Natural language processing for abstraction of cancer treatment toxicities: accuracy versus human experts
| Autor: | Jarred P. Tanksley, Andrew T. Fairchild, Julian C. Hong, Jessica D. Tenenbaum, Manisha Palta |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
AcademicSubjects/SCI01060
Application Notes medicine.medical_treatment Cancer therapy Health Informatics computer.software_genre radiation therapy 03 medical and health sciences 0302 clinical medicine medicine cancer 030212 general & internal medicine natural language processing chemoradiation Abstraction (linguistics) business.industry toxicity Cancer Common Terminology Criteria for Adverse Events medicine.disease Cancer treatment Radiation therapy 030220 oncology & carcinogenesis Patient Safety Artificial intelligence AcademicSubjects/SCI01530 AcademicSubjects/MED00010 business computer Natural language processing |
| Zdroj: | JAMIA Open JAMIA open, vol 3, iss 4 |
| ISSN: | 2574-2531 |
| DOI: | 10.1093/jamiaopen/ooaa064 |
| Popis: | Objectives Expert abstraction of acute toxicities is critical in oncology research but is labor-intensive and variable. We assessed the accuracy of a natural language processing (NLP) pipeline to extract symptoms from clinical notes compared to physicians. Materials and Methods Two independent reviewers identified present and negated National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE) v5.0 symptoms from 100 randomly selected notes for on-treatment visits during radiation therapy with adjudication by a third reviewer. A NLP pipeline based on Apache clinical Text Analysis Knowledge Extraction System was developed and used to extract CTCAE terms. Accuracy was assessed by precision, recall, and F1. Results The NLP pipeline demonstrated high accuracy for common physician-abstracted symptoms, such as radiation dermatitis (F1 0.88), fatigue (0.85), and nausea (0.88). NLP had poor sensitivity for negated symptoms. Conclusion NLP accurately detects a subset of documented present CTCAE symptoms, though is limited for negated symptoms. It may facilitate strategies to more consistently identify toxicities during cancer therapy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|