将人工智能应用于病媒控制:公共卫生的新途径

IF 1.2 4区 医学 Q4 INFECTIOUS DISEASES
Yusuf Hared Abdi, Yakub Burhan Abdullahi, Mohamed Sharif Abdi, Sharmake Gaiye Bashir, Naima Ibrahim Ahmed
{"title":"将人工智能应用于病媒控制:公共卫生的新途径","authors":"Yusuf Hared Abdi, Yakub Burhan Abdullahi, Mohamed Sharif Abdi, Sharmake Gaiye Bashir, Naima Ibrahim Ahmed","doi":"10.4103/jvbd.jvbd_144_25","DOIUrl":null,"url":null,"abstract":"<p><p>Vector-borne diseases remain a pressing global health challenge exacerbated by climate change, urbanization, and insecticide resistance. This review evaluates how artificial intelligence can strengthen vector surveillance, forecast outbreaks, and optimize interventions in public-health programs. Traditional control strategies rely on reactive. AI-driven systems, such as convolutional neural networks (CNNs, a form of image-recognition AI) and advanced machine learning models, achieve over 90% accuracy in real-time mosquito species identification, enabling targeted responses to invasive vectors such as Anopheles stephensi and Aedes aegypti. The integration of satellite imagery, climate data, and citizen science inputs into machine learning models improves outbreak prediction, with Bayesian networks forecasting dengue incidence 30 d in advance with 81% accuracy. AI also streamlines resource allocation and reduces insecticide use by 20-40% through reinforcement learning and drone-based habitat mapping. However, barriers to implementation persist, including data inequities, algorithmic biases, and infrastructure gaps in low-income regions. Ethical considerations such as privacy in data-sharing systems and community engagement in surveillance necessitate collaborative frameworks that bridge technologists, public health experts, and local stakeholders. Although AI cannot replace traditional methods, its capacity to augment decision-making in real time and data-driven insights offer a pathway for resilient, equitable vector control systems. Success depends on context-specific adaptation, investment in digital infrastructure, and sustained cross-sector partnerships to mitigate the disproportionate burden of vector-borne diseases on vulnerable populations.</p>","PeriodicalId":17660,"journal":{"name":"Journal of Vector Borne Diseases","volume":" ","pages":""},"PeriodicalIF":1.2000,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Using Artificial Intelligence in Vector Control: A New Path for Public Health.\",\"authors\":\"Yusuf Hared Abdi, Yakub Burhan Abdullahi, Mohamed Sharif Abdi, Sharmake Gaiye Bashir, Naima Ibrahim Ahmed\",\"doi\":\"10.4103/jvbd.jvbd_144_25\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Vector-borne diseases remain a pressing global health challenge exacerbated by climate change, urbanization, and insecticide resistance. This review evaluates how artificial intelligence can strengthen vector surveillance, forecast outbreaks, and optimize interventions in public-health programs. Traditional control strategies rely on reactive. AI-driven systems, such as convolutional neural networks (CNNs, a form of image-recognition AI) and advanced machine learning models, achieve over 90% accuracy in real-time mosquito species identification, enabling targeted responses to invasive vectors such as Anopheles stephensi and Aedes aegypti. The integration of satellite imagery, climate data, and citizen science inputs into machine learning models improves outbreak prediction, with Bayesian networks forecasting dengue incidence 30 d in advance with 81% accuracy. AI also streamlines resource allocation and reduces insecticide use by 20-40% through reinforcement learning and drone-based habitat mapping. However, barriers to implementation persist, including data inequities, algorithmic biases, and infrastructure gaps in low-income regions. Ethical considerations such as privacy in data-sharing systems and community engagement in surveillance necessitate collaborative frameworks that bridge technologists, public health experts, and local stakeholders. Although AI cannot replace traditional methods, its capacity to augment decision-making in real time and data-driven insights offer a pathway for resilient, equitable vector control systems. Success depends on context-specific adaptation, investment in digital infrastructure, and sustained cross-sector partnerships to mitigate the disproportionate burden of vector-borne diseases on vulnerable populations.</p>\",\"PeriodicalId\":17660,\"journal\":{\"name\":\"Journal of Vector Borne Diseases\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2025-09-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Vector Borne Diseases\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.4103/jvbd.jvbd_144_25\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"INFECTIOUS DISEASES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Vector Borne Diseases","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.4103/jvbd.jvbd_144_25","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"INFECTIOUS DISEASES","Score":null,"Total":0}
引用次数: 0

摘要

病媒传播疾病仍然是一项紧迫的全球卫生挑战,气候变化、城市化和杀虫剂耐药性加剧了这一挑战。本综述评估了人工智能如何在公共卫生计划中加强媒介监测、预测疫情和优化干预措施。传统的控制策略依赖于被动控制。人工智能驱动的系统,如卷积神经网络(cnn,一种图像识别人工智能)和先进的机器学习模型,在实时蚊子种类识别方面实现了90%以上的准确率,从而能够对斯氏按蚊和埃及伊蚊等入侵媒介做出有针对性的反应。将卫星图像、气候数据和公民科学输入整合到机器学习模型中,改进了疫情预测,贝叶斯网络提前30天预测登革热发病率,准确率为81%。人工智能还通过强化学习和基于无人机的栖息地测绘,简化了资源分配,减少了20-40%的杀虫剂使用。然而,实施的障碍仍然存在,包括数据不平等、算法偏差和低收入地区的基础设施差距。数据共享系统中的隐私和社区参与监测等伦理方面的考虑需要协作框架,将技术人员、公共卫生专家和地方利益攸关方联系起来。尽管人工智能不能取代传统方法,但其增强实时决策和数据驱动见解的能力为建立有弹性、公平的病媒控制系统提供了途径。成功取决于具体情况的适应、对数字基础设施的投资以及持续的跨部门伙伴关系,以减轻病媒传播疾病对弱势群体造成的不成比例的负担。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Using Artificial Intelligence in Vector Control: A New Path for Public Health.

Vector-borne diseases remain a pressing global health challenge exacerbated by climate change, urbanization, and insecticide resistance. This review evaluates how artificial intelligence can strengthen vector surveillance, forecast outbreaks, and optimize interventions in public-health programs. Traditional control strategies rely on reactive. AI-driven systems, such as convolutional neural networks (CNNs, a form of image-recognition AI) and advanced machine learning models, achieve over 90% accuracy in real-time mosquito species identification, enabling targeted responses to invasive vectors such as Anopheles stephensi and Aedes aegypti. The integration of satellite imagery, climate data, and citizen science inputs into machine learning models improves outbreak prediction, with Bayesian networks forecasting dengue incidence 30 d in advance with 81% accuracy. AI also streamlines resource allocation and reduces insecticide use by 20-40% through reinforcement learning and drone-based habitat mapping. However, barriers to implementation persist, including data inequities, algorithmic biases, and infrastructure gaps in low-income regions. Ethical considerations such as privacy in data-sharing systems and community engagement in surveillance necessitate collaborative frameworks that bridge technologists, public health experts, and local stakeholders. Although AI cannot replace traditional methods, its capacity to augment decision-making in real time and data-driven insights offer a pathway for resilient, equitable vector control systems. Success depends on context-specific adaptation, investment in digital infrastructure, and sustained cross-sector partnerships to mitigate the disproportionate burden of vector-borne diseases on vulnerable populations.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Vector Borne Diseases
Journal of Vector Borne Diseases INFECTIOUS DISEASES-PARASITOLOGY
CiteScore
0.90
自引率
0.00%
发文量
89
审稿时长
>12 weeks
期刊介绍: National Institute of Malaria Research on behalf of Indian Council of Medical Research (ICMR) publishes the Journal of Vector Borne Diseases. This Journal was earlier published as the Indian Journal of Malariology, a peer reviewed and open access biomedical journal in the field of vector borne diseases. The Journal publishes review articles, original research articles, short research communications, case reports of prime importance, letters to the editor in the field of vector borne diseases and their control.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信