WG/GLIMPRINT Seminars: Gerlee, Hospitalization Forecasts Using Synthetic Data, February 19, 2026 скачать в хорошем качестве

WG/GLIMPRINT Seminars: Gerlee, Hospitalization Forecasts Using Synthetic Data, February 19, 2026

Evaluation of Respiratory Disease Hospitalization Forecasts Using Synthetic Outbreak Data Dr. Philip Gerlee, PhD Chalmers University of Technology Forecasts of hospitalizations of infectious diseases play an important role for allocating healthcare resources during epidemics and pandemics. Large-scale analysis of model forecasts during the COVID-19 pandemic has shown that the model rank distribution with respect to accuracy is heterogeneous and that ensemble forecasts have the highest average accuracy. Building on that work we generated a maximally diverse synthetic dataset of 324 different hospitalization time-series that correspond to different disease characteristics and public health responses. We evaluated forecasts from 14 component models and 6 different ensembles. Our results show that component model accuracy was heterogeneous and varied depending on the current rate of disease transmission. Going from 7 day to 14 day forecasts mechanistic models improved in relative accuracy compared to statistical models. A novel adaptive ensemble method outperforms all other ensembles on synthetic data, and is closely followed by a median ensemble. When evaluated on data from the COVID-19 pandemic, component models performed worse, but the ensemble accuracy was still high, with the median ensemble performing best. We also investigated the relationship between ensemble error and variability of component forecasts and show that the coefficient of variation is predictive of future error. Our findings have the potential to improve epidemic forecasting, in particular the adaptive ensemble and the ability to assign confidence to ensemble forecasts at the time of prediction based on component forecast variability. For more information see: 1) Béchade, G., Lundh, T., & Gerlee, P. (2025). Evaluation of respiratory disease hospitalisation forecasts using synthetic outbreak data. arXiv preprint https://arxiv.org/abs/2503.22494 2) Gerlee, P., Lundh, T., Saxne Jöud, A., & Thorén, H. (2026). Evaluating infectious disease forecasts in a cost-loss situation. arXiv preprint https://arxiv.org/abs/2601.05921 3) Gerlee, P., Lundh, T., Björnham, O., Brouwers, L. & Tegnell, A. (2026). Handbook of mathematical modelling of infectious diseases for decision-making https://research.chalmers.se/publicat... 4) Gerlee, P., et al. (2022). Computational models predicting the early development of the COVID-19 pandemic in Sweden: systematic review, data synthesis, and secondary validation of accuracy. Scientific Reports 12: 13256: https://www.nature.com/articles/s4159... Contents 00:00 - Introduction 04:35 - IMOBio Seminar Series - Lessons Learned from Modeling COVID-19, Series Introduction, presented by Jacob Barhak 07:04 - Evaluation of Respiratory Disease Hospitalization Forecasts Using Synthetic Outbreak Data, presented by Philip Gerlee 45:26 - Discussion between Philip Gerlee and Jacob Barhak 50:06 - General Discussion and Questions For a copy of the slides for this video visit: https://drive.google.com/file/d/1eHKF... Moderated by: Jacob Barhak and James A.Glazier If you found this video useful, please check out our other videos on computational modeling, infection and immunology:    • IMAG/MSM WG and GLIMPRINT Seminars on Mult...   Please consider joining our IMAG/MSM WG on Multiscale Modeling and Viral Pandemics: https://www.imagwiki.nibib.nih.gov/co... Please also consider joining the Global Alliance for Immune Prediction and Intervention: http://glimprint.org/