Natural Language Processing of Radiology Reports to Detect Complications of Ischemic Stroke.
Matthew I MillerAgni OrfanoudakiMichael CroninHanife SaglamIvy So Yeon KimOluwafemi BalogunMaria TzalidiKyriakos VasilopoulosGeorgia FanaropoulouNina M FanaropoulouJack KalinMeghan HutchBrenton R PrescottBenjamin BrushEmelia J BenjaminMin ShinAsim MianDavid M GreerStelios M SmirnakisCharlene J OngPublished in: Neurocritical care (2022)
Our study demonstrates robust performance and external validity of a core NLP tool kit for identifying both categorical and continuous outcomes of ischemic stroke from unstructured radiographic text data. Medically tailored NLP methods have multiple important big data applications, including scalable electronic phenotyping, augmentation of clinical risk prediction models, and facilitation of automatic alert systems in the hospital setting.
Keyphrases
- big data
- artificial intelligence
- machine learning
- deep learning
- atrial fibrillation
- smoking cessation
- adverse drug
- healthcare
- autism spectrum disorder
- high throughput
- risk factors
- emergency department
- type diabetes
- electronic health record
- metabolic syndrome
- adipose tissue
- skeletal muscle
- single cell
- glycemic control