Title :
Attributes for causal inference in electronic healthcare databases
Author :
Reps, Jenna ; Garibaldi, Jonathan M. ; Aickelin, Uwe ; Soria, Daniele ; Gibson, Jack E. ; Hubbard, Richard B.
Author_Institution :
Sch. of Comput. Sci., Univ. of Nottingham, Nottingham, UK
Abstract :
Side effects of prescription drugs present a serious issue. Existing algorithms that detect side effects generally require further analysis to confirm causality. In this paper we investigate attributes based on the Bradford-Hill causality criteria that could be used by a classifying algorithm to definitively identify side effects directly. We found that it would be advantageous to use attributes based on the association strength, temporality and specificity criteria.
Keywords :
causality; drugs; health care; inference mechanisms; medical information systems; patient treatment; Bradford-Hill causality criteria; association strength; causal inference; classifying algorithm; electronic healthcare databases; prescription drugs; side effect detection; specificity criteria; temporality criteria; Algorithm design and analysis; Classification algorithms; Correlation; Databases; Drugs; Hazards; Standards;
Conference_Titel :
Computer-Based Medical Systems (CBMS), 2013 IEEE 26th International Symposium on
Conference_Location :
Porto
DOI :
10.1109/CBMS.2013.6627871
