FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2015168986> ?p ?o ?g. }

• W2015168986 abstract "Electronic health records (EHRs) provide a potentially valuable source of information for pharmacovigilance. However, adverse drug events (ADEs), which can be encoded in EHRs with specific diagnosis codes, are heavily under-reported. To provide more accurate estimates for drug safety surveillance, machine learning systems that are able to detect ADEs could be used to identify and suggest missing ADE-specific diagnosis codes. A fundamental consideration when building such systems is how to represent the EHR data to allow for accurate predictive modeling. In this study, two types of clinical code are used to represent drugs and diagnoses: the Anatomical Therapeutic Chemical Classification System (ATC) and the International Statistical Classification of Diseases and Health Problems (ICD). More specifically, it is investigated whether their hierarchical structure can be exploited to improve predictive performance. The use of random forests with feature sets that include only the original, low-level, codes is compared to using random forests with feature sets that contain all levels in the hierarchies. An empirical investigation using thirty datasets with different ADE targets is presented, demonstrating that the predictive performance, in terms of accuracy and area under ROC curve, can be significantly improved by exploiting codes on all levels in the hierarchies, compared to using only the low-level encoding. A further analysis is presented in which two strategies are employed for adding features level-wise according to the concept hierarchies: top-down, starting with the highest abstraction levels, and bottom-up, starting with the most specific encoding. The main finding from this subsequent analysis is that predictive performance can be kept at a high level even without employing the more specific levels in the concept hierarchies." @default.
• W2015168986 created "2016-06-24" @default.
• W2015168986 creator A5011845704 @default.
• W2015168986 creator A5033008105 @default.
• W2015168986 creator A5046274853 @default.
• W2015168986 date "2014-09-01" @default.
• W2015168986 modified "2023-09-24" @default.
• W2015168986 title "Detecting Adverse Drug Events Using Concept Hierarchies of Clinical Codes" @default.
• W2015168986 cites W1507447159 @default.
• W2015168986 cites W1520812622 @default.
• W2015168986 cites W1560686237 @default.
• W2015168986 cites W1798922800 @default.
• W2015168986 cites W1875061881 @default.
• W2015168986 cites W1975557539 @default.
• W2015168986 cites W1990788472 @default.
• W2015168986 cites W1991567209 @default.
• W2015168986 cites W2004910511 @default.
• W2015168986 cites W2009890917 @default.
• W2015168986 cites W2040555718 @default.
• W2015168986 cites W2080995941 @default.
• W2015168986 cites W2100899314 @default.
• W2015168986 cites W2120054760 @default.
• W2015168986 cites W2135102212 @default.
• W2015168986 cites W2135493362 @default.
• W2015168986 cites W2137241642 @default.
• W2015168986 cites W2148303708 @default.
• W2015168986 cites W2149863648 @default.
• W2015168986 cites W2160732112 @default.
• W2015168986 cites W2911964244 @default.
• W2015168986 doi "https://doi.org/10.1109/ichi.2014.46" @default.
• W2015168986 hasPublicationYear "2014" @default.
• W2015168986 type Work @default.
• W2015168986 sameAs 2015168986 @default.
• W2015168986 citedByCount "19" @default.
• W2015168986 countsByYear W20151689862014 @default.
• W2015168986 countsByYear W20151689862015 @default.
• W2015168986 countsByYear W20151689862016 @default.
• W2015168986 countsByYear W20151689862019 @default.
• W2015168986 countsByYear W20151689862020 @default.
• W2015168986 crossrefType "proceedings-article" @default.
• W2015168986 hasAuthorship W2015168986A5011845704 @default.
• W2015168986 hasAuthorship W2015168986A5033008105 @default.
• W2015168986 hasAuthorship W2015168986A5046274853 @default.
• W2015168986 hasConcept C197934379 @default.
• W2015168986 hasConcept C2780035454 @default.
• W2015168986 hasConcept C41008148 @default.
• W2015168986 hasConcept C71924100 @default.
• W2015168986 hasConcept C98274493 @default.
• W2015168986 hasConceptScore W2015168986C197934379 @default.
• W2015168986 hasConceptScore W2015168986C2780035454 @default.
• W2015168986 hasConceptScore W2015168986C41008148 @default.
• W2015168986 hasConceptScore W2015168986C71924100 @default.
• W2015168986 hasConceptScore W2015168986C98274493 @default.
• W2015168986 hasLocation W20151689861 @default.
• W2015168986 hasOpenAccess W2015168986 @default.
• W2015168986 hasPrimaryLocation W20151689861 @default.
• W2015168986 hasRelatedWork W1978035733 @default.
• W2015168986 hasRelatedWork W2044550192 @default.
• W2015168986 hasRelatedWork W2066101111 @default.
• W2015168986 hasRelatedWork W2096533928 @default.
• W2015168986 hasRelatedWork W2160976181 @default.
• W2015168986 hasRelatedWork W2362821665 @default.
• W2015168986 hasRelatedWork W2531132564 @default.
• W2015168986 hasRelatedWork W3031362645 @default.
• W2015168986 hasRelatedWork W31630271 @default.
• W2015168986 hasRelatedWork W3209449754 @default.
• W2015168986 isParatext "false" @default.
• W2015168986 isRetracted "false" @default.
• W2015168986 magId "2015168986" @default.
• W2015168986 workType "article" @default.