Toward structuring real-world data: Deep learning for extracting oncology information from clinical text with patient-level supervision.
Publication Title
Patterns (N Y)
Document Type
Article
Publication Date
4-14-2023
Keywords
oregon; portland; chiles; system; genomics; E01.789.625; H02.403.429.515; L01.224.050.375.580; L01.313.500.750.280.199; data mining; medical oncology; natural language processing; neoplasm staging
Abstract
Most detailed patient information in real-world data (RWD) is only consistently available in free-text clinical documents. Manual curation is expensive and time consuming. Developing natural language processing (NLP) methods for structuring RWD is thus essential for scaling real-world evidence generation. We propose leveraging patient-level supervision from medical registries, which are often readily available and capture key patient information, for general RWD applications. We conduct an extensive study on 135,107 patients from the cancer registry of a large integrated delivery network (IDN) comprising healthcare systems in five western US states. Our deep-learning methods attain test area under the receiver operating characteristic curve (AUROC) values of 94%-99% for key tumor attributes and comparable performance on held-out data from separate health systems and states. Ablation results demonstrate the superiority of these advanced deep-learning methods. Error analysis shows that our NLP system sometimes even corrects errors in registrar labels.
Clinical Institute
Cancer
Specialty/Research Institute
Earle A. Chiles Research Institute
DOI
10.1016/j.patter.2023.100726
