Theme: Medical guidelines

From Master Projects
Jump to: navigation, search

About Theme: Medical guidelines

  • This project has not yet been fulfilled.
  • This project fits in the following Bachelor programs: {{#arraymap:|, |xXx|bachelorproject within::xXx|,}}
  • This project fits in the following masterareas: {{#arraymap:Knowledge Technology and Intelligent Internet Applications, Technical Artificial Intelligence|, |xXx|project within::xXx|,}}


During the last decade, evidence-based medicine has given rise to an increasing number of medical practice guidelines and protocols. A medical guideline describes a procedure for particular patient groups. These medical guidelines are studied in both the medical domain and in AI. Our focus is on studying of KR languages for representing such guidelines, and perform various forms of reasoning with such guidelines. For instance projects on the following themes are possible:

  • Exploiting medical ontologies for developing guidelines.
  • Combining reasoning with the patient data and medical guidelines. The main problem here is the mismatch between the terminology used in the patient data and the guideline.
Consider the relation between guideline and patient records (does the guideline mention findings/data that should be retrieved from or stored in the patient records, provide support for this?)
  • Making specialised guideline for a specific group based on existing guidelines. For instance make a dialyse guideline for diabetes patient. Modelling a guideline in different representation languages (for instance Gaston, Asbru) and analyse the different models.
  • Develop an approach for extracting the right information of guideline for a particular goal or context (for instance a patient version of the guideline, a therapist version of the guideling etc.) Instead of considering the textual guideline as input (from textual guideline to structured form), we can also use the structured form as output. (e.g. generate a patient-oriented (simplified/personalised) version of the guideline once we have the structured form.
  • Evidence based guidelines are based on literature. How to incorporate updates from literature into the guidelines. The first step is how to find these papers, the second one is how to exploit these to give support for updating the guideline.
  • How to improve the transition from original textual form of evidence-based guideline to structured computer-based representation.
  • Consider the quality indicators that come with the guideline. The main question here is which data should be collected during guideline implementation for quality assurance.
  • Make special provision for updates of the guidelines: if the text of a guideline changes, decide where the computer representation should change (and give support on how).
  • Make special provision for local "adaptations" of guidelines: given a general

  national guideline, how to adapt this to local circumstances while keeping the link with the national guideline.