Deriving Trends in Historical and Real-Time Continuously Sampled Medical Data

Authors:
Apkar Salatian;Jim Hunter
Affiliations:
School of Computer and Mathematical Sciences, The Robert Gordon University, St. Andrew Street, Aberdeen AB25 1HG, UK. as@scms.rgu.ac.uk;Department of Computing Science, King‘s College, University of Aberdeen, Aberdeen AB24 3UE, UK. jhunter@csd.abdn.ac.uk
Venue:
Journal of Intelligent Information Systems - Special issue on integrating artificial intelligene and database technologies
Year:
1999

Citing 5
Cited 17

Towards a general theory of action and time

Artificial Intelligence
Dynamic across-time measurement interpretation

Artificial Intelligence - Special issue: Qualitative reasoning about physical systems II
Digital signal processing: theory, applications, and hardware

Digital signal processing: theory, applications, and hardware
A framework for knowledge-based temporal abstraction

Artificial Intelligence
A General Framework for Building Patient Monitoring Systems

AIME '95 Proceedings of the 5th Conference on Artificial Intelligence in Medicine in Europe: Artificial Intelligence Medicine

Information Systems That also Project into the Future

DNIS '02 Proceedings of the Second International Workshop on Databases in Networked Information Systems
Knowledge-Based Event Detection in Complex Time Series Data

AIMDM '99 Proceedings of the Joint European Conference on Artificial Intelligence in Medicine and Medical Decision Making
Temporal reasoning for decision support in medicine

Artificial Intelligence in Medicine
Distributed, intelligent, interactive visualization and exploration of time-oriented clinical data and their abstractions

Artificial Intelligence in Medicine
Temporal abstraction in intelligent clinical data analysis: A survey

Artificial Intelligence in Medicine
Incremental application of knowledge to continuously arriving time-oriented data

Journal of Intelligent Information Systems
A Human-Machine Cooperative Approach for Time Series Data Interpretation

AIME '07 Proceedings of the 11th conference on Artificial Intelligence in Medicine
Engineering of Software-Intensive Systems: State of the Art and Research Challenges

Software-Intensive Systems and New Computing Paradigms
Temporal data mining for the quality assessment of hemodialysis services

Artificial Intelligence in Medicine
Avian influenza: Temporal modeling of a human to human transmission case

Expert Systems with Applications: An International Journal
Features for learning local patterns in time-stamped data

LPD'04 Proceedings of the 2004 international conference on Local Pattern Detection
Probabilistic abstraction of uncertain temporal data for multiple subjects

SARA'05 Proceedings of the 6th international conference on Abstraction, Reformulation and Approximation
A new approach to the abstraction of monitoring data in intensive care

AIME'05 Proceedings of the 10th conference on Artificial Intelligence in Medicine
Learning rules with complex temporal patterns in biomedical domains

AIME'05 Proceedings of the 10th conference on Artificial Intelligence in Medicine
Probabilistic abstraction of multiple longitudinal electronic medical records

AIME'05 Proceedings of the 10th conference on Artificial Intelligence in Medicine
Human/computer interaction to learn scenarios from ICU multivariate time series

AIME'05 Proceedings of the 10th conference on Artificial Intelligence in Medicine
Querying temporal clinical databases on granular trends

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Monitors in Intensive Care Units generate large volumes ofcontinuous data which can overwhelm a database and result ininformation overload for the medical staff. Instead of reasoningwith individual data samples of one or more variables, it is betterto work with the trend of the data i.e., whether the data is increasing, decreasing or steady. We have developed a systemwhich abstracts continuous data into trends; it consists of threeconsecutive processes: filtering which smooths the data; temporal interpolation which creates simple intervals betweenconsecutive data points; and temporal inference whichiteratively merges intervals which share similar characteristics intolarger intervals. Storing trends can result in a reduction indatabase volume. Our system has been applied both to historical andreal-time data.