Identifying Patients With Heart Failure Who Are Susceptible to De Novo Acute Kidney Injury: Machine Learning Approach.
Caogen HongZhoujian SunYuzhe HaoZhanghuiya DongZhaodan GuZhengxing HuangPublished in: JMIR medical informatics (2022)
According to a machine learning analysis on electronic health record data, patients with HF who had normal renal function were clustered into separate phenogroups associated with different risk levels of de novo AKI. Our investigation suggests that using machine learning can facilitate patient phengrouping and stratification in clinical settings where the identification of high-risk patients has been challenging.
Keyphrases
- electronic health record
- machine learning
- acute kidney injury
- end stage renal disease
- big data
- ejection fraction
- newly diagnosed
- cardiac surgery
- clinical decision support
- artificial intelligence
- peritoneal dialysis
- adverse drug
- deep learning
- case report
- prognostic factors
- heart failure
- patient reported outcomes
- data analysis
- acute heart failure