Deep learning architectures for vector representations of patients and exploring predictors of 30-day hospital readmissions in patients with multiple chronic conditions.
Muhammad RafiqGeorge KeelPamela MazzocatoJonas SpaakCarl SavageChristian GuttmannPublished in: AIH@IJCAI (2018)
Keyphrases
- deep learning
- heart failure
- high risk
- health care
- emergency department
- medical doctors
- medical practice
- chronic disease
- patient groups
- vital signs
- patient records
- unsupervised feature learning
- clinical data
- intensive care unit
- hospital information systems
- deep belief networks
- unsupervised learning
- normal subjects
- computer vision
- machine learning
- cardiovascular disease
- mental models
- domain specific