Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances en e-Santé


Logo Tremplin Carnot
Logo UPMC Logo université Paris 13


Image décorative

Bulding a semanthic helath Data Warehouse: Evaluation in Clinical trials criteria

Romain Lelong

Le 25/03/2019 de 09:45 à 10:10

Description :

Background: The huge amount of clinical, administrative and demographic data recorded and maintained by hospitals can be consistently aggregated into Health DataWarehouses (HDWs) with a uniform data model.
In 2017, Rouen University Hospital (RUH) initiated the design of a Semantic Health Data Warehouse(SHDW) enabling both semantic description and retrieval of health information. Our objectives were:

First, to present a proof of concept of this SHDW, based on the data of 250,000 patients from RUH and second, to assess its ability to assist health professionals to select patient in a clinical trial context.

Methods: The SHDWrelies on three distinct semantic layers: (a) a Terminology and Ontology (T&O) portal, (b) a Semantic Annotator and (c) a Semantic Search Engine and a Not Only SQL (NoSQL) layer to enhance data access performances. The system adopts an entity-centered vision which contrasts with the usually patient-centered vision adopted by existing systems such as Informatics for Integrating Biology and the Bedside (i2b2). This vision notably provides generic search capabilities able to express data requirements in terms of the whole set of interconnected conceptual entities that compose the health information. We assessed the ability of the system to assist the search for 95 inclusion and exclusion criteria originating from _ve randomly chosen Clinical Trials from RUH.

Results: The system succeeded in fully automating 39:19% of the criteria and was recently used as a prescreening tool for 72:97% of them.

Conclusion: The semantic aspect of the system combined with its generic entity-centered vision enables the processing of a large range of clinical questions. However, an important part of the health information remains in Clinical Narratives and our department is currently investigating novel approaches (deep learning) to enhance the semantic annotation of those unstructured data.

Traitement en cours ...