Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Combining multivariate statistics and the think-aloud protocol to assess Human-Computer Interaction barriers in symptom checkers

  • MARCO RUIZ, LUIS|||0000-0001-6349-3162
  • Traver Salcedo, Vicente|||0000-0003-1806-8575
  • Bones, Erlend
  • de la Asuncion, Estela
  • Gabarron, Elia
  • Aviles-Solis, Juan Carlos
  • Lee, Eunji
  • Sato, Keiichi
  • Bellika, Johan G.
[EN] Symptom checkers are software tools that allow users to submit a set of symptoms and receive advice related to them in the form of a diagnosis list, health information or triage. The heterogeneity of their potential users and the number of different components in their user interfaces can make testing with end-users unaffordable. We designed and executed a two-phase method to test the respiratory diseases module of the symptom checker Erdusyk. Phase I consisted of an online test with a large sample of users (n = 53). In Phase I, users evaluated the system remotely and completed a questionnaire based on the Technology Acceptance Model. Principal Component Analysis was used to correlate each section of the interface with the questionnaire responses, thus identifying which areas of the user interface presented significant contributions to the technology acceptance. In the second phase, the think-aloud procedure was executed with a small number of samples (n = 15), focusing on the areas with significant contributions to analyze the reasons for such contributions. Our method was used effectively to optimize the testing of symptom checker user interfaces. The method allowed kept the cost of testing at reasonable levels by restricting the use of the think-aloud procedure while still assuring a high amount of coverage. The main barriers detected in Erdusyk were related to problems understanding time repetition patterns, the selection of levels in scales to record intensities, navigation, the quantification of some symptom attributes, and the characteristics of the symptoms. (C) 2017 Elsevier Inc. All rights reserved., This work was supported by Helse Nord [grant HST1121-13], the Faculty of Health Sciences from UIT The Arctic University of Norway [researcher code 1108], and The Research Council of Norway [grant 248150/O70]. We thank Professor Emeritus Rafael Romero-Villafranca for reviewing the statistical analysis of this paper.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Publication, discovery and interoperability of Clinical Decision Support Systems: A Linked Data approach

  • MARCO RUIZ, LUIS|||0000-0001-6349-3162
  • Pedrinaci, Carlos
  • Maldonado Segura, José Alberto
  • Panziera, Luca
  • Chen, Rong
  • Bellika, J. Gustav
[EN] Background: The high costs involved in the development of Clinical Decision Support Systems (CDSS) make it necessary to share their functionality across different systems and organizations. Service Oriented Architectures (SOA) have been proposed to allow reusing CDSS by encapsulating them in a Web service. However, strong barriers in sharing CDS functionality are still present as a consequence of lack of expressiveness of services interfaces. Linked Services are the evolution of the Semantic Web Services paradigm to process Linked Data. They aim to provide semantic descriptions over SOA implementations to overcome the limitations derived from the syntactic nature of Web services technologies. Objective: To facilitate the publication, discovery and interoperability of CDS services by evolving them into Linked Services that expose their interfaces as Linked Data. Materials and methods: We developed methods and models to enhance CDS SOA as Linked Services that define a rich semantic layer based on machine interpretable ontologies that powers their interoperability and reuse. These ontologies provided unambiguous descriptions of CDS services properties to expose them to the Web of Data. Results: We developed models compliant with Linked Data principles to create a semantic representation of the components that compose CDS services. To evaluate our approach we implemented a set of CDS Linked Services using a Web service definition ontology. The definitions of Web services were linked to the models developed in order to attach unambiguous semantics to the service components. All models were bound to SNOMED-CT and public ontologies (e.g. Dublin Core) in order to count on a lingua franca to explore them. Discovery and analysis of CDS services based on machine interpretable models was performed reasoning over the ontologies built. Discussion: Linked Services can be used effectively to expose CDS services to the Web of Data by building on current CDS standards. This allows building shared Linked Knowledge Bases to provide machine interpretable semantics to the CDS service description alleviating the challenges on interoperability and reuse. Linked Services allow for building digital libraries of distributed CDS services that can be hosted and maintained in different organizations., This work was supported by Helse Nord [grant HST1121-13]; the EU project COMPOSE [FP7-317862]; the Spanish Ministry of Economy and Competitiveness and the FEDER program [grants TIN2014-53749-C2-1-R and PTQ-12-05620]. We would like to thank Dr. Catalina Martinez-Costa for providing insights into Semantic Patterns and the outcomes of the SemanticHealthNet project. We are grateful to Cambio Healthcare Systems for providing the CDS modules used in the study. We would like to acknowledge Dr. Ian McNicoll, Dr. Gro Berntsen and Dr. Nils Kolstrup for providing information about how clinicians discover and analyze CDS guidelines and systems. Finally, we thank IHTSDO, Indizen and Ontotext for the technologies and licenses provided