Du Jian, Chen Ting, Zhang Luxia
National Institute of Health Data Science, Peking University, Beijing, China.
Institutes of Science and Development, Chinese Academy of Sciences, Beijing, China.
JMIR Med Inform. 2021 Jul 6;9(7):e26393. doi: 10.2196/26393.
There were 2 major incentives introduced by the Chinese government to promote medical informatics in 2009 and 2016. As new drugs are the major source of medical innovation, informatics-related concepts and techniques are a major source of digital medical innovation. However, it is unclear whether the research efforts of medical informatics in China have met the health needs, such as disease management and population health.
We proposed an approach to mapping the interplay between different knowledge entities by using the tree structure of Medical Subject Headings (MeSH) to gain insights into the interactions between informatics supply, health demand, and technological applications in digital medical innovation in China.
All terms under the MeSH tree parent node "Diseases [C]" or node "Health [N01.400]" or "Public Health [N06.850]" were labelled as H. All terms under the node "Information Science [L]" were labelled as I, and all terms under node "Analytical, Diagnostic and Therapeutic Techniques, and Equipment [E]" were labelled as T. The H-I-T interactions can be measured by using their co-occurrences in a given publication.
The H-I-T interactions in China are showing significant growth and a more concentrated interplay were observed. Computing methodologies, informatics, and communications media (such as social media and the internet) constitute the majority of I-related concepts and techniques used for resolving the health promotion and diseases management problems in China. Generally there is a positive correlation between the burden and informatics research efforts for diseases in China. We think it is not contradictory that informatics research should be focused on the greatest burden of diseases or where it can have the most impact. Artificial intelligence is a competing field of medical informatics research in China, with a notable focus on diagnostic deep learning algorithms for medical imaging.
It is suggested that technological transfers, namely the functionality to be realized by medical/health informatics (eg, diagnosis, therapeutics, surgical procedures, laboratory testing techniques, and equipment and supplies) should be strengthened. Research on natural language processing and electronic health records should also be strengthened to improve the real-world applications of health information technologies and big data in the future.
2009年和2016年中国政府出台了两项主要激励措施以推动医学信息学发展。由于新药是医学创新的主要来源，与信息学相关的概念和技术是数字医学创新的主要来源。然而，中国医学信息学的研究工作是否满足了疾病管理和人群健康等健康需求尚不清楚。
我们提出了一种利用医学主题词表（MeSH）的树形结构来描绘不同知识实体之间相互作用的方法，以深入了解中国数字医学创新中信息学供给、健康需求和技术应用之间的相互作用。
将MeSH树形父节点“疾病[C]”或节点“健康[N01.400]”或“公共卫生[N06.850]”下的所有术语标记为H。将节点“信息科学[L]”下的所有术语标记为I，将节点“分析、诊断和治疗技术及设备[E]”下的所有术语标记为T。H-I-T相互作用可以通过它们在给定出版物中的共现情况来衡量。
中国的H-I-T相互作用呈现出显著增长，并且观察到相互作用更加集中。计算方法、信息学和通信媒体（如社交媒体和互联网）构成了中国用于解决健康促进和疾病管理问题的与I相关的概念和技术的大部分。在中国，疾病负担与信息学研究工作之间总体上存在正相关。我们认为信息学研究应聚焦于疾病负担最大或影响最大的领域并不矛盾。人工智能是中国医学信息学研究的一个竞争领域，尤其关注医学成像的诊断深度学习算法。
建议加强技术转移，即医学/健康信息学要实现的功能（如诊断、治疗、手术程序、实验室检测技术以及设备和用品）。还应加强自然语言处理和电子健康记录的研究，以改善未来健康信息技术和大数据在现实世界中的应用。
