Developing machine learning models to personalize care levels among emergency room patients for hospital admission.
Minh NguyenConor K CorbinTiffany EulalioNicolai P OstbergGautam MachirajuBen J MarafinoMichael BaiocchiChristian C RoseJonathan H ChenPublished in: Journal of the American Medical Informatics Association : JAMIA (2021)
Undertriaging admitted ED patients who subsequently require ICU care is common and associated with poorer outcomes. Machine learning models using readily available electronic health record data predict subsequent need for ICU admission with good discrimination, substantially better than the benchmarking ESI system. The results could be used in a multitiered clinical decision-support system to improve ED triage.
Keyphrases
- electronic health record
- emergency department
- clinical decision support
- machine learning
- healthcare
- adverse drug
- intensive care unit
- palliative care
- end stage renal disease
- newly diagnosed
- big data
- ejection fraction
- artificial intelligence
- quality improvement
- ms ms
- mechanical ventilation
- prognostic factors
- peritoneal dialysis
- public health
- insulin resistance
- deep learning
- adipose tissue
- skeletal muscle
- weight loss
- health insurance
- glycemic control