Infectious Diseases
What can mathematics and data science tell us about the dynamics of infectious diseases?
Background
The COVID-19 pandemic has impacted the human population globally and mobilized the scientific community, which produced a massive effort to understand and contrast the specificities of this infectious disease.
Goals
This project aimed at producing timely data-driven results about the COVID-19 pandemic by combining differential equations and machine learning methods to study the dynamics of the diffusion of the disease at the regional and global level.
Broader Impacts
This research was disseminated through project-based courses, a thematic program, and many other initiatives that aimed at raising interest in student and community populations towards understanding the diffusion of infectious diseases using mathematical and statistical methods.
Relevant Publications
N. Olson, K.L. Foster, and A.M. Selvitella. (2022). On the possibility of mode-collapse phenomena in combined machine learning and differential equation models for infectious diseases. ICML 2022 The 1st Workshop on Healthcare AI and COVID-19.
N. Schutt, K.L. Foster, and A.M. Selvitella. (2022). An interpretable time-series model for predicting nurse shortages and planning optimal nurse scheduling and staffing during the COVID-19 pandemic. ICML 2022The 1st Workshop on Healthcare AI and COVID-19.
K.L. Foster and A.M. Selvitella. (2021). On the relationship between COVID-19 reported fatalities early in the pandemic and national socio-economic status predating the pandemic. AIMS Public Health, 8 (3), 439-455. https://doi.org/10.3934/publichealth.2021034
A.M. Selvitella, L. Carolan, J. Smethers, C. Hernandez, and K.L. Foster. (2021). A spatio-temporal investigation of the growth rate of COVID-19 incidents in Ohio, USA, early in the pandemic. The Ohio Journal of Science, 121 (2), 33-47. http://dx.doi.org/10.18061/ojs.v121i2.8059
N. Schutt, K.L. Foster, and A.M. Selvitella. (2021). On learning the effects of healthcare overextension on increased mortality rate in the COVID-19 pandemic. International Joint Conference on Artificial Intelligence 2021 Workshop on AI for Social Good. August 21st, 2021.
K.L. Foster and A.M. Selvitella. (2021). Government measures against COVID-19 must be determined according to the socio-economic status of the country. International Conference on Learning Representations 2021 Workshop on AI for Public Health. May 7th, 2021. https://aiforpublichealth.github.io/papers/ICLR-AI4PH_paper_2.pdf
A.M. Selvitella and K.L. Foster. (2021). A higher order Taylor expansion of the initial trajectory of COVID-19 cases and deaths via Bayesian hierarchical models: a toy problem and possible public health insights. International Conference on Learning Representations 2021 Workshop on AI for Public Health. May 7th, 2021. https://aiforpublichealth.github.io/papers/ICLR-AI4PH_paper_3.pdf
A.M. Selvitella and K.L. Foster. (2021). Bayesian detection and uncertainty quantification of the first change point of the COVID-19 case curve in the Midwest: Timeliness of non-pharmaceutical interventions. International Conference on Learning Representations 2021 Workshop on AI for Public Health & International Conference on Learning Representations 2021 Workshop on Machine Learning for Preventing and Combating Pandemics. May 7th, 2021. https://aiforpublichealth.github.io/papers/ICLR-AI4PH_paper_21.pdf
K. Menchhofer, N. Mills, K.L. Foster, and A.M. Selvitella. (2021). COVID-19 incidence in the Indiana’s secondary school system through a conditional Gaussian model and an age-structured compartmental model. International Conference on Learning Representations 2021 Workshop on Machine Learning for Preventing and Combating Pandemics. May 7th, 2021. https://mlpcp21.github.io/pages/Accepted%20Paper.html
A.M. Selvitella and K.L. Foster. (2020). Societal and economic factors associated with COVID-19 indicate that developing countries suffer the most. Technium Social Sciences Journal, 10, 637-644. https://doi.org/10.47577/tssj.v10i1.1357
Grants
Part of this project has been funded through the Summer Research Grant 2021 from the Purdue Research Foundation and through the Service-Learning Fellowship 2021 from the Purdue University - Office of Engagement.
Major Events
Data Science and Machine Learning Seminar Series. 2019/2020, 2020/2021, and 2021/2022.
Thematic Program on Data Science and COVID-19. 2020/2021. Co-organizer: K.L. Foster, Ball State University.
Data Science Week. 2019-2020-2021-2022. Co-organizer: K.L. Foster, Ball State University.
Main Collaborators
Kathleen Lois Foster - Ball State University Lab page