Cross-hospital portability of information extraction of cancer staging information

Abstract

Objective: We address the task of extracting information from free-text pathology reports, focusing on staging information encoded by the TNM (tumour-node-metastases) and ACPS (Australian clinico-pathological stage) systems. Staging information is critical for diagnosing the extent of cancer in a patient and for planning individualised treatment. Extracting such information into more structured form saves time, improves reporting, and underpins the potential for automated decision support.

Methods and material: We investigate the portability of a text mining model constructed from records from one health centre, by applying it directly to the extraction task over a set of records from a different health centre, with different reporting narrative characteristics. Other than a simple normalisation step on features associated with target labels, we apply the models from one system directly to the other.

Results: The best F-scores for in-hospital experiments are 81%, 85%, and 94% (for staging T, N, and M respectively), while best cross-hospital F-scores reach 84%, 81%, and 91% for the same respective categories.

Conclusions: Our performance results compare favourably to the best levels reported in the literature, and--most relevant to our aim here--the cross-corpus results demonstrate the portability of the models we developed.

Keywords: Cancer staging detection; Colorectal cancer; Information extraction; Machine learning; Text mining.