Limits...
Fine-grained information extraction from German transthoracic echocardiography reports.

Toepfer M, Corovic H, Fette G, Klügl P, Störk S, Puppe F - BMC Med Inform Decis Mak (2015)

Bottom Line: In particular, principal aspects as defined in a standardized external terminology were recognized with f 1=.989 (micro average) and f 1=.963 (macro average).As a result of keyword matching and restraint concept extraction, the system obtained high precision also on unstructured or exceptionally short documents, and documents with uncommon layout.Extracted results populate a clinical data warehouse which supports clinical research.

View Article: PubMed Central - PubMed

Affiliation: Chair of Computer Science VI, University of Würzburg, Am Hubland, Würzburg, D-97074, Germany. martin.toepfer@uni-wuerzburg.de.

ABSTRACT

Background: Information extraction techniques that get structured representations out of unstructured data make a large amount of clinically relevant information about patients accessible for semantic applications. These methods typically rely on standardized terminologies that guide this process. Many languages and clinical domains, however, lack appropriate resources and tools, as well as evaluations of their applications, especially if detailed conceptualizations of the domain are required. For instance, German transthoracic echocardiography reports have not been targeted sufficiently before, despite of their importance for clinical trials. This work therefore aimed at development and evaluation of an information extraction component with a fine-grained terminology that enables to recognize almost all relevant information stated in German transthoracic echocardiography reports at the University Hospital of Würzburg.

Methods: A domain expert validated and iteratively refined an automatically inferred base terminology. The terminology was used by an ontology-driven information extraction system that outputs attribute value pairs. The final component has been mapped to the central elements of a standardized terminology, and it has been evaluated according to documents with different layouts.

Results: The final system achieved state-of-the-art precision (micro average.996) and recall (micro average.961) on 100 test documents that represent more than 90 % of all reports. In particular, principal aspects as defined in a standardized external terminology were recognized with f 1=.989 (micro average) and f 1=.963 (macro average). As a result of keyword matching and restraint concept extraction, the system obtained high precision also on unstructured or exceptionally short documents, and documents with uncommon layout.

Conclusions: The developed terminology and the proposed information extraction system allow to extract fine-grained information from German semi-structured transthoracic echocardiography reports with very high precision and high recall on the majority of documents at the University Hospital of Würzburg. Extracted results populate a clinical data warehouse which supports clinical research.

No MeSH data available.


Integrated terminology development and information extraction workbench. a terminology editor, b query and search tool for free strings, terminology concepts and annotations, c document collection view, d annotation editor for documents from the collection in (c)
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4643516&req=5

Fig4: Integrated terminology development and information extraction workbench. a terminology editor, b query and search tool for free strings, terminology concepts and annotations, c document collection view, d annotation editor for documents from the collection in (c)

Mentions: Terminology acquisition was assisted by a tool to be used by domain experts for integrated terminology construction, terminology management, information extraction, reference standard (gold standard) annotation and evaluation (Fig. 4). A predecessor of the system has been described in [37]. The terminology as shown to the user is depicted in Fig. 4a. The software is especially tailored to support the domain expert’s process model that is shown in Fig. 3. It consists of a few general steps: initial automatic aggregation of training documents and generation of concept proposals, terminology refinement based on aggregated documents, terminology refinement based on unmodified documents, mapping of concepts to standardized terminologies (optional), evaluation, optional: request for improvement of segmentation or pre-/postprocessing rules and start of a new refinement iteration. When the system reaches sufficient quality, it is deployed and integrated into the clinical data warehouse system.Fig. 4


Fine-grained information extraction from German transthoracic echocardiography reports.

Toepfer M, Corovic H, Fette G, Klügl P, Störk S, Puppe F - BMC Med Inform Decis Mak (2015)

Integrated terminology development and information extraction workbench. a terminology editor, b query and search tool for free strings, terminology concepts and annotations, c document collection view, d annotation editor for documents from the collection in (c)
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4643516&req=5

Fig4: Integrated terminology development and information extraction workbench. a terminology editor, b query and search tool for free strings, terminology concepts and annotations, c document collection view, d annotation editor for documents from the collection in (c)
Mentions: Terminology acquisition was assisted by a tool to be used by domain experts for integrated terminology construction, terminology management, information extraction, reference standard (gold standard) annotation and evaluation (Fig. 4). A predecessor of the system has been described in [37]. The terminology as shown to the user is depicted in Fig. 4a. The software is especially tailored to support the domain expert’s process model that is shown in Fig. 3. It consists of a few general steps: initial automatic aggregation of training documents and generation of concept proposals, terminology refinement based on aggregated documents, terminology refinement based on unmodified documents, mapping of concepts to standardized terminologies (optional), evaluation, optional: request for improvement of segmentation or pre-/postprocessing rules and start of a new refinement iteration. When the system reaches sufficient quality, it is deployed and integrated into the clinical data warehouse system.Fig. 4

Bottom Line: In particular, principal aspects as defined in a standardized external terminology were recognized with f 1=.989 (micro average) and f 1=.963 (macro average).As a result of keyword matching and restraint concept extraction, the system obtained high precision also on unstructured or exceptionally short documents, and documents with uncommon layout.Extracted results populate a clinical data warehouse which supports clinical research.

View Article: PubMed Central - PubMed

Affiliation: Chair of Computer Science VI, University of Würzburg, Am Hubland, Würzburg, D-97074, Germany. martin.toepfer@uni-wuerzburg.de.

ABSTRACT

Background: Information extraction techniques that get structured representations out of unstructured data make a large amount of clinically relevant information about patients accessible for semantic applications. These methods typically rely on standardized terminologies that guide this process. Many languages and clinical domains, however, lack appropriate resources and tools, as well as evaluations of their applications, especially if detailed conceptualizations of the domain are required. For instance, German transthoracic echocardiography reports have not been targeted sufficiently before, despite of their importance for clinical trials. This work therefore aimed at development and evaluation of an information extraction component with a fine-grained terminology that enables to recognize almost all relevant information stated in German transthoracic echocardiography reports at the University Hospital of Würzburg.

Methods: A domain expert validated and iteratively refined an automatically inferred base terminology. The terminology was used by an ontology-driven information extraction system that outputs attribute value pairs. The final component has been mapped to the central elements of a standardized terminology, and it has been evaluated according to documents with different layouts.

Results: The final system achieved state-of-the-art precision (micro average.996) and recall (micro average.961) on 100 test documents that represent more than 90 % of all reports. In particular, principal aspects as defined in a standardized external terminology were recognized with f 1=.989 (micro average) and f 1=.963 (macro average). As a result of keyword matching and restraint concept extraction, the system obtained high precision also on unstructured or exceptionally short documents, and documents with uncommon layout.

Conclusions: The developed terminology and the proposed information extraction system allow to extract fine-grained information from German semi-structured transthoracic echocardiography reports with very high precision and high recall on the majority of documents at the University Hospital of Würzburg. Extracted results populate a clinical data warehouse which supports clinical research.

No MeSH data available.