Life & medical sciences · OECD FoS 3.3 · China MoE 1004 公共卫生与预防医学
Public health & epidemiology
公共卫生与流行病学
L2Local breakthroughs → Steady Score 1.90 · Last reviewed 2026-10-22 · Next review 2027-01-19
BIGGEST BREAKTHROUGH 2023-10-11 AI · majorField · major
EVEscape predicts viral immune-escape mutations (Nature) ↗
Predicted SARS-CoV-2 escape mutations from pre-pandemic data
Why this level
EVEscape forecast SARS-CoV-2 escape mutations from pre-pandemic data (Nature 2023); WHO issued LMM governance guidance in 2024. Use is mostly surveillance and analysis support.
S = 0.30·method + 0.35·discovery + 0.25·adoption + 0.10·education (education scores 0 when there is no evidence; if empty, the other weights are renormalised)
Sources
- nature.com/articles/s41586-023-06617-0
- who.int/news/item/18-01-2024-who-releases-ai-ethics-and-governance-guidance-for-large-multi-modal-models
Composite 1.5–2.49: at least one peer-reviewed/officially verified AI-key result, or one dimension at 3; routine workflow largely unchanged. All levels →
Research directions
Pathogen evolution forecastingOutbreak surveillanceBehavioural interventions
Papers
- Mantis: A foundation model for mechanistic disease forecasting
AI: trained on simulations, generalises to real outbreaks; Field: off-the-shelf forecasts for data-poor diseases and regions
2026-09-28 · Proceedings of the National Academy of Sciences
- Foundation models for time series forecasting and policy evaluation in infectious disease epidemics
Helps data-limited short-term forecasts; complements established models
2026-06 · Epidemics
- A disease-agnostic approach to ensemble learning for infectious disease forecasting
Forecasts emerging outbreaks without long histories
2026-03-20 · Nature Communications
- Artificial intelligence for modelling infectious disease epidemics
Systematic assessment of AI for epidemic modelling
2025-02-19 · Nature
- Learning from prepandemic data to forecast viral escape
Predicted SARS-CoV-2 escape mutations from pre-pandemic data
2023-10-11 · Nature
- The Parable of Google Flu: Traps in Big Data Analysis
Key cautionary case for validating public-health AI
2014-03-14 · Science
- Detecting influenza epidemics using search engine query data
Pioneered big-data real-time epidemic surveillance
2009-02-19 · Nature
- Learning Epidemic Threshold Equations from Simulation: REEBLRA, an Interpretable Bayesian Classification Framework for Reproduction Numbers
An interpretable Bayesian logistic framework that learns explicit epidemic-threshold equations (R0) from simulation data.
2026-10-21 · arXiv · Jomar F. Rabajante, Norvin P. Bansilan, Maria Czarina T. Lagura-Arreza, Destiny SM. Lutero
- Microbial traits have minimal power for predicting death from bloodstream infection
In 35,746 bloodstream infections, EHR-based ML predicts 30-day mortality (AUC 0.83); adding >70,000 microbial features does not help.
2026-10-11 · medRxiv · Gilliland, R., Valdes-Tresanco, M. E., Plakhotnyk, A., Westlund, A.
- Simpler is not always better: Phylodynamic misspecification and deep-learning corrections
Shows misspecified phylodynamic models bias R estimates and corrects them with deep learning.
2026-10-06 · medRxiv · XIE, R., Gascuel, O., ZHUKOVA, A.
- Amortized Bayesian Disease Mapping and Boundary Detection on Heterogeneous Spatial Graphs
Amortised Bayesian method decides where to break smoothing in disease maps to reveal local disparities.
2026-09-25 · arXiv · Luca Aiello, Sudipto Banerjee
- Unmasking digital despair: A language model framework for predicting depression on social media
Deep learning on Twitter/X posts predicts depression and an LLM characterises its possible causes.
2026-09-23 · medRxiv · Xie, M., He, H., Xie, Z.
- From arXiv, bioRxiv, medRxiv and OpenAlex (last ~30 days); summaries written by AIMap from the abstract.
Milestones 10
Big glowing nodes are leaps: AI leap cool · Field leap warm · double ring = both
-
Policy
WHO Hub for Pandemic and Epidemic Intelligence launches 2026–2030 strategy targeting 24-hour detection; AI-based EIOS used by 125+ Member StatesAI: EIOS scans thousands of open sources daily with AI. Field: WHO makes AI open-source intelligence one of five priority initiatives for early outbreak detection
WHO -
Model
Mantis: a foundation model for mechanistic disease forecasting (PNAS)AI: trained on simulations, generalises to real outbreaks; Field: off-the-shelf forecasts for data-poor diseases and regions
PNAS -
Paper
Foundation models for time-series forecasting and policy evaluation in infectious-disease epidemics (Epidemics)Helps data-limited short-term forecasts; complements established models
EpidemicsTo be verified -
Paper
epiFFORMA: disease-agnostic ensemble forecasting trained on synthetic outbreaks (Nat. Commun.)Forecasts emerging outbreaks without long histories
Nature Communications -
Deployment
WHO Berlin Hub: EIOS uses AI to flag unusual health events; AI pandemic simulator prototypedAI in WHO’s operational epidemic intelligence
WHO -
Paper
Artificial intelligence for modelling infectious disease epidemics (Nature)Systematic assessment of AI for epidemic modelling
Nature -
Paper
EVEscape predicts viral immune-escape mutations (Nature)Predicted SARS-CoV-2 escape mutations from pre-pandemic data
Nature -
Paper
The parable of Google Flu: traps in big data analysis (Science)Key cautionary case for validating public-health AI
Science -
Paper
Detecting influenza epidemics using search query data (Nature)Pioneered big-data real-time epidemic surveillance
Nature
No milestones match this filter.
More papers & repos 7
| Type | Title | Date |
|---|---|---|
| Paper | Mantis: A foundation model for mechanistic disease forecasting | 2026-09-28 |
| Paper | Foundation models for time series forecasting and policy evaluation in infectious disease epidemics To be verified | 2026-06 |
| Paper | A disease-agnostic approach to ensemble learning for infectious disease forecasting | 2026-03-20 |
| Paper | Artificial intelligence for modelling infectious disease epidemics | 2025-02-19 |
| Paper | Learning from prepandemic data to forecast viral escape | 2023-10-11 |
| Paper | The Parable of Google Flu: Traps in Big Data Analysis | 2014-03-14 |
| Paper | Detecting influenza epidemics using search engine query data | 2009-02-19 |
Latest news 7
- Former Crick Ph.D. student loses COVID vaccine paper for fabricationRetraction Watchen
- Epidemiological modeling in the age of artificial intelligenceNature Computational Scienceen
- Unlocking Earth AI’s planetary geospatial foundation models for global public healthGoogle Research Blogen