Back to Search
Start Over
Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival
- Source :
- Frontiers in Oncology, Vol 11 (2021), Frontiers in Oncology
- Publication Year :
- 2021
- Publisher :
- Frontiers Media S.A., 2021.
-
Abstract
- Most electronic medical records, such as free-text radiological reports, are unstructured; however, the methodological approaches to analyzing these accumulating unstructured records are limited. This article proposes a deep-transfer-learning-based natural language processing model that analyzes serial magnetic resonance imaging reports of rectal cancer patients and predicts their overall survival. To evaluate the model, a retrospective cohort study of 4,338 rectal cancer patients was conducted. The experimental results revealed that the proposed model utilizing pre-trained clinical linguistic knowledge could predict the overall survival of patients without any structured information and was superior to the carcinoembryonic antigen in predicting survival. The deep-transfer-learning model using free-text radiological reports can predict the survival of patients with rectal cancer, thereby increasing the utility of unstructured medical big data.
- Subjects :
- Cancer Research
Colorectal cancer
computer.software_genre
Carcinoembryonic antigen
Text messaging
medicine
rectal cancer
survival prediction
RC254-282
Original Research
biology
business.industry
Medical record
Deep learning
deep learning
Neoplasms. Tumors. Oncology. Including cancer and carcinogens
Retrospective cohort study
Patient survival
medicine.disease
Oncology
Radiological weapon
biology.protein
natural language processing (NLP)
Artificial intelligence
business
computer
Natural language processing
MRI
Subjects
Details
- Language :
- English
- Volume :
- 11
- Database :
- OpenAIRE
- Journal :
- Frontiers in Oncology
- Accession number :
- edsair.doi.dedup.....da03c7eb9b775620ee952f8691e4d382
- Full Text :
- https://doi.org/10.3389/fonc.2021.747250/full