Machine Learning Prediction of Hypoglycemia and Hyperglycemia From Electronic Health Records: Algorithm Development and Validation.
Harald WitteChristos Theodoros NakasLia BallyAlexander Benedikt LeichtlePublished in: JMIR formative research (2022)
Electronic health records have the potential to reliably predict all types of BG decompensation. Readily available patient details and routine laboratory data can support the decisions for proactive interventions and thus help to reduce the detrimental health effects of hypoglycemia and hyperglycemia.
Keyphrases
- electronic health record
- machine learning
- type diabetes
- clinical decision support
- glycemic control
- public health
- healthcare
- artificial intelligence
- deep learning
- adverse drug
- diabetic rats
- big data
- case report
- human health
- mental health
- physical activity
- clinical practice
- health information
- risk assessment
- oxidative stress
- social media
- skeletal muscle
- data analysis