![[2602.22673] Forecasting Antimicrobial Resistance Trends Using Machine Learning on WHO GLASS Surveillance Data: A Retrieval-Augmented Generation Approach for Policy Decision Support](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.22673] Forecasting Antimicrobial Resistance Trends Using Machine Learning on WHO GLASS Surveillance Data: A Retrieval-Augmented Generation Approach for Policy Decision Support
Summary
This article presents a machine learning framework for forecasting antimicrobial resistance (AMR) trends using WHO GLASS data, highlighting the effectiveness of XGBoost in predicting resistance rates and supporting policy decisions.
Why It Matters
Antimicrobial resistance is a critical global health issue, projected to cause millions of deaths annually. This research leverages machine learning to analyze WHO surveillance data, providing valuable insights for policymakers to combat AMR effectively. By identifying key predictors and utilizing advanced forecasting techniques, the study aims to enhance public health responses to this growing crisis.
Key Takeaways
- XGBoost outperformed other models in forecasting AMR trends with a test MAE of 7.07%.
- The prior-year resistance rate was identified as the most significant predictor of future resistance.
- Regional variations in forecasting accuracy highlight the need for tailored approaches in different WHO regions.
- The study integrates a Retrieval-Augmented Generation pipeline to support evidence-based policy decisions.
- Open access to code and data promotes transparency and further research in AMR forecasting.
Computer Science > Machine Learning arXiv:2602.22673 (cs) [Submitted on 26 Feb 2026] Title:Forecasting Antimicrobial Resistance Trends Using Machine Learning on WHO GLASS Surveillance Data: A Retrieval-Augmented Generation Approach for Policy Decision Support Authors:Md Tanvir Hasan Turja View a PDF of the paper titled Forecasting Antimicrobial Resistance Trends Using Machine Learning on WHO GLASS Surveillance Data: A Retrieval-Augmented Generation Approach for Policy Decision Support, by Md Tanvir Hasan Turja View PDF HTML (experimental) Abstract:Antimicrobial resistance (AMR) is a growing global crisis projected to cause 10 million deaths per year by 2050. While the WHO Global Antimicrobial Resistance and Use Surveillance System (GLASS) provides standardized surveillance data across 44 countries, few studies have applied machine learning to forecast population-level resistance trends from this data. This paper presents a two-component framework for AMR trend forecasting and evidence-grounded policy decision support. We benchmark six models -- Naive, Linear Regression, Ridge Regression, XGBoost, LightGBM, and LSTM -- on 5,909 WHO GLASS observations across six WHO regions (2021-2023). XGBoost achieved the best performance with a test MAE of 7.07% and R-squared of 0.854, outperforming the naive baseline by 83.1%. Feature importance analysis identified the prior-year resistance rate as the dominant predictor (50.5% importance), while regional MAE ranged from 4.16% (European ...
