Automatic Diagnosis Coding of Radiology Reports: A Comparison of Deep Learning and Conventional Classification Methods

Diagnosis autocoding is intended to both improve the productivity of clinical coders and the accuracy of the coding. We investigate the applicability of deep learning at autocoding of radiology reports using International Classification of Diseases (ICD). Deep learning methods are known to require large training data. Our goal is to explore how to use these methods when the training data is sparse, skewed and relatively small, and how their effectiveness compares to conventional methods. We identify optimal parameters for setting up a convolutional neural network for autocoding with comparable results to that of conventional methods.

[1]  Anthony N. Nguyen,et al.  Automatic ICD-10 classification of cancers from free-text death certificates , 2015, Int. J. Medical Informatics.

[2]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[3]  H. Suominen.  Machine Learning to Automate the Assignment of Diagnosis Codes to Free-text Radiology Reports : a Method Description , 2008 .

[4]  Ramakanth Kavuluru,et al.  Convolutional neural networks for biomedical text classification: application in indexing biomedical articles , 2015, BCB.

[5]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[6]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[7]  Yuan Lu,et al.  An empirical evaluation of supervised learning approaches in assigning diagnosis codes to electronic medical records , 2015, Artif. Intell. Medicine.

[8]  K. Luyckx,et al.  Data integration of structured and unstructured sources for assigning clinical codes to patient stays , 2015, J. Am. Medical Informatics Assoc..

[9]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[10]  Frank D. Wood,et al.  Diagnosis code assignment: models and evaluation metrics , 2013, J. Am. Medical Informatics Assoc..

[11]  Ramakanth Kavuluru,et al.  Classification of Helpful Comments on Online Suicide Watch Forums , 2016, BCB.

[12]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[13]  Ming Zhang,et al.  Automatic classification of diseases from free-text death certificates for real-time surveillance , 2015, BMC Medical Informatics and Decision Making.

[14]  Richárd Farkas,et al.  Automatic construction of rule-based ICD-9-CM coding systems , 2008, BMC Bioinformatics.

[15]  K. Bretonnel Cohen,et al.  A shared task involving multi-label classification of clinical free text , 2007, BioNLP@ACL.

[16]  Anthony N. Nguyen,et al.  Assessing the Utility of Automatic Cancer Registry Notifications Data Extraction from Free-Text Pathology Reports , 2015, AMIA.

[17]  Christopher D. Manning,et al.  Baselines and Bigrams: Simple, Good Sentiment and Topic Classification , 2012, ACL.

[18]  Koby Crammer,et al.  Automatic Code Assignment to Medical Text , 2007, BioNLP@ACL.