Automatically extracting cancer disease characteristics from pathology reports into a Disease Knowledge Representation Model

Abstract

We introduce an extensible and modifiable knowledge representation model to represent cancer disease characteristics in a comparable and consistent fashion. We describe a system, MedTAS/P which automatically instantiates the knowledge representation model from free-text pathology reports. MedTAS/P is based on an open-source framework and its components use natural language processing principles, machine learning and rules to discover and populate elements of the model. To validate the model and measure the accuracy of MedTAS/P, we developed a gold-standard corpus of manually annotated colon cancer pathology reports. MedTAS/P achieves F1-scores of 0.97-1.0 for instantiating classes in the knowledge representation model such as histologies or anatomical sites, and F1-scores of 0.82-0.93 for primary tumors or lymph nodes, which require the extractions of relations. An F1-score of 0.65 is reported for metastatic tumors, a lower score predominantly due to a very small number of instances in the training and test sets.

Pattern-based information extraction from pathology reports for cancer registration

“…We found that over 90% recall and precision are achievable in the extraction of staging term-value(s) data, even when pathologists use several different ways of representing them. This compares very well with even much more complex techniques [17,18]. In the case studied, the completeness of cancer staging was increased by up to a third.…”

Creating a rule based system for text mining of Norwegian breast cancer pathology reports

“…Rule based systems and machine learning systems are both used, and in some cases in combination. Coden et al (2009) built a model called Cancer Disease Knowledge Representation Model, which has nine classes including anatomical site, histology, and metastatic tumor. Evaluation found that recall was between 76% and 100% and precision was between 72% and 100% for all classes except metastatic tumor where both precision and recall were lower.…”

Efficient Encoding of Pathology Reports Using Natural Language Processing

“…For a review of the research area, see Spasić et al (2014). Coden et al (2009) extracted information from pathology reports for colon cancer. A combination of rules and machine learning were used to extract nine different classes from the reports.…”