A dynamic ensemble model for short-term forecasting in pandemic situations
Bibliographic Data
| ID | 19590685 |
|---|---|
| Authors | Jonas Botz (0009-0004-6056-3144), Laure-Amélie Couturié, Diego Valderrama (0000-0003-1497-2954), J Lucas y Hernandez (0000-0002-2333-923X), Jannis Guski (0000-0003-4911-2751), Holger Fröhlich (0000-0002-5328-1243) |
| Editors | Francesco Branda (0000-0002-9485-3877) |
| Year | 2024 |
| Volume | 4 |
| Issue | 8 |
| Pages | e0003058 |
| Publication date | 2024-08-22 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | PLOS Global Public Health (JOURNAL) |
| Journal identifiers | ISSN: 2767-3375 • E-ISSN: 2767-3375 |
| Publisher | Public Library of Science (PLoS) (PUBLISHER) |
| DOI | 10.1371/journal.pgph.0003058 |
| OpenAlex | W39172923 |
| Language | EN |
| Citations received | 1 |
| References cited | 31 |
During the COVID-19 pandemic, many hospitals reached their capacity limits and could no longer guarantee treatment of all patients. At the same time, governments endeavored to take sensible measures to stop the spread of the virus while at the same time trying to keep the economy afloat. Many models extrapolating confirmed cases and hospitalization rate over short periods of time have been proposed, including several ones coming from the field of machine learning. However, the highly dynamic nature of the pandemic with rapidly introduced interventions and new circulating variants imposed non-trivial challenges for the generalizability of such models. In the context of this paper, we propose the use of ensemble models, which are allowed to change in their composition or weighting of base models over time and could thus better adapt to highly dynamic pandemic or epidemic situations. In that regard, we also explored the use of secondary metadata—Google searches—to inform the ensemble model. We tested our approach using surveillance data from COVID-19, Influenza, and hospital syndromic surveillance of severe acute respiratory infections (SARI). In general, we found ensembles to be more robust than the individual models. Altogether we see our work as a contribution to enhance the preparedness for future pandemic situations
Humanities · Political science · Advanced Database Systems and Queries · Distributed and Parallel Computing Systems · Philosophy · Service-Oriented Architecture and Web Services
A random forest guided tour
Use of Ranks in One-Criterion Variance Analysis
Impact of Covid-19 on the social, economic, environmental and energy domains
Stacked generalization
Individual Comparisons by Ranking Methods
Long Short-Term Memory
Modeling approaches for early warning and monitoring of pandemic situations as well as decision support
| Unique citing works | 1 |
|---|---|
| Citations per year | 1 |
| Citation span | 2025 - 2025 (1) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 1 |