1. Electronic medical records
 
　　By far the most powerful application of big data is the collection of electronic medical records. Every patient has their own electronic record, including personal medical history, family medical history, allergies, and all medical test results.
 
　　These records are shared between different medical institutions through a secure information system (whether it is debatable). Every doctor can add or change records in the system, eliminating the need for time-consuming paper work. These records can also help patients master their own medications, and are also important data references for medical research.
 
　　Hidden dangers of network security
 
　　The potential safety hazards (disclosure, damage, tampering, etc.) of the data collector in data storage, transmission, and use; the safety
 
　　hazards of third-party medical institutions that obtain data sharing in the storage, transmission, and use of data.
 
　　2. Real-time health status alert
 
　　Another innovation in the medical industry is the application of wearable devices, which can report the health status of patients in real time.
 
　　Similar to the software that analyzes medical data in hospitals, these new analysis devices have the same functions, but can be used outside of medical institutions, reducing medical costs, allowing patients to know their health status at home, and at the same time gain intelligence. Treatment recommendations provided by the device.
 
　　These wearables continuously collect health data and store it in the cloud.
 
　　In addition to providing real-time information for individual patients, the collection of this information can also be used to analyze the health status of a group and for medical research based on geographic location, demographic or socioeconomic level. Finally, on the basis of these preliminary studies, formulate and adjust disease prevention and treatment programs.
 
　　An asthma inhaler equipped with GPS positioning is a typical example. It not only observes the asthma of a single patient, but also finds a better treatment plan for the area from the asthma patterns of multiple patients in the same area.
 
　　Another example is a blood pressure tracker. Once it is found that the blood pressure reaches the warning value, the blood pressure meter will send an alarm to the doctor. After receiving the alarm, the doctor immediately reminds the patient to treat it in time.
 
　　Wearable devices are ubiquitous in our daily lives, with pedometers, weight trackers, sleep monitors, home blood pressure monitors, and more providing critical data for medical databases.
 
　　Cybersecurity Hazards
 
　　Wearable devices are a small part of the Internet of Things. In addition to personal information such as names, ID cards, and phone numbers, our physical health is also "on the cloud" and monitored.
 
　　Although the collection of health data is of great significance to the timely detection of diseases, if the data is not protected, once the data is obtained by criminals, telephone harassment to promote medical products, telecommunication fraud related to physical health, and physical information of users of wearable devices Negative effects such as location will also follow.
 
　　3. According to the forecast of patient demand, the
 
　　on-demand allocation of medical resources in the "lineup" of medical staff can greatly reduce medical costs, so this work is of great significance to the global medical industry.
 
　　It may seem like an impossible task, but big data has helped some "pilot" units realize this idea. In Paris, France, four hospitals used data from multiple sources to predict the number of patients per day and hour in each hospital.
 
　　They used a technique known as "time series analysis" to analyze patient admission records over the past 10 years. The study could help researchers discover patterns in patient admissions and use machine learning to find algorithms that can predict future admission patterns.
 
　　This data will eventually be provided to hospital managers to help them predict the "lineup" of medical staff needed in the next 15 days, provide patients with more "corresponding" services, shorten their waiting time, and also help to provide medical services for patients. Medical staff arrange their workload as rationally as possible.
 
　　Hidden dangers of network security
 
　　Once the data is tampered with, the scheduling management of medical staff will fall into chaos, which will affect the normal operation of the hospital and even delay the timely treatment of patients.
 
　　4. Big data and artificial intelligence
 
　　Another application of big data in the medical industry is due to the rise of AI.
 
　　To put it simply, artificial intelligence technology analyzes complex medical data through algorithms and software to achieve the purpose of approximating human cognition. AI thus makes it possible for computer algorithms to predict conclusions without direct human input.
 
　　For example:
 
　　AI-powered brain-computer interfaces can help restore fundamental human experiences, such as speech and communication lost due to neurological disease and trauma to the nervous system.
 
　　Creating a direct interface between the human brain and a computer without the use of a keyboard, monitor or mouse would dramatically improve the quality of life for patients with amyotrophic lateral sclerosis or stroke injuries.
 
　　AI is an important part of a new generation of radiology tools, helping to analyze the entire tumor through a "virtual biopsy" instead of a small invasive biopsy sample. The application of AI in radiology can utilize image-based algorithms to characterize tumors.
 
　　Especially in developing countries, there is a shortage of medical personnel skilled in fields such as radiology and ultrasound. To a certain extent, AI can complete the diagnostic behavior that originally required human participation. For example, AI imaging tools can screen X-rays, reducing the need for a specialist radiologist in practice.
　　AI can also improve the efficiency of electronic medical record entry. The electronic entry of patient information takes a lot of time and effort.
 
　　At present, it is feasible to record every medical record of a patient in the form of video, and AI and machine learning can obtain more valuable information by retrieving the information in the video.
 
　　In addition, virtual assistants like Amazon's Alexa can enter real-time information at the patient's bedside, or help medical staff with routine patient requests, such as medication refills or notification of test results.
 
　　In short, AI can greatly reduce the workload of medical workers in management.
 
　　Hidden dangers of network security
 
　　Since machines can be used by good people to benefit mankind, they can also be controlled by evil people to destroy social stability. The security risks in artificial intelligence are no longer limited to data. What we worry about is that these human-imitating machines are controlled by malicious hackers and act against moral ethics.
 
　　5. Application of big data in medical imaging
 
　　Medical imaging includes X-rays, magnetic resonance imaging, ultrasound, etc., which are key links in the medical process.
 
　　Radiologists often need to view each examination result individually, which not only creates a huge workload, but also may delay the best treatment time for patients. But big data can completely change the way they are analyzed.
 
　　For example, hundreds of thousands of images enable the construction of an algorithm that recognizes patterns in images. These models can in turn form a numbering system that helps doctors make a diagnosis. The number of images that an algorithm can study far exceeds that of a human brain, and no radiologist can match the speed and strength of a machine in a lifetime.
 
　　Hidden dangers of network security
 
　　If the sample data in the information system is stolen or tampered with, the doctor will make a wrong diagnosis based on the wrong analysis result, endangering the life of the patient.