A Deep Learning Approach for Automated Extraction of Functional Status and New York Heart Association Class for Heart Failure Patients During Clinical Encounters.
Philip AdejumoPhyllis ThangarajLovedeep Singh DhingraArya AminorroayaXinyu ZhouCynthia A BrandtHua XuHarlan M KrumholzRohan KheraPublished in: medRxiv : the preprint server for health sciences (2024)
We developed and validated an NLP approach to extract NYHA classification and activity-related HF symptoms from clinical notes, enhancing the ability to track optimal care and identify trial-eligible patients.
Keyphrases
- deep learning
- ejection fraction
- machine learning
- end stage renal disease
- healthcare
- newly diagnosed
- artificial intelligence
- palliative care
- clinical trial
- prognostic factors
- oxidative stress
- convolutional neural network
- heart failure
- high throughput
- quality improvement
- randomized controlled trial
- phase ii
- physical activity
- patient reported outcomes
- pain management
- health insurance
- single cell