Deep learning and social network analysis elucidate drivers of HIV transmission in a high-incidence cohort of people who inject drugs.
Deep learning and social network analysis elucidate drivers of HIV transmission in a high-incidence cohort of people who inject drugs.
复制标题
深度学习和社交网络分析阐明了注射毒品人群中艾滋病毒传播的驱动因素。
DOI：
10.1126/sciadv.abf0158
复制
发表时间：
2022-10-21
期刊：
影响因子：
13.6
通讯作者：
中科院分区：
文献类型：
--
作者：
在全球范围内，注射吸毒人群（PWID）中的艾滋病疫情增长速度位居前列。基于社交网络的研究方法是了解和应对这些疫情的有力工具；然而，详细的社交网络研究数量有限，且在分析上存在挑战。我们从印度新德里的2512名注射吸毒者中收集了纵向社交（注射伙伴）和空间（注射场所）网络信息。我们运用网络分析和图神经网络（GNN）来揭示与艾滋病病毒传播相关的因素，并确定最佳干预实施点。纵向艾滋病发病率为每100人年21.3例。利用图神经网络进行的重叠社区检测显示存在七个社区，艾滋病发病率集中在其中一个社区。研究发现，与发病率关联最为紧密的注射场所与七个社区中的六个存在重叠，这表明在这一个地点开展干预措施能够覆盖大部分研究样本。这些研究结果凸显了网络分析和深度学习在艾滋病防治项目设计中的实用价值。
社交和空间网络结构是注射吸毒人群中艾滋病发病率的关键驱动因素。
Globally, people who inject drugs (PWID) experience some of the fastest-growing HIV epidemics. Network-based approaches represent a powerful tool for understanding and combating these epidemics; however, detailed social network studies are limited and pose analytical challenges. We collected longitudinal social (injection partners) and spatial (injection venues) network information from 2512 PWID in New Delhi, India. We leveraged network analysis and graph neural networks (GNNs) to uncover factors associated with HIV transmission and identify optimal intervention delivery points. Longitudinal HIV incidence was 21.3 per 100 person-years. Overlapping community detection using GNNs revealed seven communities, with HIV incidence concentrated within one community. The injection venue most strongly associated with incidence was found to overlap six of the seven communities, suggesting that an intervention deployed at this one location could reach the majority of the sample. These findings highlight the utility of network analysis and deep learning in HIV program design. Social and spatial network structures are critical drivers of HIV incidence among people who inject drugs.
登录
查看更多内容
影响因子：
3.8
作者：
Linton, Sabriya L.;Cooper, Hannah L. F.;Luo, Ruiyan;Karnes, Conny;Renneker, Kristen;Haley, Danielle F.;Dauria, Emily F.;Hunter-Jones, Josalin;Ross, Zev;Wingood, Gina M.;Adimora, Adaora A.;Bonney, Loida;Rothenberg, Richard
通讯作者：
Rothenberg, Richard
影响因子：
5.8
作者：
Kursa, Miron B.;Rudnicki, Witold R.
通讯作者：
Rudnicki, Witold R.
影响因子：
3.7
作者：
Logan, James J.;Jolly, Ann M.;Blanford, Justine I.
通讯作者：
Blanford, Justine I.
直接和间接的社会和空间关系在注射药物的人中艾滋病毒和HCV传播中的作用：印度新德里的基于横断面的社区网络分析。
影响因子：
7.7
作者：
Clipman SJ;Mehta SH;Srikrishnan AK;Zook KJ;Duggal P;Mohapatra S;Shanmugam S;Nandagopal P;Kumar MS;Ogburn E;Lucas GM;Latkin CA;Solomon SS
通讯作者：
Solomon SS
影响因子：
3.7
作者：
Chamie G;Kato-Maeda M;Emperador DM;Wandera B;Mugagga O;Crandall J;Janes M;Marquez C;Kamya MR;Charlebois ED;Havlir DV
通讯作者：
Havlir DV