Ko-Jiunn Liu


2020

pdf bib
Cancer Registry Information Extraction via Transfer Learning
Yan-Jie Lin | Hong-Jie Dai | You-Chen Zhang | Chung-Yang Wu | Yu-Cheng Chang | Pin-Jou Lu | Chih-Jen Huang | Yu-Tsang Wang | Hui-Min Hsieh | Kun-San Chao | Tsang-Wu Liu | I-Shou Chang | Yi-Hsin Connie Yang | Ti-Hao Wang | Ko-Jiunn Liu | Li-Tzong Chen | Sheau-Fang Yang
Proceedings of the 3rd Clinical Natural Language Processing Workshop

A cancer registry is a critical and massive database for which various types of domain knowledge are needed and whose maintenance requires labor-intensive data curation. In order to facilitate the curation process for building a high-quality and integrated cancer registry database, we compiled a cross-hospital corpus and applied neural network methods to develop a natural language processing system for extracting cancer registry variables buried in unstructured pathology reports. The performance of the developed networks was compared with various baselines using standard micro-precision, recall and F-measure. Furthermore, we conducted experiments to study the feasibility of applying transfer learning to rapidly develop a well-performing system for processing reports from different sources that might be presented in different writing styles and formats. The results demonstrate that the transfer learning method enables us to develop a satisfactory system for a new hospital with only a few annotations and suggest more opportunities to reduce the burden of cancer registry curation.