背景:艾滋病毒/艾滋病仍然是全球人类健康的主要挑战之一,特别是在资源有限的环境中。到2017年,超过7730万人感染了这种疾病。大约3540万人已经死于艾滋病相关疾病。大约有2170万人获得了具有显着临床结果的ART。然而,在不同护理级别的各种医疗保健提供者提供和准确解释艾滋病毒患者数据方面,遇到了许多挑战。移动健康(mHealth)技术正在逐步进入卫生部门和医学研究领域。不同的移动设备在医疗保健环境中变得很常见,导致开发专门用于实现特定健康相关目的的可下载软件的快速增长。
目的:我们开发了一种名为ARVPredictor的基于移动的应用程序,并证明它可以准确定义HIVpol基因中的HIV-1耐药性突变,以用于护理点。
方法:ARVPredictor是使用AndroidStudio和Java作为编程语言设计的,与Android和iOS兼容。应用程序系统托管在Nginx服务器上,和网络调用建立在由改造库处理的PHP的Laravel框架上。DigitalOcean为ARVPredictor提供高性能和稳定的云计算平台。此移动应用程序在GooglePlay商店中被列为“ARVPredictor”,源代码可在GitHub存储库的MIT许可许可下获得。为了测试ARVPredictor和斯坦福HIV数据库在检测HIV亚型和NNRT和NRTI突变方面的一致性,共评估了100个已知的HIV序列.
结果:基于移动的应用程序(ARVPredictor)接受一组序列或已知突变(蛋白酶,逆转录酶和整合酶)。然后返回推断的对所选核苷的抗性水平,非核苷蛋白酶,和整合酶抑制剂,用于在护理点准确管理艾滋病毒/艾滋病。与斯坦福HIV数据库相比,ARVPredictor在98/100序列中鉴定出相似的HIV亚型(κ=0.98,表明接近完美一致)。ARVPredictor鉴定出89/100主要NNRTI和NRTI突变,类似于斯坦福艾滋病毒数据库(κ=0.89,表明接近完美的一致性)。斯坦福HIV数据库分类为主要的八个突变被ARVPredictor分类为其他突变。
结论:ARVPredictor在识别主要和次要蛋白酶方面与StanfordHIV数据库基本一致,逆转录酶,和整合酶突变。该应用程序可以方便地在艾滋病毒/艾滋病护理提供者的护理点使用,以改善艾滋病毒感染的管理。
BACKGROUND: HIV/AIDS remains one of the major global human health challenges, especially in resource-limited environments. By 2017, over 77.3 million people were infected with the disease, and approximately 35.4 million individuals had already died from AIDS-related illnesses. Approximately 21.7 million people were accessing ART with significant clinical outcomes. However, numerous challenges are experienced in the delivery and accurate interpretation of data on patients with HIV data by various health care providers at different care levels. Mobile health (mHealth) technology is progressively making inroads into the health sector as well as medical research. Different mobile devices have become common in health care settings, leading to rapid growth in the development of downloadable software specifically designed to fulfill particular health-related purposes.
OBJECTIVE: We developed a mobile-based app called ARVPredictor and demonstrated that it can accurately define HIV-1 drug-resistance mutations in the HIV pol gene for use at the point of care.
METHODS: ARVPredictor was designed using Android Studio with Java as the programming language and is compatible with both Android and iOS. The app system is hosted on Nginx Server, and network calls are built on PHP\'s Laravel framework handled by the Retrofit Library. The DigitalOcean offers a high-performance and stable cloud computing platform for ARVPredictor. This mobile app is enlisted in the Google Play Store as an \"ARVPredictor\" and the source code is available under MIT permissive license at a GitHub repository. To test for agreement between the ARVPredictor and Stanford HIV Database in detecting HIV subtype and NNRT and NRTI mutations, a total of 100 known HIV sequences were evaluated.
RESULTS: The mobile-based app (ARVPredictor) takes in a set of sequences or known mutations (
protease, reverse transcriptase and integrase). It then returns inferred levels of resistance to selected nucleoside, nonnucleoside
protease, and integrase inhibitors for accurate HIV/AIDS management at the point of care. The ARVPredictor identified similar HIV subtypes in 98/100 sequences compared with the Stanford HIV Database (κ=0.98, indicating near perfect agreement). There were 89/100 major NNRTI and NRTI mutations identified by ARVPredictor, similar to the Stanford HIV Database (κ=0.89, indicating near perfect agreement). Eight mutations classified as major by the Stanford HIV Database were classified as others by ARVPredictor.
CONCLUSIONS: The ARVPredictor largely agrees with the Stanford HIV Database in identifying both major and minor proteases, reverse transcriptase, and integrase mutations. The app can be conveniently used robustly at the point of care by HIV/AIDS care providers to improve the management of HIV infection.