Artificial intelligence (AI) is one of the key drivers of digital health. Digital health and AI applications in medicine and biology are emerging worldwide, not only in resource-rich but also resource-limited regions. AI predates to the mid-20th century, but the current wave of AI builds in part on machine learning (ML), big data, and algorithms that can learn from massive amounts of online user data from patients or healthy persons. There are lessons to be learned from AI applications in different medical specialties and across developed and resource-limited contexts. A case in point is congenital heart defects (CHDs) that continue to plague sub-Saharan Africa, which calls for innovative approaches to improve risk prediction and performance of the available diagnostics. Beyond CHDs, AI in cardiology is a promising context as well. The current suite of digital health applications in CHD and cardiology include complementary technologies such as neural networks, ML, natural language processing and deep learning, not to mention embedded digital sensors. Algorithms that build on these advances are beginning to complement traditional medical expertise while inviting us to redefine the concepts and definitions of expertise in molecular diagnostics and precision medicine. We examine and share here the lessons learned in current attempts to implement AI and digital health in CHD for precision risk prediction and diagnosis in resource-limited settings. These top 10 lessons on AI and digital health summarized in this expert review are relevant broadly beyond CHD in cardiology and medical innovations. As with AI itself that calls for systems approaches to data capture, analysis, and interpretation, both developed and developing countries can usefully learn from their respective experiences as digital health continues to evolve worldwide.

中文翻译：

---

在资源受限的环境中实施人工智能和数字健康？我们在先天性心脏病和心脏病学中学习的十大经验教训。

人工智能（AI）是数字健康的关键驱动力之一。数字健康和人工智能在医学和生物学中的应用正在全球范围内兴起，不仅在资源丰富的地区而且在资源有限的地区。人工智能早于20世纪中叶，但当前的人工智能浪潮部分建立在机器学习（ML），大数据和算法上，这些技术可以从患者或健康人的大量在线用户数据中学习。从不同医学专业以及发达和资源有限的环境中的AI应用程序中可以汲取教训。一个典型的例子是继续困扰撒哈拉以南非洲的先天性心脏缺陷（CHD），这要求采用创新方法来改善风险预测和现有诊断方法的性能。除冠心病外，心脏病学中的AI也是有希望的背景。当前在冠心病和心脏病方面的数字健康应用套件包括互补技术，例如神经网络，机器学习，自然语言处理和深度学习，更不用说嵌入式数字传感器了。基于这些进步的算法正在开始补充传统医学专业知识，同时邀请我们重新定义分子诊断和精密医学专业知识的概念和定义。我们在这里检查并分享从当前尝试在CHD中实现AI和数字健康以在资源有限的环境中进行精确风险预测和诊断的经验教训。这篇专家评论总结的有关人工智能和数字健康的前十大课程在心脏病学和医学创新方面与冠心病无关。与AI本身一样，它要求采用系统方法来进行数据捕获，分析，