Analysis of the Suitability of Existing Medical Ontologies for Building a Scalable Semantic Interoperability Solution Supporting Multi-site Collaboration in Oncology

Abstract

Abstract-Semantic interoperability is essential to facilitate efficient collaboration in heterogeneous multi-site healthcare environments. The deployment of a semantic interoperability solution has the potential to enable a wide range of informaticssupported applications in clinical care and research both within a single healthcare organization and in a network of organizations. At the same time, building and deploying a semantic interoperability solution may require significant effort to carry out data transformation and to harmonize the semantics of the information in the different systems. Our approach to semantic interoperability leverages existing healthcare standards and ontologies, focusing first on specific clinical domains and key applications, and gradually expanding the solution when needed. An important objective of this work is to create a semantic link between clinical research and care environments to enable applications such as streamlining the execution of multi-centric clinical trials, including the identification of eligible patients for the trials. This paper presents an analysis of the suitability of several widely-used medical ontologies in the clinical domain: SNOMED-CT, LOINC, MedDRA, to capture the semantics of the clinical trial eligibility criteria, of the clinical trial data (e.g., Clinical Report Forms), and of the corresponding patient record data that would enable the automatic identification of eligible patients. Next to the coverage provided by the ontologies we evaluate and compare the sizes of the sets of relevant concepts and their relative frequency to estimate the cost of data transformation, of building the necessary semantic mappings, and of extending the solution to new domains. This analysis shows that our approach is both feasible and scalable.

Developing Bayesian networks from a dependency‐layered ontology: A proof‐of‐concept in radiation oncology

“…Mapping across platforms to combine data sources into comprehensive models relies on this underlying semantic interoperability. 51,52 The rich semantics in the dependency layered ontology connect domain concepts in a way not found in search engines and thus give it some advantage over those types of resources. As the domain of what is known grows, the power of connecting disparate concepts also grows.…”

“…Moreover, the formalization of terminology also makes possible semantic mapping to oncology information systems, aiding in cross compatibility for a variety of modeling concepts not included in existing protocols such as DICOM, and for which there exists a large amount of currently underutilized data. Mapping across platforms to combine data sources into comprehensive models relies on this underlying semantic interoperability …”

A semantic interoperability approach to support integration of gene expression and clinical data in breast cancer

“…These services provided uniform access to data stored in the SIL, exploiting semantic and abstraction capabilities of the CIM. The core dataset integrates terminologies such as SNOMED-CT, HGNC and LOINC for covering the clinical scenario domain [30]. The CDM is a HL7 RIM-based structure required to homogenize data models of information systems from different institutions.…”

“…For this reason, the semantic layer can store both the original and the annotated code. The annotation process strongly depends on each data source, from original data sources structured with coded values where automatic translations using UMLS are possible, to free-text data sources where annotation is a more laborious process that could be enhanced using NLP techniques [30]. In any case, after the annotation process, a manual validation of mapped terms by a domain expert is required.…”