Published on 11/14/2016 | Strategy
Over the years ,doctors developed their own specialized languages and lexicons to help them store and communicate general medical knowledge and patient-related information efficiently. The promise of a global standard for Electronic Health Care Records is still years away. As we know medical information systems need to be able to communicate complex and detailed medical data securely and efficiently. This is obviously a difficult task and requires a profound analysis of the structure and the concepts of medical terminologies. But while this task sounds daunting it can be achieved by constructing medical domain ontologies for representing medical terminology systems. The most significant benefit that ontologies may bring to healthcare systems is their ability to support the indispensable integration of knowledge and data.
Unfortunately, ontologies are not widely used in software engineering today. They are not well understood by the majority of developers. Undergraduate computer science programs don't usually teach ontologies. There is an urgent need to educate a new generation of ontology-savvy healthcare application developers. I suggest there is a growing need to familiarize oneself with Ontology, and the importance of Semantics.
The goal of an ontology is to achieve a common and shared knowledge that can be transmitted between people and between application systems. Thus, ontologies play an important role in achieving interoperability across organizations and on the Semantic Web, because they aim to capture domain knowledge and their role is to create semantics explicitly in a generic way, providing the basis for agreement within a domain. Thus, ontologies have become a popular research topic in many communities. In fact, ontology is a main component of this research; therefore, the definition, structure and the main operations and applications of ontology are provided.
My goal in this blog is to define the key components necessary to enable true interoperability in the healthcare domain. These same components would benefit any domain specific industry.
• Ontology is about the exact description of things and their relationships.
• For the web, ontology is about the exact description of web information and relationships between web information.
• Ontologies are the next emerging generation of database concepts and technology.
Most importantly, a Domain Specific Ontology can once and for all eliminate the need to integrate disparate data sources.
At a basic level, semantics is simply a data model for linking together two entities (people, places, or things) based on the relationship between them to form a triple. When linked together, triples form a graph that is without hierarchy, is machine readable, and can even be used to infer new facts. With this simple model, it is possible to build a common vocabulary for describing an almost limit-less number of facts and relationships about the world. The standard language for writing triples is RDF (Resource Description Framework), and the standard query language is SPARQL.
Semantic Web is actually an extension of the current one in that it represents information more meaningfully for humans and computers alike. It enables the description of contents and services in machine-readable form, and enables annotating, discovering, publishing, advertising and composing services to be automated. It was developed based on Ontology, which is considered as the backbone of the Semantic Web. In other words, the current Web is transformed from being machine-readable to machine-understandable. In fact, Ontology is a key technique with which to annotate semantics and provide a common, comprehensible foundation for resources on the Semantic Web. Moreover, Ontology can provide a common vocabulary, a grammar for publishing data, and can supply a semantic description of data which can be used to preserve the Ontologies and keep them ready for inference. With this understanding we know The Semantic Web provides a compelling vision for a common framework that allows data to be shared, understood by machines and humans and reused across applications, enterprises, and community boundaries. But it raises many challenges such as the availability of content, ontology development and evolution, scalability, multilinguality, visualization to reduce information overload, and stability of Semantic Web languages. In addressing these challenges, we must focus on efficient ontology building and managing techniques, learning ontologies, and matching the numerous healthcare ontologies that already exist looking for reuse opportunities.
Deriving actionable data and business value from Big Data Analytics requires unifying diverse data sources, including unstructured data and content in order to extract intelligence across these previously disparate data sources. While analyzing any one data source provides marginal value, unified Big Data Analytics returns exponentially more powerful insights. It is well known that traditional relational databases and related business intelligence tools are simply not up to the task of processing and analyzing large volumes of unstructured data and content in a time-efficient or cost-effective way.
The challenge doesn’t end there. In healthcare, it is not enough to simply make unstructured content and data analysis available to healthcare givers and data scientists alongside traditional, structured data analysis. Rather, unstructured content and data must be unified with structured data sources by a common ontological layer that allows users to understand and visualize important correlations between multiple data types and healthcare specific terms. For example, it is not as simple as talking about cancer. There are any number of cancer types, including some of the more common ones including, lung, breast, and prostate cancer. In addition, each of these has different stages. So understanding ontologically, the different variables and being able to relate them across relational databases and document sets into one common entity is really crucial. Using an ontology that describes the exact description of things of cancer and their relationships not just to understand the cancer type and stage, but a given approved drug or treatment is likely to be important from a clinical and treatment perspective.
The Internet of Things paradigm where millions of smart sensors, devices and applications are involved in collecting a vast amount of real-time data only adds to the challenge at hand. The data collected comes from various sources in diverse formats and then processed by different intelligent systems. Even though there are known technologies for most of these smart environments, putting them together to make intelligent and context-aware systems is not an easy task. The reason is that there are semantic inconsistencies between applications and systems. These inconsistencies can be solved by using metadata. Metadata management is a key to make data integration successful. It has to be taken into consideration in the development of systems since it helps in making the systems scalable. For formal metadata management, semantic technologies have been developed. Ontology, which as previously stated, is a part of semantic technologies, plays a significant role in managing metadata of a domain. Ontologies can be used to support data integration in terms of facilitating knowledge sharing and data exchange between participants in a domain. In ontologies, concepts, properties, relations, functions, constraints, and axioms of a particular domain are explicitly defined. By using semantic technologies to exploit the semantics of data, we ease metadata handling introduced by these IoT based smart environments.
While other techniques and tools may be used, overcoming end-user reluctance to embrace new, data-driven decision making technologies and processes cannot be overlooked when embarking on Big Data analytics projects, specifically in healthcare.
This article was originally posted on LinkedIn.
