Considerations on the Electronic Health Record–Based Machine Learning Model for Gastrointestinal Bleeding
We read with great interest the recent article by Shung et al,1 which developed and validated an electronic health record (EHR)–based machine learning model. This model outperforms currently recommended clinical risk scores, identifies more very low-risk patients eligible for discharge from the emergency department, and therefore, provides more proper clinical decision support to suggest outpatient management for very low-risk patients and potentially decrease unnecessary hospitalizations and medical costs.
