Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing.
Mohit PandeyZhuoran XuEvan T SholleGabriel MaliakalGurpreet SinghLohendran BaskaranDaria LarineBenjamin C LeeJing WangAlexander R van RosendaelLohendran BaskaranLeslee J ShawJames K MinSubhi J Al'ArefPublished in: PloS one (2020)
An ML-based NLP approach to unstructured CT reports demonstrates excellent accuracy for the extraction of predetermined radiographic findings, and provides prognostic value in HF patients.
Keyphrases
- computed tomography
- convolutional neural network
- end stage renal disease
- newly diagnosed
- ejection fraction
- dual energy
- positron emission tomography
- image quality
- deep learning
- contrast enhanced
- magnetic resonance imaging
- peritoneal dialysis
- emergency department
- adverse drug
- machine learning
- magnetic resonance
- atrial fibrillation