Recording – Mining Electronic Health Records for Insights

Electronic Health Records (EHR) are the primary source of information for providing insights into the diagnoses and outcome of clinical treatments. Retrieving useful analytical information from these records is challenging though. The complex nature of clinical text can result in much of the information extracted being of limited value. Natural Language Processing (NLP) techniques, however, can process large volumes of clinical text while automatically encoding clinical information in a structured form.

Many of today’s solutions utilize ontology based information extraction. This approach alone does not taking into consideration context or additional aspects such as negation, temporality, and experiencer. As a result, the information extracted from EHRs (signs & symptoms, diagnoses, and treatments) is not as meaningful as it could be.
When done properly, Information Extraction techniques applied to aggregate patient and clinical data can reveal more effective operational analytics as well as open up new opportunities for clinical research.
This webinar will highlight some of the challenges in text mining clinical patient data and the solutions which Ontotext provides to overcome them, including:

  • Ontology-based Information Extraction
  • Application of flexible gazetteers
  • Negations detection
  • Temporality identification
  • Discovery of post-coordination patterns
  • Generation of Linked Data

Finally, you will see a demonstration of the power of fusing semantic annotations with clinical data and how it is used to improve information retrieval from clinical documents.

todor_primov

Todor Primov leads Ontotext’s Life Sciences and Healthcare Semantic Applications Group. His background in Molecular Biology and Bioinformatics & Health Informatics gives him a deep understanding of the domain. For the last 15 years, Todor has been utilizing Semantic Mapping and Information Extraction approaches to develop knowledge discovery systems.

Back to top