Integrating Different Methodologies for Insulin Therapy Support in Type 1 Diabetic Patients

  • Authors:
  • Stefania Montani;Paolo Magni;Abdul V. Roudsari;Ewart R. Carson;Riccardo Bellazzi

  • Affiliations:
  • -;-;-;-;-

  • Venue:
  • AIME '01 Proceedings of the 8th Conference on AI in Medicine in Europe: Artificial Intelligence Medicine
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a Multi Modal Reasoning (MMR) methodology designed to provide physicians with knowledge management and decision support functionality in the context of type 1 diabetes mellitus care. The MMR system performs a tight integration of Case Based Reasoning (CBR), Rule Based Reasoning (RBR) and Model Based Reasoning (MBR), with the aim of suggesting a therapy properly tailored to the patient's needs, overcoming the single approaches' limitations. This methodology allows the exploitation of the implicit knowledge embedded in patients' visits (past cases) and in monitoring data through Case Based retrieval. Moreover the explicit domain knowledge is formalized in a set of production rules and in a mathematical model. The system has been preliminary tested both on simulated and on real patients' data.