Implement a Connected Inventory of enterprise data assets, based on a knowledge graph, to get business insights about the current status and trends, risk and opportunities, based on a holistic interrelated view of all enterprise assets.
Improve engagement, discoverability and personalized recommendations for Financial and Business Media, Market Intelligence and Investment Information Agencies,Science, Technology and Medicine Publishers, etc.
Ontotext Helps a Leading US Children’s Hospital Track the Impact of Its Faculty Research
Ontotext worked with a leading US Children's Hospital, which was not only a medical service provider but also a major research center with hundreds of faculty members engaged in a variety of scientific activities. By using semantic data integration and leveraging both proprietary and public Linked Open Data sources to create a comprehensive knowledge graph, Ontotext helped the hospital keep better track of these research activities.
A major Children’s Hospital in the Midwestern United States needed to be able to efficiently track the research activities of its faculty members and to assess its impact as an institution on the current state of pediatrics medical research. Apart from their medical duties, the Hospital’s several hundred faculty members were engaged in a variety of scientific activities like:
publishing more than ten thousand peer-reviewed scientific articles;
speaking at research conferences;
participating in major research projects and in various stages of major clinical trials;
receiving awards and citations for their work;
collaborating with other research institutions across the globe.
The main challenges were related to the fragmented nature of the available information:
Each faculty member wore many hats (employee, doctor, author of peer-reviewed publications, investigator in clinical trials, public figure participating in conferences and receiving recognition for their scientific work, etc.).
Different departments kept their data in various systems without a unified access or a way to identify individuals between different databases.
The methods used for collecting the data varied, which led to differences in coverage and reliability (for activities in which the institution was directly involved the data was kept internally but other information was gathered by various self-reporting protocols.)
Another challenge was that, on top of being fragmented, the data about academic publications is very complex and hence extracting insights from such data requires access to huge volumes of structured and unstructured information. Executing such complex analytical tasks by hand requires a lot of effort by people closely familiar with the field of research and there is still a significant risk of missing some important connections.
The Solution: Semantic Data Integration of Proprietary and Public LOD Sources into a Doctor 360-degree Comprehensive Knowledge Graph
The knowledge graph based solution provided by Ontotext enabled the integration of both internal and some large external data sources (Linked Open Data). This included structured information about academic output (PubMed, Microsoft Academic Graph, which was replaced by OpenAlex as of 2022, and CrossRef, etc.), government data providers (such as ClinicalTrials.gov and the NIH register about grants in Healthcare), etc.
Combining and integrating all these external sources with the Hospital’s proprietary data in a big knowledge graph, provided a unified access to all the data and made it easy to query, track and analyze.
Ontotext’s approach consisted of the following steps:
Discussing with the Hospital the analytics they wanted to be able to perform and examining the data they had available.
Building a unified model for a knowledge graph that would support the Hospital’s requirements.
Taking several internal datasets in different formats with versatile information about the same several hundred faculty members and converting each dataset to RDF following the created model.
Connecting the people between the records in the different datasets to get a Doctor-360-degree view.
Using focused data from several external datasets to fill out the parts of the knowledge graph that were not available in internal data but were required for the analytics.
Developing and fine-tuning the analytics over the knowledge graph together with the Hospital.
Once the data was fully integrated in the Research Impact Tracking Knowledge Graph, it was easy for the Hospital to:
gain valuable insights into the activities of a faculty by automatically discovering connections;
analyze and calculate indicators of interest (such as geographical distribution of faculty collaboration with external institutions, emerging co-authorship networks, publications resulting from collaboration in clinical trials, comparative rate of increase of scientific output, etc.);
identify trending and emerging areas of research and gain easier access to public or private research grants;
distribute financial support more wisely among top priority scientific areas and specific research topics;
answer new questions that were beyond the scope of the original information by seamlessly adding specific missing data pieces to the knowledge graph;
generate various reports, including intuitive and data-rich interactive visualizations (for example, major co-authorship networks within a slice of the dataset with their different topologies).
Why Choose Ontotext
Thanks to Ontotext’s Research Impact Tracking Knowledge Graph, now the US Children’s Hospital has a much more comprehensive and up-to-date picture of their faculty research activities.
With the help of the new impact metrics analytics, the Hospital can identify trending and emerging areas of research as well as strengthen scientific collaboration with individual researchers and institutions. It can also provide easier access to public or private research grants and distribute the financial support more judiciously among top priority scientific areas and specific research topics.
Do you think this case resembles your particular business needs?