0 137

Cited 3 times in

Natural language processing to predict isocitrate dehydrogenase genotype in diffuse glioma using MR radiology reports

Authors
 Minjae Kim  ;  Kai Tzu-Iunn Ong  ;  Seonah Choi  ;  Jinyoung Yeo  ;  Sooyon Kim  ;  Kyunghwa Han  ;  Ji Eun Park  ;  Ho Sung Kim  ;  Yoon Seong Choi  ;  Sung Soo Ahn  ;  Jinna Kim  ;  Seung-Koo Lee  ;  Beomseok Sohn 
Citation
 EUROPEAN RADIOLOGY, Vol.33(11) : 8017-8025, 2023-11 
Journal Title
EUROPEAN RADIOLOGY
ISSN
 0938-7994 
Issue Date
2023-11
MeSH
Brain Neoplasms* / diagnostic imaging ; Brain Neoplasms* / genetics ; Brain Neoplasms* / pathology ; Genotype ; Glioma* / diagnostic imaging ; Glioma* / genetics ; Glioma* / pathology ; Humans ; Isocitrate Dehydrogenase / genetics ; Magnetic Resonance Imaging ; Male ; Natural Language Processing ; Neoplasm Grading ; Retrospective Studies
Keywords
Glioma ; Isocitrate dehydrogenase ; Natural language processing
Abstract
ObjectivesTo evaluate the performance of natural language processing (NLP) models to predict isocitrate dehydrogenase (IDH) mutation status in diffuse glioma using routine MR radiology reports.Materials and methodsThis retrospective, multi-center study included consecutive patients with diffuse glioma with known IDH mutation status from May 2009 to November 2021 whose initial MR radiology report was available prior to pathologic diagnosis. Five NLP models (long short-term memory [LSTM], bidirectional LSTM, bidirectional encoder representations from transformers [BERT], BERT graph convolutional network [GCN], BioBERT) were trained, and area under the receiver operating characteristic curve (AUC) was assessed to validate prediction of IDH mutation status in the internal and external validation sets. The performance of the best performing NLP model was compared with that of the human readers.ResultsA total of 1427 patients (mean age +/- standard deviation, 54 +/- 15; 779 men, 54.6%) with 720 patients in the training set, 180 patients in the internal validation set, and 527 patients in the external validation set were included. In the external validation set, BERT GCN showed the highest performance (AUC 0.85, 95% CI 0.81-0.89) in predicting IDH mutation status, which was higher than LSTM (AUC 0.77, 95% CI 0.72-0.81; p = .003) and BioBERT (AUC 0.81, 95% CI 0.76-0.85; p = .03). This was higher than that of a neuroradiologist (AUC 0.80, 95% CI 0.76-0.84; p = .005) and a neurosurgeon (AUC 0.79, 95% CI 0.76-0.84; p = .04).ConclusionBERT GCN was externally validated to predict IDH mutation status in patients with diffuse glioma using routine MR radiology reports with superior or at least comparable performance to human reader.Clinical relevance statementNatural language processing may be used to extract relevant information from routine radiology reports to predict cancer genotype and provide prognostic information that may aid in guiding treatment strategy and enabling personalized medicine.Key Points center dot A transformer-based natural language processing (NLP) model predicted isocitrate dehydrogenase mutation status in diffuse glioma with an AUC of 0.85 in the external validation set.center dot The best NLP models were superior or at least comparable to human readers in both internal and external validation sets.center dot Transformer-based models showed higher performance than conventional NLP model such as long short-term memory.Key Points center dot A transformer-based natural language processing (NLP) model predicted isocitrate dehydrogenase mutation status in diffuse glioma with an AUC of 0.85 in the external validation set.center dot The best NLP models were superior or at least comparable to human readers in both internal and external validation sets.center dot Transformer-based models showed higher performance than conventional NLP model such as long short-term memory.Key Points center dot A transformer-based natural language processing (NLP) model predicted isocitrate dehydrogenase mutation status in diffuse glioma with an AUC of 0.85 in the external validation set.center dot The best NLP models were superior or at least comparable to human readers in both internal and external validation sets.center dot Transformer-based models showed higher performance than conventional NLP model such as long short-term memory.
Full Text
https://link.springer.com/article/10.1007/s00330-023-10061-z
DOI
10.1007/s00330-023-10061-z
Appears in Collections:
1. College of Medicine (의과대학) > Research Institute (부설연구소) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers
Yonsei Authors
Kim, Min Jae(김민재)
Kim, Jinna(김진아) ORCID logo https://orcid.org/0000-0002-9978-4356
Sohn, Beomseok(손범석) ORCID logo https://orcid.org/0000-0002-6765-8056
Ahn, Sung Soo(안성수) ORCID logo https://orcid.org/0000-0002-0503-5558
Lee, Seung Koo(이승구) ORCID logo https://orcid.org/0000-0001-5646-4072
Choi, Seonah(최선아)
Choi, Yoon Seong(최윤성)
Han, Kyung Hwa(한경화)
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/197963
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links