Predictive Risk-Stratification Model

How it works

Evidence quality

Where it comes from

Highlighted claims

• The Trust bought an off-the-shelf predictive no-show model from a US-based supplier because it was convenient. — Mixed-methods evaluation of how a predictive model pilot intervention addresses patient non-attendance at outpatient services in an NHS Foundation Trust in England
• The model was a cloud-based random forest originally developed, trained, and calibrated in the United States. — Mixed-methods evaluation of how a predictive model pilot intervention addresses patient non-attendance at outpatient services in an NHS Foundation Trust in England
• The model used appointment characteristics and history from EHR data to produce a risk score from 0 to 1. — Mixed-methods evaluation of how a predictive model pilot intervention addresses patient non-attendance at outpatient services in an NHS Foundation Trust in England
• The evaluation did not assess the model's prediction accuracy or validity. — Mixed-methods evaluation of how a predictive model pilot intervention addresses patient non-attendance at outpatient services in an NHS Foundation Trust in England
• A single risk score cannot capture the heterogeneous causes of appointment non-attendance. — Mixed-methods evaluation of how a predictive model pilot intervention addresses patient non-attendance at outpatient services in an NHS Foundation Trust in England