Scientific article
Open access

Using multimodal mining to drive clinical guidelines development

Published inStudies in health technology and informatics, vol. 169, p. 477-481
Publication date2011

We present exploratory investigations of multimodal mining to help designing clinical guidelines for antibiotherapy. Our approach is based on the assumption that combining various sources of data, such as the literature, a clinical datawarehouse, as well as information regarding costs will result in better recommendations. Compared to our baseline recommendation system based on a question-answering engine built on top of PubMed, an improvement of +16% is observed when clinical data (i.e. resistance profiles) are injected into the model. In complement to PubMed, an alternative search strategy is reported, which is significantly improved by the use of the combined multimodal approach. These results suggest that combining literature-based discovery with structured data mining can significantly improve effectiveness of decision-support systems for authors of clinical practice guidelines.

  • Algorithms
  • Anti-Bacterial Agents/economics/therapeutic use
  • Computer Systems
  • Decision Support Systems, Clinical
  • Drug Costs
  • Humans
  • National Institutes of Health (U.S.)
  • Practice Guidelines as Topic
  • PubMed
  • Staphylococcus aureus/metabolism
  • Staphylococcus epidermidis/metabolism
  • Statistics as Topic/methods
  • United States
Citation (ISO format)
PASCHE, Emilie et al. Using multimodal mining to drive clinical guidelines development. In: Studies in health technology and informatics, 2011, vol. 169, p. 477–481. doi: 10.3233/978-1-60750-806-9-477
Main files (1)
Article (Published version)
ISSN of the journal0926-9630

Technical informations

Creation06/04/2012 8:09:00 PM
First validation06/04/2012 8:09:00 PM
Update time03/14/2023 5:37:28 PM
Status update03/14/2023 5:37:28 PM
Last indexation05/02/2024 12:34:13 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack