Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

The interpretation of time-varying data with DIAMON-1

F Steimann1

  • 1100607.704@compuserve.com

Artificial Intelligence in Medicine
|August 1, 1996
PubMed
Summary

Artificial Intelligence (AI) in clinical monitoring needs signal-to-symbol conversion and history-sensitive processing. The DIAMON-1 framework uses fuzzy set theory for trend detection and disease tracking in time-varying patient data.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

On the use and usefulness of fuzzy sets in medical AI.

Artificial intelligence in medicine·2001
Same author

Fuzzy diagnosis.

Artificial intelligence in medicine·1999
Same author

Dependency parsing for medical language and concept representation.

Artificial intelligence in medicine·1998
Same author

Fuzzy set theory in medicine.

Artificial intelligence in medicine·1997
Same author

A method to derive the time of onset of infection from serological findings.

Methods of information in medicine·1997
Same author

Definition of severity and compiling of entry criteria in patients undergoing ECLA: the use of a fuzzy logic expert system.

Acta anaesthesiologica Scandinavica. Supplementum·1996

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Computational Biology

Background:

  • Clinical monitoring generates complex, time-varying data crucial for diagnosis and patient management.
  • Traditional AI methods often struggle with the inherent uncertainty and temporal dynamics of medical data.
  • Effective signal-to-symbol conversion is a prerequisite for applying AI in healthcare.

Observation:

  • The DIAMON-1 framework addresses the challenge of interpreting time-varying clinical data for AI applications.
  • It incorporates methods for trend detection based on data patterns and disease progression modeling.
  • The framework utilizes fuzzy set theory to handle the ambiguity and continuous nature of medical states.

Findings:

  • DIAMON-1 offers two primary methods: trend detection using classes of courses and disease history tracking via deterministic automata.
  • Fuzzy set theory is employed to manage the elasticity of medical categories and patient data.
  • This approach allows discrete models to accurately reflect continuous patient progression through illness stages.

Implications:

  • DIAMON-1 enhances the application of AI in clinical monitoring by improving the interpretation of temporal patient data.
  • This framework can lead to more accurate diagnostic tools and personalized patient management strategies.
  • It provides a robust method for integrating AI with the nuanced realities of clinical practice.

Related Experiment Videos