Cited 0 times in

Deep-Transfer-Learning-Based Natural Language Processing of Serial Free-Text Computed Tomography Reports for Predicting Survival of Patients With Pancreatic Cancer

Authors
 Sunkyu Kim  ;  Seung-Seob Kim  ;  Eejung Kim  ;  Michael Cecchini  ;  Mi-Suk Park  ;  Ji A Choi  ;  Sung Hyun Kim  ;  Ho Kyoung Hwang  ;  Chang Moo Kang  ;  Hye Jin Choi  ;  Sang Joon Shin  ;  Jaewoo Kang  ;  Choong-Kun Lee 
Citation
 JCO CLINICAL CANCER INFORMATICS, Vol.8 : e2400021, 2024-08 
Journal Title
JCO CLINICAL CANCER INFORMATICS
Issue Date
2024-08
MeSH
Aged ; Deep Learning* ; Female ; Humans ; Male ; Middle Aged ; Natural Language Processing* ; Pancreatic Neoplasms* / diagnostic imaging ; Pancreatic Neoplasms* / mortality ; Prognosis ; ROC Curve ; Retrospective Studies ; Tomography, X-Ray Computed* / methods
Abstract
Purpose: To explore the predictive potential of serial computed tomography (CT) radiology reports for pancreatic cancer survival using natural language processing (NLP).

Methods: Deep-transfer-learning-based NLP models were retrospectively trained and tested with serial, free-text CT reports, and survival information of consecutive patients diagnosed with pancreatic cancer in a Korean tertiary hospital was extracted. Randomly selected patients with pancreatic cancer and their serial CT reports from an independent tertiary hospital in the United States were included in the external testing data set. The concordance index (c-index) of predicted survival and actual survival, and area under the receiver operating characteristic curve (AUROC) for predicting 1-year survival were calculated.

Results: Between January 2004 and June 2021, 2,677 patients with 12,255 CT reports and 670 patients with 3,058 CT reports were allocated to training and internal testing data sets, respectively. ClinicalBERT (Bidirectional Encoder Representations from Transformers) model trained on the single, first CT reports showed a c-index of 0.653 and AUROC of 0.722 in predicting the overall survival of patients with pancreatic cancer. ClinicalBERT trained on up to 15 consecutive reports from the initial report showed an improved c-index of 0.811 and AUROC of 0.911. On the external testing set with 273 patients with 1,947 CT reports, the AUROC was 0.888, indicating the generalizability of our model. Further analyses showed our model's contextual interpretation beyond specific phrases.

Conclusion: Deep-transfer-learning-based NLP model of serial CT reports can predict the survival of patients with pancreatic cancer. Clinical decisions can be supported by the developed model, with survival information extracted solely from serial radiology reports.
Full Text
https://ascopubs.org/doi/10.1200/CCI.24.00021
DOI
10.1200/cci.24.00021
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Surgery (외과학교실) > 1. Journal Papers
Yonsei Authors
Kang, Chang Moo(강창무) ORCID logo https://orcid.org/0000-0002-5382-4658
Kim, Sung Hyun(김성현) ORCID logo https://orcid.org/0000-0001-7683-9687
Kim, Seung-seob(김승섭) ORCID logo https://orcid.org/0000-0001-6071-306X
Park, Mi-Suk(박미숙) ORCID logo https://orcid.org/0000-0001-5817-2444
Shin, Sang Joon(신상준) ORCID logo https://orcid.org/0000-0001-5350-7241
Lee, Choong-kun(이충근) ORCID logo https://orcid.org/0000-0001-5151-5096
Choi, Hye Jin(최혜진) ORCID logo https://orcid.org/0000-0001-5917-1400
Hwang, Ho Kyoung(황호경) ORCID logo https://orcid.org/0000-0003-4064-7776
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/200506
사서에게 알리기
  feedback

qrcode

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

Browse

Links