Rule-based and machine learning algorithms identify patients with systemic sclerosis accurately in the electronic health record.
Lia JamianLee WhelessLeslie J CroffordApril BarnadoPublished in: Arthritis research & therapy (2019)
Algorithms using only ICD-9 codes did not perform well to identify SSc patients. The highest performing algorithms incorporated clinical data with billing codes. EHR-based algorithms can identify SSc patients across a healthcare system, enabling researchers to examine important outcomes.
Keyphrases
- machine learning
- electronic health record
- systemic sclerosis
- end stage renal disease
- chronic kidney disease
- ejection fraction
- deep learning
- newly diagnosed
- interstitial lung disease
- big data
- prognostic factors
- artificial intelligence
- peritoneal dialysis
- rheumatoid arthritis
- clinical decision support
- skeletal muscle
- adipose tissue