publication . Thesis . 2016

Towards semantic interpretation of clinical narratives with ontology-based text mining

Zhao, Bo;
Open Access English
  • Published: 01 Jan 2016
  • Country: United Kingdom
Abstract
In the realm of knee pathology, magnetic resonance imaging (MRI) has the advantage of visualising all structures within the knee joint, which makes it a valuable tool for increasing diagnostic accuracy and planning surgical treatments. Therefore, clinical narratives found in MRI reports convey valuable diagnostic information. A range of studies have proven the feasibility of natural language processing for information extraction from clinical narratives. However, no study focused specifically on MRI reports in relation to knee pathology, possibly due to the complexity of knee anatomy and a wide range of conditions that may be associated with different anatomical...
Subjects
free text keywords: QA75
Related Organizations
176 references, page 1 of 12

8.1 Summary of contributions .................................................................................................99

Table 2-1 Part-of-speech frequency distributions in clinical and non-clinical english texts (Campbell and S. B. Johnson, 2001).....................................................................................9

Table 2-2 Part-of-speech bigram frequency distributions in clinical and non-clinical english texts (Campbell and S. B. Johnson, 2001).....................................................................................9

Table 2-3 Yearly i2b2 shared task challenges (Uzuner, 2009; Uzuner et al., 2006; 2008; 2007; 2010; 2011; Uzuner and Stubbs, 2015)...............................................................................15

Table 4-1 Comparison of diagnostic values for meniscus tear with and without MRI (Yan et al., 2011) ...................................................................................................................................39

Table 4-2 Training set statistics ...................................................................................................42

Table 4-3 Top 20% frequently occurred semantic types .............................................................44

Table 4-4 Classification of semantic types ..................................................................................45

Table 4-5 Semantic type classifications to annotation tags conversion interpretation and examples .............................................................................................................................................46

Table 4-6 MetaMap performances on development set (Exact match) .......................................47

Table 4-7 Fleiss' Kappa coefficient value interpretation (Landis and Koch, 1977) ....................48

Table 5-1 Statistics of annotated terms on development set........................................................58

Table 6-1 An excerpt of conversion from ontology vocabulary to PathNER dictionary ............69

Table 6-2 Corresponding semantic types for slots.......................................................................81

Table 6-3 System performances on test set over slots .................................................................86

176 references, page 1 of 12
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue