Explaining Medical Model Exceptions

Vorobieva, Olga

doi:10.1007/978-3-642-14464-6_12

Cited by 1 publication

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These are the most time consuming and resource demanding patients, for which intelligent decision support is particularly called for. Our approach is in line with other hybrid methods that use CBR to handle outliers, exceptions, and non-compliances, while generalization-based methods take care of the more common type of situations [4].…”

Section: The Data Level Architecturementioning

confidence: 62%

“…There is ample evidence that clinicians partly reason from theoretical knowledge, and partly from case-specific or prototype-based experience, depending on how strong causal theories the particular medical area is supported with [3]. It has been argued that computerized medical decision support should to a larger degree concentrate on the rare but difficult patient cases, instead of the more frequent routine ones [4], [5]. Past patient cases provide a level of specificity that is focused on single patients rather than generalized principles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid CBR and BN architecture refined through data analysis

Bruland

Aamodt

Langseth

2011

2011 11th International Conference on Intelligent Systems Design and Applications

View full text Add to dashboard Cite

Abstract-The overall goal of this research is to study reasoning under uncertainty by combining Bayesian Networks and Case-Based Reasoning through constructing an experimental decision support system for classification of cancer pain. We have experimentally analysed a medical dataset in order to reveal properties of the data with respect to properties of the two reasoning methods. We also preprocessed our medical data with help from a clinical expert, which resulted in four data sets with different characteristics. This culminates in a hybrid system architecture, where CBR handles the exceptions or outliers with respect to the distribution of the data and the target class, while BN handles the more common situations. Through a set of experiments under varying conditions we show that a hybrid BN+CBR system is favorable over each single method.

show abstract

Section: The Data Level Architecturementioning

confidence: 62%