Journal Articles

Tiny people listening doctor recommendations from mobile phone

The CrowdHEALTH project and the Hollistic Health Records: Collective Wisdom Driving Public Health Policies

Contributing authors Dimosthenis Kyriazis Argyro Mavrogiorgou Athanasios Kiourtis Abstract Introduction: With the expansion of available Information and Communication Technology (ICT) services, a plethora of data sources provide structured and unstructured… Read More »The CrowdHEALTH project and the Hollistic Health Records: Collective Wisdom Driving Public Health Policies

Male and female medics examining scientific data vector

Aggregating the syntactic and semantic similarity of healthcare data towards their transformation to HL7 FHIR through ontology matching

Contributing authors Athanasios Kiourtis Argyro Mavrogiorgou Dimosthenis Kyriazis Abstract Background and objective: Healthcare systems deal with multiple challenges in releasing information from data silos, finding it almost impossible to be implemented, maintained and upgraded, with difficulties ranging in the technical, security and human interaction fields. Currently, the increasing availability of health data is demanding data-driven approaches, bringing the opportunities to automate healthcare related tasks, providing better disease detection, more accurate prognosis, faster clinical research advance and better fit for patient management. In order to share data with as many stakeholders as possible, interoperability is the only sustainable way for letting systems to talk with one another and getting the complete image of a patient. Thus, it becomes clear that an efficient solution in the data exchange incompatibility is of extreme importance. Consequently, interoperability can develop a communication framework between non-communicable systems, which can be achieved through transforming healthcare data into ontologies. However, the multidimensionality of healthcare domain and the way that is conceptualized, results in the creation of different ontologies with contradicting or overlapping parts. Thus, an effective solution to this problem is the development of methods for finding matches among the various components of ontologies in healthcare, in order to facilitate semantic interoperability.Methods: The proposed mechanism promises healthcare interoperability through the transformation of healthcare data into the corresponding HL7 FHIR structure. In more detail, it aims at building ontologies of healthcare data, which are later stored into a triplestore. Afterwards, for each constructed ontology the syntactic and s​

usiness people meeting to discuss the situation on the marketing

Analyzing data and data sources towards a unified approach for ensuring end-to-end data and data sources quality in healthcare 4.0

Contributing authors Argyro Mavrogiorgou Athanasios Kiourtis Dimosthenis Kyriazis Abstract Background and objective: Healthcare 4.0 is being hailed as the current industrial revolution in the healthcare domain, dealing with billions of heterogeneous IoT data sources that are connected over the Internet and aim at providing real-time health-related information for citizens and patients. It is of major importance to utilize an automated way to identify the quality levels of these data sources, in order to obtain reliable health data. Methods: In this manuscript, we demonstrate an innovative mechanism for assessing the quality of various datasets in correlation with the quality of the corresponding data sources. For that purpose, the mechanism follows a 5-stepped approach through which the available data sources are detected, identified and connected to health platforms, where finally their data is gathered. Once the data is obtained, the mechanism cleans it and correlates it with the quality measurements that are captured from each different data source, in order to finally decide whether these data sources are being characterized as qualitative or not, and thus their data is kept for further analysis. Results: The proposed mechanism is evaluated through an experiment using a sample of 18 existing heterogeneous medical data sources. Based on the captured results, we were able to identify a data source of unknown type, recognizing that it was a body weight scale. Afterwards, we were able to find out that the API method that was responsible for gathering data out of this data source was the getMeasurements() method, while combining both the body weight scale’s quality and its derived data quality, we could decide that this data source was considered as qualitative enough. Conclusions: By taking full advantage of capturing t​h​e​

global technology earth digital background with circuit diagram

A plug ‘n’ play approach for dynamic data acquisition from heterogeneous IoT medical devices of unknown nature

Contributing authors Argyro Mavrogiorgou Athanasios Kiourtis Dimosthenis Kyriazis Abstract With the rapid development of Information Technology, the existence of Cyber-Physical Systems (CPSs) has revealed, which are slowly emerging to dominate… Read More »A plug ‘n’ play approach for dynamic data acquisition from heterogeneous IoT medical devices of unknown nature

digital 5g fifth generation technology background design

Internet of Medical Things (IoMT): Acquiring and Transforming Data into HL7 FHIR through 5G Network Slicing

Contributing authors Argyro Mavrogiorgou Athanasios Kiourtis Dimosthenis Kyriazis Abstract The Healthcare 4.0 era is surrounded by challenges varying from the Internet of Medical Things (IoMT) devices’ data collection, integration and… Read More »Internet of Medical Things (IoMT): Acquiring and Transforming Data into HL7 FHIR through 5G Network Slicing