Machine learning for prediction of intra-abdominal abscesses in patients with Crohn's disease visiting the emergency department.
Asaf LevartovskyYiftach BarashShomron Ben-HorinBella UngarShelly SofferMarianne M AmitaiEyal KlangUri KopylovPublished in: Therapeutic advances in gastroenterology (2021)
In our large tertiary center cohort, the machine learning model identified the association of six clinical features (CRP, hemoglobin, WBC, age, BUN, and biologic therapy) with the presentation of an IA. These may assist as a decision support tool in triaging CD patients for imaging to exclude this potentially life-threatening complication.
Keyphrases
- machine learning
- emergency department
- end stage renal disease
- ejection fraction
- chronic kidney disease
- newly diagnosed
- artificial intelligence
- rheumatoid arthritis
- high resolution
- peritoneal dialysis
- prognostic factors
- big data
- deep learning
- patient reported outcomes
- adverse drug
- mass spectrometry
- drug induced
- nk cells
- replacement therapy