Investigating Cross-Institutional Recognition of Cancer Registration Items: A Case Study on Catastrophic Forgetting

ROCLING 2023 Submission ***. Confidential review Copy. DO NOT DISTRIBUTE. 000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 Abstract A cancer registry is a critical database for cancer research, which require diverse domain knowledge and manual extraction of vital information from patient records for surveillance. In order to building a real-time and high-quality cancer registry database, a named entity recognition (NER) model based on bidirectional long short-term memory (BiLSTM)-conditional random fields (CRFs) to automatically extract 14 cancer registry items from unstructured pathology reports was developed for five hospitals. Because not all hospitals have sufficient training data, so that we apply transfer learning to develop our models for different hospitals. However, catastrophic forgetting leads to poor performance of the transferred model on the source hospital. To address this issue, we study the effectiveness of applying the elastic weight consolidation (EWC) method for the extraction of cancer registry items from the unstructured pathology reports of colorectal cancer to mitigate the occurrence of catastrophic forgetting. In our results, we observe that effective parameter settings can reduce the impact of catastrophic forgetting. Keywords: Electronic Medical Records, Natural Language Processing, Transfer Learning, Elastic Weight Consolidation 1 Introduction Electronic medical records (EMR) contain large amounts of data collected during routine medical care delivery and have the potential to generate practice-based evidence, such as early diagnosis of cancer patients and improved quality of care. Cancer is one of the main causes of mortality worldwide, and it is the leading cause of death in Taiwan, and the overall incidence rate has gradually increased (Kuo et al., 2020). In recent years, domestic cancer research has continued to increase, promoting cooperation and resource integration among cancer centers to accelerate breakthroughs in cancer research bottlenecks. The Taiwan Cancer Registry (TCR), which provide a comprehensive measurement of cancer incidence, morbidity, survival, and mortality for persons with cancer in Taiwan. Unfortunately, the process of reporting cancer cases requires manual review of numerous reports, such as radiology reports and pathology reports, which is obviously labor- intensive and time-consuming. One solution to this problem currently being explored is the application of Natural Language Processing (NLP) techniques to automatically read and extract information from cancer reports. In the field of machine learning, the quantity of the dataset has a significant impact on the performance and generalization ability of algorithms. Transfer learning has been proven to be an effective learning method to solve the problem of dataset scarcity (Hutchinson et al., 2017). It uses the …

Content truncated to 500 words