In 1,245 ambulance resource-constrained situations in Sweden, a machine learning risk score helped dispatchers send the first ambulance to the highest-NEWS2 low-priority patient more often than usual practice (68.3% vs 62.5%; OR 1.28, 95% CI 1.00-1.63).
RCTn = 1,245 resource-constrained situations
Spangler et al. Machine learning assisted differentiation of low acuity patients at dispatch: The MADLAD randomized controlled trial