Nowadays, medical robots have long been used in the medical field. At present, the famous one is Da Vinci, which is a general-purpose surgical robot, which is the most used in clinical practice. In the context of the rapid development of artificial intelligence today, medical robots will be the next blue ocean market in the medical field.
"The four-hour test of 150 minutes, averaging 15 minutes and 8 seconds, 456 points, 96 points on the passing line." On November 14, "Xiao Medical" received a comprehensive written test transcript of 2017 clinical practitioners According to the data, among the 530,000 candidates in the same period of the country, this score can be ranked higher.
"Xiao Medical" is a robot, officially known as "Chili Medical Assistant". It was developed by Tsinghua-Xinfei Joint Laboratory in February this year, and it can realize independent learning, independent reasoning and independent judgment. Wu He, director of the joint laboratory, said that the “intellectual assistant†passed the exam and did not benefit from the “sea tacticsâ€, but developed for the medical examination needs, so that it has the multi-level reasoning ability between words, sentences and paragraphs. Will help improve the doctor's diagnostic accuracy and shorten the treatment cycle. It said that the robot plays a role in assisting diagnosis and treatment, and will not try to replace the doctor for independent treatment, and will not replace people.
On August 26th, the first day of the 2017 national clinical practitioners comprehensive written test. On this day, 530,000 medical students and medical practitioners took the test.
A special "candidate" also ushered in a challenge this day. As an important project of Tsinghua-Xunfei Joint Laboratory (hereinafter referred to as the Joint Laboratory), the artificial intelligence system “Intelligent Medical Assistant†participated in the supervision of the National Health and Family Planning Commission, the Anhui Provincial Health Planning Commission, and the National Medical Examination Center. Two days, four written tests before and after.
The reporter learned from the joint laboratory that the "intelligent assistant" is the test site designated by the National Medical Testing Center. The answering process is notarized by the Beijing Guoxin Notary Office, and it is "strictly notarized, independent, and tested." Network shielding, on-site supervision." This is the first time in the world that artificial intelligence robots have participated in the “national†professional qualification examinations with human candidates for the first time, and the first response ability test of artificial intelligence technology in the medical field.
In two days, the time required for each exam is 150 minutes. The actual answer time of the “Smart Doctor Assistant†robot is 17 minutes 36 seconds, 13 minutes 46 seconds, 5 minutes 09 seconds, and 16 minutes 44 seconds, and the average time is 15 minutes. Zero 8 seconds.
On November 14, the Joint Laboratories reported that after reviewing the experts, the “Intelligent Doctor Assistant†scored a total of 456 points, ranking among the highest among the national candidates, with scores exceeding 90% of the candidates in Anhui Province this year. This is also the first time in the world that robots have passed the written test in the medical field.
I have been learning after the technology has been deposited."Intelligent Assistant" from the establishment of the project to the medical examination, a total of 9 months before and after. On February 14 this year, the Multimedia Signal and Intelligent Information Processing Laboratory of Tsinghua University and the AI ​​Research Institute and Xunfei Medical Company jointly established the medical test system R&D team. The joint laboratory is responsible for core algorithm research and core engine development.
This is not the first time that artificial intelligence technology has been involved in the medical field. Xu Geliang, president of Anhui Provincial Hospital, said in an interview with local media that in June 2016, Anhui Provincial Hospital and Keda Xunfei jointly developed an artificial intelligence medical image-assisted diagnosis system. In the past year, this system has diagnosed about 11,000 CT images in the CT room of the Provincial Hospital by learning 680,000 CT images of the lungs, and the diagnostic accuracy rate is 94%.
Since then, the Anhui Provincial Smart Hospital, which relies on artificial intelligence technology, has been established, which is also the first in China. In the hospital, artificial intelligence devices such as intelligent guiding medical guiding robots and artificial intelligence medical image assisted diagnosis systems have entered the application stage.
Even so, for artificial intelligence, technically it is still difficult to pass the medical comprehensive test. The reporter learned that when the first-generation product of "Intelligent Medical Assistant" was used as a simulation test, the score was only over 100 points. After learning nearly a million medical image materials, 53 professional medical textbooks, 2 million to identify real electronic medical records, 400,000. Medical literature and medical record reports, after continuous iteration and research and development, finally achieved high scores.
Have a massive knowledge base for comprehensive analysisThe robot passed the written test of the practicing doctor, and the score was higher than that of most candidates, which caused concern at one time. One view is that the secret of the "smart doctor assistant" is "the sea tactics", relying on the powerful memory of the computer. In this regard, the joint laboratory director Wu He denied.
Wu and introduction, the written test questions are changing every year, so for the machine, the annual written test is "new". In addition, the written test questions can be divided into two types: “knowledge type†and “case typeâ€. Since 2013, the new test syllabus has required to strengthen the assessment of clinical thinking ability, resulting in a continuous increase in the proportion of “case-type†test questions. Has reached more than 50%. Therefore, relying solely on memory ability and quick retrieval ability to answer questions obviously does not work. It said that the "intellectual assistant" passed the medical examination because it possessed the ability of independent learning, independent reasoning and self-determination.
The reporter learned that because artificial intelligence technology was first applied to the medical test field, the R&D team had no experience to follow. In the early stage of research and development, a problem arises: the medical knowledge is large and complex, and the traditional knowledge mapping technology cannot meet the needs of describing medical knowledge. It is more difficult to make the machine learn and understand how to use it.
In response to this situation, Wu He said that the joint laboratory proposed a set of methods called “semantic tensorâ€, which is to input huge amounts of materials including medical undergraduate textbooks, clinical guides and classic cases for medical examination needs. Make it have a huge medical knowledge base and do "learning". In addition, through the "keypoint semantic reasoning", "context semantic reasoning", "evidence chain semantic reasoning" and other algorithms, the machine's text reasoning ability is improved, so that it can "learn".
That is to say, after obtaining the professional knowledge base, the “Intelligent Doctor Assistant†has deep thinking and comprehensive application ability through technical innovation, and finally completes the medical knowledge test. In this process, the machine will complete the process from reasoning to analysis and judgment. Wu and introduction, in the answer, the robot first analyzes the stem and individual options, synchronizes the search in the knowledge base to find the possible conditions for each option to become the correct answer, and then analyzes the relationship between the stem, options and evidence. Finally make a judgment.
Developer: Artificial intelligence does not replace humansThe reporter was informed that the "Intelligent Assistant" will be promoted nationwide in March next year. Since it only passed the written test and did not participate in the practical skills test, it is still unable to obtain the qualification certificate for practicing doctors.
Is artificial intelligence technology a substitute for humans? The joint lab gave a negative answer. Tao Xiaodong, one of the project leaders and general manager of Keda Xunfei Medical, has publicly stated that practicing medicine alone will not be the development direction of “intelligent assistantsâ€. It is said that there are often unexpected situations in the actual diagnosis and treatment process, and artificial intelligence technology currently only has mastered the professional knowledge, and can not fully realize the use of knowledge. Wu He also said that the robot can play a role in assisting diagnosis and treatment, but will not try to replace the doctor for independent treatment, and will not replace people.
According to the plan of the joint laboratory, after the application of “Intelligent Doctor Assistantâ€, it will be used for medical education and standardized training research. In addition, it will also assist doctors in clinical diagnosis and treatment, which will help improve the diagnosis accuracy of doctors and shorten the diagnosis and treatment cycle. To the role of "medical secretary". For example, traditional reading medical records and admission records work, technical requirements are not high, but it takes a lot of doctors to work, the future can be carried out by robots, and through the understanding and extraction of information, give preliminary diagnosis recommendations. In addition, in the follow-up observations, the “Smart Doctor Assistant†can also provide more medical advice for doctors to choose.
"Help doctors with 60 points to do 80 points and 90 points for doctors to do 60 points less." At present, the "Chili Doctor Assistant" project has cooperated with the National Medical Testing Center to explore artificial intelligence in the field of medical examinations. Further application.
Hospital Bed Lift,Medical Bed Lift,Hospital Hoyer Lift,Hospital Lifts For Patients
XI'AN TYPICAL ELEVATOR CO., LTD , https://www.chinaxiantypical.com