Literature DB >> 32335686

Comparison of deep learning models for natural language processing-based classification of non-English head CT reports.

Yiftach Barash1,2, Gennadiy Guralnik3, Noam Tau1, Shelly Soffer1,2,4, Tal Levy2,3, Orit Shimon3, Eyal Zimlichman4, Eli Konen1, Eyal Klang5,6.   

Abstract

PURPOSE: Natural language processing (NLP) can be used for automatic flagging of radiology reports. We assessed deep learning models for classifying non-English head CT reports.
METHODS: We retrospectively collected head CT reports (2011-2018). Reports were signed in Hebrew. Emergency department (ED) reports of adult patients from January to February for each year (2013-2018) were manually labeled. All other reports were used to pre-train an embedding layer. We explored two use cases: (1) general labeling use case, in which reports were labeled as normal vs. pathological; (2) specific labeling use case, in which reports were labeled as with and without intra-cranial hemorrhage. We tested long short-term memory (LSTM) and LSTM-attention (LSTM-ATN) networks for classifying reports. We also evaluated the improvement of adding Word2Vec word embedding. Deep learning models were compared with a bag-of-words (BOW) model.
RESULTS: We retrieved 176,988 head CT reports for pre-training. We manually labeled 7784 reports as normal (46.3%) or pathological (53.7%), and 7.1% with intra-cranial hemorrhage. For the general labeling, LSTM-ATN-Word2Vec showed the best results (AUC = 0.967 ± 0.006, accuracy 90.8% ± 0.01). For the specific labeling, all methods showed similar accuracies between 95.0 and 95.9%. Both LSTM-ATN-Word2Vec and BOW had the highest AUC (0.970).
CONCLUSION: For a general use case, word embedding using a large cohort of non-English head CT reports and ATN improves NLP performance. For a more specific task, BOW and deep learning showed similar results. Models should be explored and tailored to the NLP task.

Entities:  

Keywords:  Attention; Deep learning; Emergency service, hospital; Natural language processing; Tomography, X-ray computed

Mesh:

Year:  2020        PMID: 32335686     DOI: 10.1007/s00234-020-02420-0

Source DB:  PubMed          Journal:  Neuroradiology        ISSN: 0028-3940            Impact factor:   2.804


  4 in total

1.  Labeling Noncontrast Head CT Reports for Common Findings Using Natural Language Processing.

Authors:  M Iorga; M Drakopoulos; A M Naidech; A K Katsaggelos; T B Parrish; V B Hill
Journal:  AJNR Am J Neuroradiol       Date:  2022-04-28       Impact factor: 3.825

2.  Deep Learning-Based Natural Language Processing in Radiology: The Impact of Report Complexity, Disease Prevalence, Dataset Size, and Algorithm Type on Model Performance.

Authors:  A W Olthof; P M A van Ooijen; L J Cornelissen
Journal:  J Med Syst       Date:  2021-09-04       Impact factor: 4.460

3.  Machine learning to predict in-hospital mortality among patients with severe obesity: Proof of concept study.

Authors:  Shelly Soffer; Eyal Zimlichman; Matthew A Levin; Alexis M Zebrowski; Benjamin S Glicksberg; Robert Freeman; David L Reich; Eyal Klang
Journal:  Obes Sci Pract       Date:  2022-03-24

4.  Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection.

Authors:  Meenu Gupta; Hao Wu; Simrann Arora; Akash Gupta; Gopal Chaudhary; Qiaozhi Hua
Journal:  J Healthc Eng       Date:  2021-07-27       Impact factor: 2.682

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.