Predictive and interpretable machine learning for COVID-19 resurgences: the role of SARS-CoV-2 variants in the post-pandemic era
Rafaella S Ferreira, Marilaine Colnago, Wallace Casaca · 2025
Read Predictive and interpretable machine learning for COVID-19 resurgences: the role of SARS-CoV-2 variants in the post-pandemic era by Rafaella S Ferreira, Marilaine Colnago, Wallace Casaca (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12750626.txt.
Description
Rafaella Ferreira, Marilaine Colnago, and Wallace Casaca add virus variant data to COVID-19 forecasting, in this 2025 study. Older forecasts tracked case counts alone and missed how fast new variants outrun old ones. That blind spot slowed public health responses when waves turned. The authors argue that genomic watch data, which track variant shares, can sharpen neural forecasts in the current phase of the disease.
They tested their approach on data from New York City and the United Kingdom spanning 2022 to 2025. Several network designs were compared, and a memory-based design called LSTM won. Feeding variant shares in improved the forecasts over case data alone. Just as important, the team kept the model readable, so officials can see what drives each forecast rather than trusting a black box.
Catalog record
| CREATOR | Rafaella S Ferreira, Marilaine Colnago, Wallace Casaca |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |