Smartphone-based DNA diagnostics for malaria detection using deep learning for local decision support and blockchain technology for security
Smartphone-based DNA diagnostics for malaria detection using deep learning for local decision support and blockchain technology for security
复制标题
DOI：
10.1038/s41928-021-00612-x
复制
发表时间：
2021-08-02
影响因子：
34.3
通讯作者：
Cooper, Jonathan M.
中科院分区：
文献类型：
--
作者：
Guo, Xin;Khalid, Muhammad Arslan;Cooper, Jonathan M.
在传染病诊断中，一旦检测完成，结果需要迅速传达给医疗专业人员，以便实施护理路径。在偏远、资源少的农村社区进行检测时，这是一个特别的挑战，在这些社区，这种疾病往往造成最大的负担。在这里，我们报告了一个基于智能手机的端到端平台，用于疟疾的多路DNA诊断。该方法使用低成本的纸质微流控诊断测试，与用于本地决策支持的深度学习算法和用于安全数据连接和管理的区块链技术相结合。我们通过在乌干达农村地区的现场测试验证了该方法，在那里它正确识别了98%以上的测试病例。我们的平台还提供安全的地理标记诊断信息，这为在监测框架内集成传染病数据创造了可能性。基于智能手机的系统使用深度学习算法进行本地决策支持，并结合区块链技术提供安全的数据连接和管理，可用于疟疾的多路DNA诊断。
In infectious disease diagnosis, results need to be communicated rapidly to healthcare professionals once testing has been completed so that care pathways can be implemented. This represents a particular challenge when testing in remote, low-resource rural communities, in which such diseases often create the largest burden. Here, we report a smartphone-based end-to-end platform for multiplexed DNA diagnosis of malaria. The approach uses a low-cost paper-based microfluidic diagnostic test, which is combined with deep learning algorithms for local decision support and blockchain technology for secure data connectivity and management. We validated the approach via field tests in rural Uganda, where it correctly identified more than 98% of tested cases. Our platform also provides secure geotagged diagnostic information, which creates the possibility of integrating infectious disease data within surveillance frameworks.A smartphone-based system that uses deep learning algorithms for local decision support, and incorporates blockchain technology to provide secure data connectivity and management, can be used for multiplexed DNA diagnosis of malaria.