Recurrent Neural Networks for Early Detection of Heart Failure From Longitudinal Electronic Health Record Data: Implications for Temporal Modeling With Respect to Time Before Diagnosis, Data Density, Data Quantity, and Data Type.

Journal: Circulation. Cardiovascular quality and outcomes

PMID: 31610714

Abstract

BACKGROUND: We determined the impact of data volume and diversity and training conditions on recurrent neural network methods compared with traditional machine learning methods.

Authors

Robert Chen

Research, Sutter Health Research, Walnut Creek, CA (R.C., X.Y.).
Walter F Stewart

Research Development & Dissemination Sutter Health Walnut Creek, CA, USA.
Jimeng Sun

College of Computing Georgia Institute of Technology Atlanta, GA, USA.
Kenney Ng

Center for Computational Health, IBM Research, Yorktown Heights, NY, USA.
Xiaowei Yan

Research, Sutter Health Research, Walnut Creek, CA (R.C., X.Y.).

Keywords

Alcohol Drinking California Diagnosis, Computer-Assisted Early Diagnosis Electronic Health Records Female Heart Failure Humans Incidence Longitudinal Studies Machine Learning Male Neural Networks, Computer Predictive Value of Tests Primary Health Care Reproducibility of Results Risk Factors Smoking Time Factors Vital Signs

External Resources

View on PubMed Access via DOI PubMed (31610714)

Recurrent Neural Networks for Early Detection of Heart Failure From Longitudinal Electronic Health Record Data: Implications for Temporal Modeling With Respect to Time Before Diagnosis, Data Density, Data Quantity, and Data Type.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals