Automatic Extraction of Breast Cancer Information from Clinical Reports

The majority of clinical data is only available in unstructured text documents. Thus, their automated usage in data-based clinical application scenarios, like quality assurance and clinical decision support by treatment suggestions, is hindered because it requires high manual annotation efforts. In this work, we introduce a system for the automated processing of clinical reports of mamma carcinoma patients that allows for the automatic extraction and seamless processing of relevant textual features. Its underlying information extraction pipeline employs a rule-based grammar approach that is integrated with semantic technologies to determine the relevant information from the patient record. The accuracy of the system, developed with nine thousand clinical documents, reaches accuracy levels of 90% for lymph node status and 69% for the structurally most complex feature, the hormone status.

I. Introduction

In order to make use of the wealth of unstructured text data captured in electronic health records (EHR) in clinical data intelligence applications, its semantic annotation is required. The automatic detection of medial information extraction (IE) classes is crucial for integrated decision support. Currently, enormous manual effort is put in the acquisition of the structured data needed for clinical data intelligence or as input for quality assurance processes. In order to automate this step, we introduce a semantically enhanced IE pipeline that allows us to extract relevant information from EHRs of mamma carcinoma patients. We extract six medical IE classes, i.e., type of operation conducted, tumour size, grading of tumour, lymph node status, hormone receptor state, HER2 state, and lymphatic spread. These IE classes, together with the age of treated patient in structured format, are considered to be the main influencing indicators for the therapeutic measure to choose.