eXiT*CBR: A framework for case-based medical diagnosis development and experimentation

Beatriz López, Carles Pous, Pablo Gay, Albert Pla, Judith Sanz, Joan Brunet
2011 Artificial Intelligence in Medicine  
Objective: Medical applications have special features that require the development of particular tools. The eXiT*CBR framework is proposed to support the development of and experimentation with new case-based reasoning (CBR) systems for medical diagnosis. Method : Our framework offers a modular, heterogeneous environment that combines different CBR techniques for different application requirements. The graphical user interface allows easy navigation through a set of experiments that are
more » ... alized as plots (receiver operator characteristics (ROC) curves and other kinds of charts). This user-friendly navigation allows physicians to analyze the experiments easily. Experiment replication * is managed automatically by the system. Used as a plug-in on the same interface, eXiT*CBR can work with any data mining technique such as learning the relevance of features. Results: The results show that eXiT*CBR is a user-friendly tool that facilitates physicians to use the CBR method to determine a diagnoses in the field of breast cancer, dealing with different patterns implicit in the data. Conclusions: Although several tools have been developed to facilitate the rapid construction of prototypes, none of them has taken into account the particularities of medical applications. eXiT*CBR aims to fill this gap. It uses CBR methods and common medical visualization tools, such as ROC plots, that facilitate the interpretation of the results. The navigation capabilities of this tool facilitate the tuning of the different CBR parameters using experimental results. In addition, the tool allows reproducibility, as the experiments can be replicated as many times as required.
doi:10.1016/j.artmed.2010.09.002 pmid:20971621 fatcat:dwdshqtufrelhpxxwv6ovnbwq4