions from heterogeneous time-oriented clinical data. Our system employs domain-specific ontologies to produce temporal and statistical abstractions of data, and also as the basis for semantically-based browsing and visualization. This builds on previous work in data mining, temporal reasoning, and information visualization, but offers fundamental advantages over any isolated approach, by leveraging each off the others. We performed an evaluation of a prototype, leading us to conclude that users can indeed use the system to perform such semantically-based browsing in a reasonable amount of time. "
start date end date location support
February 2001

Successor to the KNAVE project of the mid-1990s (Stanford Medical Informatics).
December 2004 Medical Informatics Research Center, Ben Gurion Umiversity, Israel Supported in part by NIH award No. LM-06806
contact Websites
Yuval Shahar
yshahar@bgumail.bgu.ac.il

David Boaz
dboaz@bgumail.bgu.ac.il

Department of Information Systems Engineering
Ben-Gurion University of the Negev
Beer-Sheva 84105, ISRAEL

KNAVE II

Medical Informatics Research Center, Ben Gurion Umiversity
Entry in directory: January 13 2004
Last main update: January 13 2004

Search this site
 

 

Privacy policy User agreement Copyright Feedback

Last modified:
© Copyright OpenClinical 2002-2011