用机器学习预测细菌耐药趋势，帮政策制定者快速获取可信建议。
Forecasting Bacterial Antimicrobial Resistance Trends Using Machine Learning on WHO GLASS Surveillance Data: A Retrieval-Augmented Generation Approach for Policy Decision Support
- 用XGBoost模型结合往年耐药数据和用药量预测一年后耐药率。
- 模型误差比基础方法降低85.3%，欧洲区预测误差仅3.65%。
- 通过检索增强生成系统，自动输出有据可查的政策建议。
背景：抗菌药物耐药性（AMR）是全球健康威胁。尽管世界卫生组织全球抗菌药物耐药性与使用监测系统（GLASS）提供了标准化数据，但基于人群的机器学习耐药趋势预测仍有限。将计算结果转化为政策支持需透明的解释机制。方法：处理2021-2023年共5,909条观测数据，覆盖44个国家和五个世卫组织区域，采用严格的时序划分防止数据泄露。对比六种模型（朴素、线性、岭回归、XGBoost、LightGBM、LSTM），以过去一年耐药率和抗生素使用量为特征，预测一年后耐药率，评估指标包括MAE、RMSE、sMAPE，MAE采用95%自举置信区间。引入本地检索增强生成（RAG）系统，基于Gemma 4模型，从检索到的世卫组织文件中生成政策指导。结果：XGBoost表现最佳（测试MAE = 6.13% [95% CI: 5.83–6.44]），相比朴素基线（MAE = 41.79%）误差降低85.3%。SHAP分析显示，前一年耐药率是主导预测因子（贡献50.5%），证实强自回归特性。区域预测误差与监测覆盖率相关，欧洲区为3.65%，东南亚区达8.61%。RAG流程生成准确、来源可追溯的政策响应，无虚构引用。结论：短期耐药率具有显著时间自相关性，可通过梯度提升模型精准预测。将预测结果与抗幻觉RAG系统结合，可构建可扩展、基于证据的耐药性治理决策支持框架。
原文摘要 · Abstract (English)
Background: Antimicrobial resistance (AMR) is a global health threat. While the WHO Global Antimicrobial Resistance and Use Surveillance System (GLASS) provides standardized data, population-level machine learning forecasting of resistance trends remains limited. Translating computational forecasts into policy requires transparent interpretation mechanisms. Methods: Surveillance data (2021-2023) comprising 5,909 observations across 44 countries and five WHO regions were processed. A rigorous temporal split prevented data leakage. Six models (Naive, Linear, Ridge, XGBoost, LightGBM, LSTM) were benchmarked to forecast one-year-ahead resistance rates using features including prior-year resistance and antibiotic consumption. Evaluation metrics (MAE, RMSE, sMAPE) were computed, with 95% bootstrap confidence intervals for MAE. A local Retrieval-Augmented Generation (RAG) system utilizing Gemma 4 was implemented to translate forecast findings into policy guidance grounded in retrieved WHO documents. Results: XGBoost achieved the best performance (test MAE = 6.13% [95% CI: 5.83-6.44]), an 85.3% error reduction versus the naive baseline (MAE = 41.79%). SHAP analysis identified prior-year resistance as the dominant predictor (50.5% gain), confirming strong autoregressive behavior. Regional forecast error tracked closely with surveillance coverage, ranging from 3.65% in the European Region to 8.61% in South-East Asia. The RAG pipeline generated accurate, source-attributed policy responses without fabricated citations. Conclusion: Short-term AMR resistance rates exhibit strong temporal autocorrelation that can be accurately forecasted using gradient boosting. Coupling these forecasts with a hallucination-resistant RAG system provides a scalable, evidence-based decision-support framework for AMR governance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。