Extracting clinical knowledge from electronic medical records

Abstract

As the adoption of Electronic Medical Records (EMRs) rises in the healthcare institutions, these resources' importance increases because of the clinical information they contain about patients. However, the unstructured information in the form of clinical narratives present in those records, makes it hard to extract and structure useful clinical knowledge. This unstructured information limits the potential of the EMRs, because the clinical information these records contain can be used to perform important tasks inside healthcare institutions such as searching, summarization, decision support and statistical analysis, as well as be used to support management decisions or serve for research. These tasks can only be done if the unstructured clinical information from the narratives is properly extracted, structured and transformed in clinical knowledge. Usually, this extraction is made manually by healthcare practitioners, which is not efficient and is error-prone. This research uses Natural Language Processing (NLP) and Information Extraction (IE) techniques, in order to develop a pipeline system that can extract clinical knowledge from unstructured clinical information present in Portuguese EMRs, in an automated way, in order to help EMRs to fulfil their potential.