Paper

FasTag: automatic text classification of unstructured medical narratives

Rivas, Manuel A, Bustamante, Carlos D, Venkataraman, Guhan R, Ayyar, Sandeep, Arturo Lopez Pineda, Page, Rodney L, Zehnder, Ashley M, Oliver J Bear Don't Walk Iv

2019

Overview

Objective: Unstructured clinical narratives are continuously being recorded as part of delivery of care in electronic health records, and dedicated tagging staff spend considerable effort manually assigning clinical codes for billing purposes; despite these efforts, label availability and accuracy are both suboptimal. Materials and Methods: In this retrospective study, we trained long short-term memory (LSTM) recurrent neural networks (RNNs) on 52,722 human and 89,591 veterinary records. We investigated the accuracy of both separate-domain and combined-domain models and probed model portability. We established relevant baselines by training Decision Trees (DT) and Random Forests (RF), and using MetaMap Lite, a clinical natural language processing tool. Results: We show that the LSTM-RNNs accurately classify veterinary and human text narratives into top-level categories with an average weighted macro F1 score of 0.74 and 0.68 respectively. In the \"neoplasia\" category, the model built with veterinary data has a high accuracy in veterinary data, and moderate accuracy in human data, with F1 scores of 0.91 and 0.70 respectively. Our LSTM method scored slightly higher than that of the DT and RF models. Discussion: The use of LSTM-RNN models represents a scalable structure that could prove useful in cohort identification for comparative oncology studies. Conclusion: Digitization of human and veterinary health information will continue to be a reality, particularly in the form of unstructured narratives. Our approach is a step forward for these two domains to learn from, and inform, one another. Footnotes * This revised version has updated descriptions and focuses on comparative oncology.

• Publisher: Cold Spring Harbor Laboratory Press,Cold Spring Harbor Laboratory
• Subject: Classification / Electronic medical records / Epidemiology / Learning algorithms / Long short-term memory / Medical records / Neural networks / Public health