Provision of Decision Support Through Continuous Prediction of Recurring Clinical Actions

Michal Weisman Raymond, Yuval Shahar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a framework for provision of decision support through the continuous prediction of recurring targets, in particular clinical actions, which can potentially occur more than once in the patient's longitudinal clinical record. We first perform an abstraction of the patient's raw time-stamped data into intervals. Then, we partition the patient's timeline into time windows, and perform frequent temporal patterns mining in the features' window. Finally, we use the discovered patterns as features for a prediction model. We demonstrate the framework on the task of treatment prediction in the Intensive Care Unit, in the domains of Hypoglycemia, Hypokalemia and Hypotension.

Original languageAmerican English
Title of host publicationHealthcare Transformation with Informatics and Artificial Intelligence
EditorsJohn Mantas, Parisis Gallos, Emmanouil Zoulias, Arie Hasman, Mowafa S. Househ, Martha Charalampidou, Andriana Magdalinou
PublisherIOS Press BV
Pages200-203
Number of pages4
ISBN (Electronic)9781643684000
DOIs
StatePublished - 29 Jun 2023
Event21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023 - Athens, Greece
Duration: 1 Jul 20233 Jul 2023

Publication series

NameStudies in Health Technology and Informatics
Volume305

Conference

Conference21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023
Country/TerritoryGreece
CityAthens
Period1/07/233/07/23

Keywords

  • Clinical Decision Support
  • Machine Learning
  • Temporal Data Mining

All Science Journal Classification (ASJC) codes

  • Health Information Management
  • Health Informatics
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Provision of Decision Support Through Continuous Prediction of Recurring Clinical Actions'. Together they form a unique fingerprint.

Cite this