Comparing Machine Learning and Nurse Predictions for Hospital Admissions in a Multisite Emergency Care System.

ABSTRACT:

Background

Emergency department (ED) crowding strains patient care and drives up costs. Early decisions on the need for patient hospital admissions can allow for better planning and potentially improve throughput and alleviate crowding. We sought to prospectively compare nurse predictions with a machine learning (ML) model for hospital admissions and to evaluate whether adding the nurse prediction to ML outputs enhances predictive performance.

Methods

In this prospective, observational study at six hospitals in a large mixed quarternary/community ED system (annual ED census ~500,000), triage nurses recorded a binary admission prediction for adult patients. These predictions were compared with an ensemble ML model (XGBoost + Bio-Clinical BERT) trained on structured data (demo

SUBMITTER: Nover J 

PROVIDER: S-EPMC12036418 | biostudies-literature | 2025 Apr

REPOSITORIES: biostudies-literature