A Machine Learning Approach to Support Urgent Stroke Triage Using Administrative Data and Social Determinants of Health at Hospital Presentation: Retrospective Study.
Min ChenXuan TanRema PadmanPublished in: Journal of medical Internet research (2023)
Using data widely available at the time of patients' hospital presentations, we developed a stroke prediction model with high sensitivity and reasonable specificity. The prediction algorithm uses variables that are routinely collected by providers and payers and might be useful in underresourced hospitals with limited availability of sensitive diagnostic tools or incomplete data-gathering capabilities.
Keyphrases
- machine learning
- healthcare
- big data
- electronic health record
- end stage renal disease
- atrial fibrillation
- ejection fraction
- emergency department
- chronic kidney disease
- newly diagnosed
- artificial intelligence
- deep learning
- adverse drug
- prognostic factors
- data analysis
- risk assessment
- case report
- health information
- cerebral ischemia
- health promotion
- human health