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}
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.
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.