Extraction of Tumor Site from Cancer Pathology Reports using Deep Filters

Abstract

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 highdimensionality 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 potentially 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.

Assigning ICD-O-3 codes to pathology reports using neural multi-task training with hierarchical regularization

“…However, their work is limited to 12 topography codes and four histology grades (e.g., "well differentiated"). Similarly, Dubey et al ( 2019) experiment with deep filters to extract 14 different ICD-O-3 codes [9]. They also explore grade, locality, and behavior classification, but they are still limited to 29 total classes.…”

Research Progress of Tumor Big Data Visualization

“…Gaidano [62] used word cloud maps to show the mutated genes in chronic lymphocytic leukemia, where font size is proportional to molecular lesion frequency. Christian [63] used word clouds to show which words were most associated with cancer in the selection algorithm (Figure 16). This method is suitable for the visualization of all textual information in the field of oncology, such as case information, clinical medical records, drug lists, gene analysis, etc.…”