Editor's Note Artificial intelligence medical care is composed of smart hospital system, regional health system, and family health system, and promotes the development of the medical industry by building a regional medical information platform for health records and using the most advanced Internet of Things technology to realize the interaction between patients and medical staff, medical institutions and medical equipment. According to data from the Internet Data Center (IDC), the global AI application market is expected to reach $127 billion by 2025, of which global AI healthcare is in a high-speed growth period, accounting for one-fifth of the AI market. The mainland artificial intelligence industry has developed rapidly, the top-level design, business model and technical model of artificial intelligence medical care are becoming increasingly mature, and the investment and financing market is active. The rapid development and popularization of artificial intelligence medical care has improved the quality of medical care, reduced medical costs, and helped the medical industry solve many livelihood problems such as resource shortage and uneven distribution, but at the same time, the ethical and legal issues of artificial intelligence medical care, as well as data sharing, application scenarios, technology iteration, and doctor-patient recognition, have also attracted the attention of the academic community. This journal specially invites experts and scholars from relevant branches of the Chinese Medical Association to discuss the opportunities and challenges of the development of artificial intelligence medical care for readers.
Lv Chuanzhu
Emergency medicine is a discipline that spans various clinical specialties and has its own theoretical system, which runs through pre-hospital emergency care, in-hospital emergency care, and critical intensive care. In the past decade, artificial intelligence has been widely used in the medical field, and has played a huge advantage and potential in assisting medical personnel to complete disease diagnosis, risk assessment and treatment. However, the popularization and application of artificial intelligence in the field of emergency medicine still faces many problems and challenges. This article will review the current application of artificial intelligence in the field of emergency medicine.
Application of artificial intelligence in pre-hospital first aid
Pre-hospital first aid refers to the on-site or in-transit medical treatment of patients with acute and/or trauma by emergency and/or trauma patients before they arrive at the hospital. It has strict requirements for first aid response time, first aid facilities, first aid personnel ability and first aid technology level. Severe patients with acute myocardial infarction, stroke and trauma have high mortality due to rapid progression, and early recognition, early diagnosis and targeted treatment are extremely important. Some studies have established a machine learning-based model for the automatic identification of seriously injured patients after traffic accidents by mining the text of emergency calls. In May 2019, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital invested in the 5G urban medical emergency rescue system for the first time, changing the past emergency mode and carrying out synchronous examination and diagnosis on ambulances, realizing patients "entering the hospital as soon as they get on the bus" and opening up the "high-speed channel" of life rescue. Pre-hospital diagnosis and condition assessment with the help of artificial intelligence is of great significance to improve the level of pre-hospital diagnosis and treatment.
Application of artificial intelligence in hospital emergency department
Overcrowding in emergency departments is a common problem faced by emergency medical staff, which significantly increases the emergency stay time of patients and increases the occurrence of emergency adverse events such as in-hospital deaths. The use of artificial intelligence technology to conduct a preliminary assessment of a patient's condition can improve the efficiency of pre-examination and triage and effectively relieve the pressure of emergency department admission. A retrospective analysis of 172 726 emergency patients was carried out, and machine learning algorithms such as random forests were used to build an electronic triage system, which can quickly and accurately identify patients.
Application of artificial intelligence in emergency ICU
Emergency ICU patients have an acute onset, severe disease, and rapid progression, so early prevention of severe patients is very important. Emergency physiology and chronic health scores, simplified acute physiology scores, etc., which are widely used in emergency ICUs, can assist medical staff in assessing the current vital signs and risk of patients, but they have limitations. With the rapid development of big data and artificial intelligence, the application in the fields of disease risk assessment, disease deterioration warning and mortality early warning is also increasing. Jawad et al. used real-time vital signs and laboratory monitoring data of ICU patients to predict the probability of septic shock in patients. Wang et al. used more than 30 vital signs data and basic patient information in the first 48 hours of the ICU to evaluate the mortality rate of patients.
With the development of information technology, the application of big data and artificial intelligence in the field of emergency medicine is also advancing by leaps and bounds. In 2017, the construction of the "Emergency First Aid Platform" led by Professor Lv Chuanzhu, Professor Chen Yuguo and Professor Yu Xuezhong enabled the systematic deployment of 5G, artificial intelligence and big data in the field of emergency medicine. In the same year, the National Health Commission officially issued a document to the Emergency Medicine Branch of the Chinese Medical Association, requiring the comprehensive promotion of the construction of a large emergency emergency platform. The development of emergency medicine has entered a new era - the era of China Emergency 3.0. With the assistance of big data and artificial intelligence, first aid is no longer limited to distance, and remote consultation, emergency rescue, remote surgery, remote ultrasound and other applications are used in daily diagnosis and treatment; First aid is no longer limited to the region, and can be consulted through video and other means, innovate the medical community emergency system, and promote the construction of a large emergency first aid platform in the county. Launched on November 30, 2022, ChatGPT can quickly complete tasks such as decision support, intelligent diagnosis, intelligent search, intelligent recommendation, and disease analysis and prediction with high accuracy, and further optimize its capabilities through continuous deep learning and data training. It can be seen that the scientific use of artificial intelligence such as ChatGPT is of great significance to promote the construction of emergency emergency first aid platform in the future. However, big data itself also has shortcomings, and it needs to be further improved in terms of accuracy and patient privacy protection. Therefore, artificial intelligence is only used as an auxiliary tool to enhance the work efficiency of medical personnel, and cannot replace medical personnel.
(Emergency Department, Peking Union Medical College Hospital, Wang Ruijie, Li Quan, Emergency Center, Sichuan Academy of Medical Sciences, Sichuan Provincial People's Hospital (Affiliated Hospital of University of Electronic Science and Technology of China), Lv Chuanzhu)
(The author of this article, Lv Chuanzhu, is the chairman of the Emergency Medicine Branch of the Chinese Medical Association)
Edit | Zheng Mengying Responsible Editor | Zheng Mengying Review | Han Jing
Chinese Medical Information Herald, Issue 8, 2023, 12th Edition
Director: China Association for Science and Technology
Organizer: Chinese Medical Association
Editor: Editorial Board of China Medical Information Herald
Address: 100052, No. 69, Donghe Yan Street, Xicheng District, Beijing
Editor-in-chief: Rao Keqin
Editorial Director: Han Jing
WeChat: cmaxxdb
Submission email: [email protected]
Official website: http://zhyxxxdb.yiigle.com