Toward interactive scheduling systems for managing medical resources

  • Authors:

  • Angelo Oddi;Amedeo Cesta

  • Affiliations:

  • IP-CNR, National Research Council of Italy, Viale Marx 15, I-00137 Rome, Italy;IP-CNR, National Research Council of Italy, Viale Marx 15, I-00137 Rome, Italy

  • Venue:
  • Artificial Intelligence in Medicine
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

Managers of medico-hospital facilities are facing two general problems when allocating resources to activities: (1) to find an agreement between several and contrasting requirements; (2) to manage dynamic and uncertain situations when constraints suddenly change over time due to medical needs. This paper describes the results of a research aimed at applying constraint-based scheduling techniques to the management of medical resources. A mixed-initiative problem solving approach is adopted in which a user and a decision support system interact to incrementally achieve a satisfactory solution to the problem. A running prototype is described called Interactive Scheduler which offers a set of functionalities for a mixed-initiative interaction to cope with the medical resource management. Interactive Scheduler is endowed with a representation schema used for describing the medical environment, a set of algorithms that address the specific problems of the domain, and an innovative interaction module that offers functionalities for the dialogue between the support system and its user. A particular contribution of this work is the explicit representation of constraint violations, and the definition of scheduling algorithms that aim at minimizing the amount of constraint violations in a solution.