After more than 20 years of medical information dataization, China already has a huge medical data base. According to IDC, the global medical data volume has reached 153 EB in 2013, more than 600 EB in 2017, and is expected to reach 2.314 PB by 2020.
It is also the deep accumulation of medical big data . In recent years, after the rise of AI technology such as deep learning, many startups have tried to use clinical language understanding, image recognition and other technologies to clean clinical data. In the process, people found that the amount of medical data is enough, but the quality of medical data is worrying.
At the recent 2018 Shenzhen International BT Leaders Summit, Hu Shengshou, dean of the Chinese Academy of Medical Sciences Fuwai Hospital, mentioned in his keynote speech that the current data rate of medical institutions can reach 50% to 60%. It is.
At this stage, most artificial intelligence enterprises still need to ask a large number of experienced doctors to manually mark and machine assist in the process of cleaning the medical data.
How can we produce high quality medical data from the beginning? Recently, at the 80th China International Medical Equipment Fair, Professor Lu Xudong, Professor of Biomedical Engineering and Instrument Science, Zhejiang University, Zhao Dongsheng, Researcher of Military Medical Research Institute, and Zhang Siwei, General Manager of Medical Products Line of Shenzhen Zhongxing Netcom Technology Co., Ltd. People, gave a keynote speech on how to use the open international standard openEHR to build high-quality, standardized medical big data.
"waves" set off by medical big data
Whether it is a country, a business or a university, in recent years, the “reverberation†of medical big data has been great.
In 2015, the State Council issued the “Outline for the Promotion of Big Data Developmentâ€, which clarified the general requirements for data usage. At the end of June 2016, the State Council issued the “Guiding Opinions on Promoting and Regulating the Development of Big Data Applications for Health Careâ€, officially integrating medical big data into national development, and opening up the construction of medical big data integration and sharing in medical, medical, and public health. , medical insurance and other aspects of the application, as well as the use of security and other aspects of comprehensive regulation. In 2017, the national key enterprises led the establishment of three health big data companies: China Health Medical Big Data Industry Development Group Corporation, China Health Medical Big Data Technology Development Group Corporation, China Health Medical Big Data Co., Ltd.
In terms of enterprises, as the “Al+Medical†cake continues to expand, the importance of medical big data is also growing. Whether it is pharmaceutical companies, medical device manufacturers, life science companies, etc., they want to share a piece of it. . The market size of medical big data is also expanding. According to McKinsey's forecast, the market size of medical big data in the United States is between 300 billion and 450 billion US dollars per year. China also has a market scale of hundreds of billions of dollars in the field of medical big data. In this regard, investors have also sniffed business opportunities. The report released by Zhiyan Consulting also showed that in the first quarter of 2018, there were 35 investments in the field of health care big data, accounting for 22.2% in the field of big health.
In colleges and universities, the combination of production and research has always been strongly advocated by the state. In August of this year, approved by the China Health Information and Health Medical Big Data Society, Xiamen University established the “National Research Institute of Health and Medical Data of Xiamen Universityâ€. In October, Wuhan University announced the establishment of the “Wuhan University Health and Medical Big Data National Research Institute†to promote and standardize the development of health care big data applications.
Building high quality medical big data with openEHR
The application fields of medical big data can be described as a wide range, including intelligent auxiliary medicine and new drug research and development. However, many companies have found that the low quality of medical data has become a stumbling block in the development of “quick horsesâ€. Taking clinical medical data as an example, the main reasons for the low quality are:
First, when doctors use clinical data collection systems, the writing standards of medical records are not uniform and incomplete. Especially in the top three hospitals, the daily workload of doctors is large, and it is easy to fill in the electronic medical records.
Second, in the hospital electronic medical record data processing, although the medical industry has a high degree of informationization, but the degree of data is very low, most hospitals have achieved full coverage of the HIS system, and many patient data can be collected through the HIS system. However, because the underlying logic of patient information is not clear, most of the patient data is unstructured document data, and there is no way to directly analyze and apply the data.
Third, in the data quality control analysis, the quality control team is not serious enough to verify the data. This makes it easy for junk data to pass through the audit and enter the medical big data.
At the meeting, Lu Xudong of Zhejiang University proposed to use openEHR to create high-quality medical data from the source. But at the moment, most people are relatively new to openEHR.
According to the official website of openEHR China, openEHR is an open electronic health file specification proposed by the international openEHR organization in 1999. The core of the openEHR specification is to separate medical domain knowledge from specific clinical information and to establish a two-layer model—a reference model and a prototype model. The reference model models the stable concepts in the information system and defines the underlying data types and data structures required for information representation. The prototype model includes prototypes and templates. The prototype defines the clinical content by adding constraints to the reference model, and expresses the domain knowledge. The template meets the actual application requirements by constraining and customizing the prototype.
The openEHR model-driven open medical data platform can solve the problem that different roles have dynamic changes in data requirements, but each business system responds slowly. In addition, it can also solve the problem of increasing the number of medical service systems, and the continuous growth of data sources, but the inability to integrate them in time has become an issue of data silos.
In fact, OpenEHR has been widely used in countries such as Europe, Australia and Japan, and was accepted by the International Standards Organization in 2008 and developed into the ISO 13606-2 standard. To date, the National Electronic Health Archives Data Center has been adopted in many European countries, and the National Electronic Health Archives Data Center project launched in 2015 is also planned to adopt this standard.
Gelatin Size 0 Empty Capsule,Empty Shell Gelatin Capsule,Empty Gelatin Color Hard Capsules,Colorful Capsule Empty Gelatin
Ningbo Jiangnan Capsule Co., Ltd. , https://www.ningbocapsule.com