SeDIE: A Semantic-Driven Engine for Integration of Healthcare Data

Dhayne, Houssein; Kilany, Rima; Haque, Rafiqul; Taher, Yéhia

doi:10.1109/bibm.2018.8621243

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rigidity of the triple format, however, is what allows the data contained in triples to be understood and consumed by different agents across the web-in other words, enabling interoperability. A number of prior studies have used triplestores for storing and analyzing EHR data, with a variety of rationales for doing so, (11)(12)(13)(14)(15)(16)(17)(18)(19)(20)(21) though this approach appears to exist outside the computable phenotyping mainstream. Some of the specific affordances of triplestores for clinical data are listed below.…”

Section: Triplestores For Storing and Analyzing Clinical Datamentioning

confidence: 99%

Cohort Identification Using Semantic Web Technologies: Triplestores as Engines for Complex Computable Phenotyping

Pfaff

Bradford

Clark

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundComputable phenotypes are increasingly important tools for patient cohort identification. As part of a study of risk of chronic opioid use after surgery, we used a Resource Description Framework (RDF) triplestore as our computable phenotyping platform, hypothesizing that the unique affordances of triplestores may aid in making complex computable phenotypes more interoperable and reproducible than traditional relational database queries.To identify and model risk for new chronic opioid users post-surgery, we loaded several heterogeneous data sources into a Blazegraph triplestore: (1) electronic health record data; (2) claims data; (3) American Community Survey data; and (4) Centers for Disease Control Social Vulnerability Index, opioid prescription rate, and drug poisoning rate data. We then ran a series of queries to execute each of the rules in our “new chronic opioid user” phenotype definition to ultimately arrive at our qualifying cohort.ResultsOf the 4,163 patients in the denominator, our computable phenotype identified 248 patients as new chronic opioid users after their index surgical procedure. After validation against charts, 228 of the 248 were revealed to be true positive cases, giving our phenotype a PPV of 0.92.ConclusionWe successfully used the triplestore to execute the new chronic opioid user phenotype logic, and in doing so noted some advantages of the triplestore in terms of schemalessness, interoperability, and reproducibility. Future work will use the triplestore to create the planned risk model and leverage the additional links with ontologies, and ontological reasoning.

show abstract

Section: Triplestores For Storing and Analyzing Clinical Datamentioning

confidence: 99%

Cohort Identification Using Semantic Web Technologies: Triplestores as Engines for Complex Computable Phenotyping

Pfaff

Bradford

Clark

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A typical step in medical data processing that aggregates unstructured clinical notes is the identification of these medical concepts from UMLS using MetaMap [138]. UMLS uses as well, the notion of a Concept Unique Identifier (CUI) to map terms with similar meaning in different terminologies [139]. The difficulty with current labeling techniques is that they do not understand model relationships between classes.…”

Section: ) Data Annotation and Labelingmentioning

confidence: 99%

In Search of Big Medical Data Integration Solutions - A Comprehensive Survey

Dhayne

Haque²,

Kilany

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

In recent years, the radical advancement of technologies has given rise to an abundance of software applications, social media, and smart devices such as smartphone, sensors, and so on. More extensive use of these applications and tools in various industrial domains has led to data deluge, which has fostered enormous challenges and opportunities. However, it is not only the volume of the data but also the speed, variety, and uncertainty, which are promoting a massive challenge for traditional technologies such as data warehouse. These diverse and unprecedented characteristics have engendered the notion of ''Big Data.'' The data-intensive industries have been experiencing a wide variety of challenges in terms of processing, managing, and analysis of data. For instance, the healthcare sector is confronting difficulties in respect of integration or fusion of diverse medical data stemming from multiple heterogeneous sources. Data integration is critically important within the healthcare sector because it enriches data, enhances its value, and more importantly paves a solid foundation for highly efficient and effective healthcare analytics such as predicting diseases or an outbreak. Several data integration technologies and tools have been developed over the last two decades. This paper aims at studying data integration technologies, tools, and applications within the healthcare domain. Furthermore, this paper discusses future research directions in the integration of Big healthcare data. INDEX TERMS Big data, data integration, healthcare data.

show abstract

Towards Semantic Data Integration in Resource-Limited Settings for Decision Support on Gait-Related Diseases

Daramola

Moser

2021

Advances in Computational Intelligence and Robotics

View full text Add to dashboard Cite

Resource-limited settings (RLS) are characterised by lack of access to adequate resources such as ICT infrastructure, qualified medical personnel, healthcare facilities, and affordable healthcare for common people. The potential for the application of AI and clinical decision support systems in RLS are limited due to these challenges. Towards the improvement of the status quo, this chapter presents the conceptual design of a framework for the semantic integration of health data from multiple sources to facilitate decision support for the diagnosis and treatment of gait-related diseases in RLS. The authors describe how the framework can leverage ontologies and knowledge graphs for semantic data integration to achieve this. The plausibility of the proposed framework and the general imperatives for its practical realisation are also presented.

show abstract

SeDIE: A Semantic-Driven Engine for Integration of Healthcare Data

Cited by 4 publications

References 20 publications

Cohort Identification Using Semantic Web Technologies: Triplestores as Engines for Complex Computable Phenotyping

Cohort Identification Using Semantic Web Technologies: Triplestores as Engines for Complex Computable Phenotyping

In Search of Big Medical Data Integration Solutions - A Comprehensive Survey

Towards Semantic Data Integration in Resource-Limited Settings for Decision Support on Gait-Related Diseases

Contact Info

Product

Resources

About