Hospital mortality prediction in traumatic injuries patients: comparing different SMOTE-based machine learning algorithms.
Roghayyeh HassanzadehMaryam FarhadianHassan RafieemehrPublished in: BMC medical research methodology (2023)
This study has shown that SMOTE-based ML algorithms better predict outcomes in traumatic injuries than ML algorithms. They have the potential to assist ICU physicians in making clinical decisions.
Keyphrases
- machine learning
- deep learning
- spinal cord injury
- artificial intelligence
- big data
- end stage renal disease
- newly diagnosed
- ejection fraction
- healthcare
- peritoneal dialysis
- cardiovascular events
- emergency department
- primary care
- prognostic factors
- risk assessment
- patient reported outcomes
- human health
- risk factors
- climate change
- metabolic syndrome
- skeletal muscle
- glycemic control