Deep-Transfer-Learning-Based Natural Language Processing of Serial Free-Text Computed Tomography Reports for Predicting Survival of Patients With Pancreatic Cancer.
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
{"title":"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","doi":"10.1200/CCI.24.00021","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To explore the predictive potential of serial computed tomography (CT) radiology reports for pancreatic cancer survival using natural language processing (NLP).</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusion: </strong>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.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":null,"pages":null},"PeriodicalIF":3.3000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JCO Clinical Cancer Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1200/CCI.24.00021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
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.