Υπηρεσίες διαλειτουργικότητας δεδομένων με εφαρμογή σε ετερογενείς υποδομές και εφαρμογές υγείας
Services of data interoperability applied to heterogeneous healthcare infrastructures and applications
View/ Open
Keywords
Ετερογένεια ; HL7 FHIR ; Σημασιολογία ; Semantics ; Διαλειτουργικότητα δεδομένων ; Ηλεκτρονική υγεία ; ΟντολογίαAbstract
In the last decade, there has been a transition from a data-poor to a data-rich world, with the aim of improving the quality of transport, governance, environment, communication and health. Much of this unprecedented increase in data generation can be attributed to the abundance of thousands of mobile devices, wearables, and sensors. Such thing results into a myriad of heterogeneous devices that will be connected to the world of Internet of Things (IoT), producing data of different types that may have been collected at different locations and time scales, by different devices. Most of these devices are typically characterized by a high degree of heterogeneity, in terms of having different characteristics, capabilities, or network specifications, needing to be easily manageable in particular with regard to the management of the heterogeneous data they generate. Especially for the Internet of Medical Things (IoMT) devices that are widely adopted and used in Healthcare 4.0, the need for using, understanding, and processing of these devices’ data is an issue of vital importance. However, with regard to the best use of this data, heterogeneity, complexity, noise and imperfection are among their most common challenges. It is undeniable that vast amounts of heterogeneous medical data are becoming available in various healthcare organizations and devices, thus completely reshaping the Healthcare 4.0. In order for these heterogeneous medical data to be exchanged with as many stakeholders as possible, and to be a key driver of providing personalized and efficient medical care to patients and citizens, interoperability is the only way. Additionally, the quality of the healthcare services can be improved, health costs and medical errors can be reduced, and patients’ privacy can be increased, while public health can be completely renewed.
Currently, the rapidly increasing availability of health records is pushing towards the adoption of data-driven approaches, bringing the opportunities for more accurate disease and symptom prognosis, to automate healthcare related tasks, providing better disease detection, and more efficient clinical research. Nevertheless, the healthcare organizations are still facing many difficulties in implementing, maintaining and upgrading their healthcare systems, including many challenges in the technical, security and human interaction fields. Among others, what is missing is an integrated data exchange system for which, in order to exchange data with as many stakeholders as possible to improve public health, interoperability is the only way for letting systems interact with each other. Having in mind that the wearable medical devices market is expected to quadruple, and that hospitals and doctors’ offices nationwide could dramatically improve their patients’ quality of life, such thing results into making the health interoperability task even more daunting. For this purpose, many standardization techniques are annually invested in health data interoperability. Among the different existing researches and standards, the Health Level Seven (HL7) organization provides the development and the framework of standards that are widely used in the medical market and research, with HL7 Fast Healthcare Interoperability Resources (FHIR) being the latest standard created by this organization, for the exchange of clinical information.
The current PhD dissertation aims to create an Interoperability Services’ approach in the form of an automated transformation of heterogeneous medical data deriving from heterogeneous devices. This approach will transform both semantically and syntactically health data of different representation and morphology, in order to identify, match into a single language, and eventually merge it into a common level. For this reason, the mechanisms that were studied more are those that aim in the interoperable exchange of health data and information, between systems belonging to different groups or under different health standards. Following this research, an approach was developed which was able to separate health data into categories according to how they were modelled, and then exporting knowledge, information and metadata, the data was translated into a single language, which retained combined data from other already-standardized health data representation languages. Subsequently, this translation approach was adapted to generate ontologies through specific metamodel layers and ontologies, with the ultimate goal of jointly rendering the data in a single format. Using the created ontologies, the next approach was to create ontologies and to compare them with individual HL7 FHIR resources’ ontologies due to its worldwide dissemination and adoption. This comparison concerned both the syntactic and the semantic mapping of the ontologies so that the ontologies of the health data can be mapped to the ontologies of the HL7 FHIR resources. The final approach was therefore based on the above-mentioned solution, where both the ontology implementation mechanisms, but also the syntactic and semantic comparison and mapping, were improved based on relevant experimental tests.
Focusing on the healthcare domain, most of the existing health data interoperability practices and techniques are based on health standards as well as mechanisms for ontological transformations and mappings. However, these are designed for specific cases of use with the pre-defined format in which the data must be entered without having adaptability, without the ability to be considered as holistic solutions. This gap is covered by the current PhD dissertation, delivering a unified and generalized approach that can be applied automatically to any set of health data without the need for pre-processing, assigning and matching this data to one of the most powerful and promising health standards, the HL7 FHIR. The results of the experimental tests listed below, evaluate and demonstrate the operation and efficiency of the proposed approach, making it possible to use it for integration into multiple sectors and environments, particularly in the field of health care, as well as in the fields of telecommunications and networks, devices’ identification, e-Government and e-Procurement.