Mantis: A Foundation Model for Mechanistic Disease Forecasting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dudley, Carson, Magdaleno, Reiden, Harding, Christopher, Sharma, Ananya, Martin, Emily, Eisenberg, Marisa
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913028074635264
author Dudley, Carson
Magdaleno, Reiden
Harding, Christopher
Sharma, Ananya
Martin, Emily
Eisenberg, Marisa
author_facet Dudley, Carson
Magdaleno, Reiden
Harding, Christopher
Sharma, Ananya
Martin, Emily
Eisenberg, Marisa
contents Infectious disease forecasting in novel outbreaks or low-resource settings is hampered by the need for large disease and covariate data sets, bespoke training, and expert tuning, all of which can hinder rapid generation of forecasts for new settings. To help address these challenges, we developed Mantis, a foundation model trained entirely on mechanistic simulations, which enables out-of-the-box forecasting across diseases, regions, and outcomes, even in settings with limited historical data. We evaluated Mantis against 78 forecasting models across sixteen diseases with diverse modes of transmission, assessing both point forecast accuracy (mean absolute error) and probabilistic performance (weighted interval score and coverage). Despite using no real-world data during training, Mantis achieved lower mean absolute error than all models in the CDC's COVID-19 Forecast Hub when backtested on early pandemic forecasts which it had not previously seen. Across all other diseases tested, Mantis consistently ranked in the top two models across evaluation metrics. Mantis further generalized to diseases with transmission mechanisms not represented in its training data, demonstrating that it can capture fundamental contagion dynamics rather than memorizing disease-specific patterns. These capabilities illustrate that purely simulation-based foundation models such as Mantis can provide a practical foundation for disease forecasting: general-purpose, accurate, and deployable where traditional models struggle.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mantis: A Foundation Model for Mechanistic Disease Forecasting
Dudley, Carson
Magdaleno, Reiden
Harding, Christopher
Sharma, Ananya
Martin, Emily
Eisenberg, Marisa
Artificial Intelligence
Quantitative Methods
Infectious disease forecasting in novel outbreaks or low-resource settings is hampered by the need for large disease and covariate data sets, bespoke training, and expert tuning, all of which can hinder rapid generation of forecasts for new settings. To help address these challenges, we developed Mantis, a foundation model trained entirely on mechanistic simulations, which enables out-of-the-box forecasting across diseases, regions, and outcomes, even in settings with limited historical data. We evaluated Mantis against 78 forecasting models across sixteen diseases with diverse modes of transmission, assessing both point forecast accuracy (mean absolute error) and probabilistic performance (weighted interval score and coverage). Despite using no real-world data during training, Mantis achieved lower mean absolute error than all models in the CDC's COVID-19 Forecast Hub when backtested on early pandemic forecasts which it had not previously seen. Across all other diseases tested, Mantis consistently ranked in the top two models across evaluation metrics. Mantis further generalized to diseases with transmission mechanisms not represented in its training data, demonstrating that it can capture fundamental contagion dynamics rather than memorizing disease-specific patterns. These capabilities illustrate that purely simulation-based foundation models such as Mantis can provide a practical foundation for disease forecasting: general-purpose, accurate, and deployable where traditional models struggle.
title Mantis: A Foundation Model for Mechanistic Disease Forecasting
topic Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2508.12260