Prediction of high-risk emergency department revisits from a machine-learning algorithm: a proof-of-concept study.
Chih-Wei SungJoshua HoCheng-Yi FanChing-Yu ChenChi-Hsin ChenShao-Yung LinJia-How ChangJiun-Wei ChenEdward Pei-Chuan HuangPublished in: BMJ health & care informatics (2024)
The stacked ensemble algorithm exhibited better prediction performance in which the predictions were generated from different ML algorithms to optimally maximise the final set of results. Patients with older age and abnormal systolic blood pressure and heart rate at the index ED visit were vulnerable to high-risk ED revisit. Further studies should be conducted to externally validate the model.
Keyphrases
- machine learning
- heart rate
- emergency department
- blood pressure
- heart rate variability
- deep learning
- hypertensive patients
- artificial intelligence
- big data
- heart failure
- convolutional neural network
- left ventricular
- physical activity
- neural network
- type diabetes
- community dwelling
- blood glucose
- middle aged
- atrial fibrillation
- skeletal muscle
- weight loss