[论文解读] Interpretable machine learning applied to on-farm biosecurity and porcine reproductive and respiratory syndrome virus

Abagael L. Sykes, Gustavo S. Silva+5 more|arXiv (Cornell University)|Jun 11, 2021

Animal Virus Infections Studies参考文献 96被引用 23

一句话总结

本研究开发了MrIML-biosecurity——一种可解释的机器学习工具包，通过利用生物安全措施和农场人口统计学数据，预测猪场蓝耳病病毒（PRRSV）暴发风险。通过应用局部和全局模型解释方法，识别出关键风险因素，如员工流动率、共用运输拖车以及与其他猪场的接近程度，从而实现基于数据的、针对特定猪场的生物安全基准评估，并提供可操作的疾病预防见解。

ABSTRACT

Effective biosecurity practices in swine production are key in preventing the introduction and dissemination of infectious pathogens. Ideally, biosecurity practices should be chosen by their impact on bio-containment and bio-exclusion, however quantitative supporting evidence is often unavailable. Therefore, the development of methodologies capable of quantifying and ranking biosecurity practices according to their efficacy in reducing risk have the potential to facilitate better informed choices. Using survey data on biosecurity practices, farm demographics, and previous outbreaks from 139 herds, a set of machine learning algorithms were trained to classify farms by porcine reproductive and respiratory syndrome virus status, depending on their biosecurity practices, to produce a predicted outbreak risk. A novel interpretable machine learning toolkit, MrIML-biosecurity, was developed to benchmark farms and production systems by predicted risk, and quantify the impact of biosecurity practices on disease risk at individual farms. Quantifying the variable impact on predicted risk 50% of 42 variables were associated with fomite spread while 31% were associated with local transmission. Results from machine learning interpretations identified similar results, finding substantial contribution to predicted outbreak risk from biosecurity practices relating to: the turnover and number of employees; the surrounding density of swine premises and pigs; the sharing of trailers; distance from the public road; and production type. In addition, the development of individualized biosecurity assessments provides the opportunity to guide biosecurity implementation on a case-by-case basis. Finally, the flexibility of the MrIML-biosecurity toolkit gives it potential to be applied to wider areas of biosecurity benchmarking, to address weaknesses in other livestock systems and industry relevant diseases.

研究动机与目标

• 为猪生产中的农场生物安全措施缺乏定量、基于证据的基准评估提供解决方案。
• 开发一种方法，量化并排序各项生物安全措施对PRRSV暴发风险的影响。
• 创建一个可解释的机器学习工具，支持农场层面和系统层面的风险评估与生物安全优化。

提出的方法

• 基于139个猪群的调查数据，训练多种机器学习算法，根据生物安全措施和农场人口统计学特征对PRRSV状态进行分类。
• 开发MrIML-biosecurity，一种专门扩展MrIML框架的工具包，用于生物安全领域的可解释机器学习。
• 应用全局基准分析，按整体重要性对变量进行排序，评估其在各类猪场和生产系统中预测PRRSV风险的贡献。
• 使用局部模型无关解释方法（如SHAP值），量化每项生物安全措施对单个农场预测风险的独立贡献。
• 生成传播图和水桶图，可视化各变量对预测暴发风险的方向和大小贡献。
• 通过Matthew相关系数（MCC）、特异性、敏感性和AUC等指标验证模型性能。

实验结果

研究问题

• RQ1 哪些农场生物安全措施和人口统计因素对预测PRRSV暴发风险具有最显著影响？
• RQ2 如何利用可解释的机器学习对农场层面的个体生物安全措施对疾病风险的影响进行排序和量化？
• RQ3 共用设备、员工流动率以及与其他猪场的距离在多大程度上影响PRRSV风险预测？
• RQ4 模型解释能否揭示有暴发史和无暴发史农场之间的可操作性差异？
• RQ5 MrIML-biosecurity工具包如何支持在多样化生产系统中实现个性化生物安全评估与基准比较？

主要发现

• 在分析的42个变量中，50%与媒介传播相关，31%与本地传播途径相关。
• 关键风险因素包括高员工流动率、共用运输拖车、靠近公共道路以及本地猪场密度高。
• 每月兽医和管理人员的访问次数对风险有负向贡献，表明具有保护作用。
• 曾用淘汰种猪或断奶猪运输车运送过PRRSV阳性动物的猪场，其预测暴发风险显著升高。
• 局部解释显示，不同猪场中对预测风险贡献最大的措施各不相同，从而支持按案例定制生物安全优先级。
• MrIML-biosecurity工具包表现出强劲的预测性能，MCC、特异性、敏感性和AUC均较高，证实其在风险基准评估中的可靠性。