Use of Natural Language Processing to Infer Sites of Metastatic Disease From Radiology Reports at Scale.
See Boon TayGuat Hwa LowGillian Jing En WongHan Jieh TeyFun Loon LeongConstance H LiMatthew Chin Heng ChuaDaniel Shao-Weng TanChoon Hua ThngIain Bee Huat TanRyan Shea Ying Cong TanPublished in: JCO clinical cancer informatics (2024)
We developed an IE system that accurately infers metastatic sites in multiple primary cancers from radiology reports. It has explainable methods and performs better than some clinical LLMs. The inferred metastatic phenotypes could enhance cancer research databases and clinical trial matching, and identify potential patients for oligometastatic interventions.
Keyphrases
- squamous cell carcinoma
- small cell lung cancer
- clinical trial
- end stage renal disease
- artificial intelligence
- ejection fraction
- newly diagnosed
- chronic kidney disease
- physical activity
- papillary thyroid
- prognostic factors
- autism spectrum disorder
- adverse drug
- emergency department
- machine learning
- peritoneal dialysis
- big data
- phase ii
- open label
- randomized controlled trial
- double blind
- squamous cell
- childhood cancer
- risk assessment
- human health