Skip to main content
SHARE
Publication

Extraction of Tumor Site from Cancer Pathology Reports using Deep Filters...

by Abhishek K Dubey, Jacob D Hinkle, James B Christian, Georgia Tourassi
Publication Type
Conference Paper
Book Title
Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics
Publication Date
Page Numbers
320 to 327
Conference Name
10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB 2019)
Conference Location
Niagra Fall, New York, United States of America
Conference Sponsor
ACM
Conference Date
-

Purpose: Pathology reports are the primary source of information concerning the millions of cancer cases across the United States. % Cancer registries manually process the pathology reports to extract the pertinent information including primary tumor site, behavior, histology, laterality, and grade. % Processing a large volume of the pathology reports in a timely manner is a continuing challenge for cancer registries. % The purpose of this study is to develop an information extraction pipeline to reliably and efficiently extract reportable information.\\ Method: % We have developed a novel inverse-regression (IR) based information extraction pipeline. % The inverse-regression based supervised filter has been successfully applied to many application domains. % However, its application to the information extraction from unstructured text is hindered primarily by the extreme high-dimensionality of n-gram representations of text. % In this study, we attempt to overcome the obstacles by a novel bootstrapping strategy. % First, we use an information-theoretic mutual information based filter to discard the excessive and redundant n-gram features. % This step reduces the size and improves the condition number of the sample covariance matrix, thus reducing the computational cost and improving the numerical stability of the subsequent inverse-regression step. % Then we use localized sliced inverse-regression (LSIR) to learn a low-dimensional discriminatory subspace for information inference. % In particular, we use the k-nearest neighbors of an unlabeled pathology report in the learned representation to infer the desired information from the labeled data in a supervised manner. % \\ % Results: The experiments were conducted on a set of de-identified pathology reports with human expert labels as the ground truth. % Our pipeline consistently performed better than or comparable to the best performing state-of-the-art methods while reducing the training and inference times substantially.\\ Conclusion: Our results demonstrate the potential of \emergencystretch 3em inverse-regression based information extraction pipeline for reliable and efficient information extraction from unstructured text. % The information extracted from the pathology reports can be used along with clinical information, medical imaging, and genomic information to instigate discoveries in cancer research.