Related Experiment Video
Updated: Nov 2, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Validation of a Belgian Prediction Model for Patient Encounters at Belgium's Largest Public Cultural Mass Gathering
Kris Spaepen1, Geert Arno2, Leonard Kaufman1
1Research Group on Emergency and Disaster Medicine, Vrije Universiteit Brussels, Belgium.
Objective:
To compare actual patient presentation rates from Belgium's largest public open-air cultural festival with predictions provided by existing models and the Belgian Plan Risk Manifestations model.
Methods:
Retrospectively, actual patient presentation rates gathered from the Ghent Festivities (Belgium) during 2013-2019 were compared to predicted patient presentation rates by the Arbon, Hartman, and PRIMA models.
Results:
During 7 editions, 8673000 people visited the Ghent Festivities; 9146 sought medical assistance resulting in a mean patient presentation rate (PPR) of 1.05. The PRIMA model overestimated the number of patient encounters for each occasion. The other models had a high rate of underprediction. When comparing deviations in predictions between the PRIMA model to the other models, there is a significant difference in the mean deviation (Arbon: T = 0.000, P < 0.0001, r = -0.8701; Hartman: T = 0.000, P < 0.0001, r = -0.869).
Conclusion:
Despite the differences between the predictions of all 3 models, our results suggest that the PRIMA model is a valid tool to predict patient presentations to IEHS during public cultural MG. However, to substantiate the PRIMA model even further, more research is needed to further validate the model for a broad range of MG.
