With the development of society and the progress of technology, artificial intelligence (AI) and big data technology have penetrated into all walks of life in social production and promoted social production and lifestyle greatly. In the medical field, the applications of AI, such as AI-assisted diagnosis and treatment, robots, medical imaging and so on, have greatly promoted the development and transformation of the entire medical industry. At present, with the support of national policy, market, and technology, we should seize the opportunity of AI development, so as to build the first-mover advantage of AI development. Of course, the development and challenges are coexisted. In the future development process, we should objectively analyze the gap between our country and developed countries, think about the unfavorable factors such as AI chips and data problems, and extend the application and service of AI and big data to all links of medical industry, integrate with clinic fully, so as to better promote the further development of AI medicine treatment in China.
Objective To explore the impact of personal digital assistant (PDA) information system on surgery operations, so as to provide basis for improving the efficiency of surgery operations and building medical research databases. Methods The data of patients undergoing surgical treatment in Northern Jiangsu People’s Hospital between October 1, 2018 and September 30, 2020 were retrospectively analysised. According to whether to operate the PDA information system, the patients who did not use the PDA information system for surgical treatment between October 1, 2018 and September 30, 2019 were taken as the control group (before the operation), and the patients who used the PDA information system for surgical treatment between October 1, 2019 and September 30, 2020 were taken as the intervention group (after the operation). The quality of surgical operation, the time of anesthesia opening, the time of opening operation, the length of operation, and other operation indicators before and after the operation of the PDA information system were analyzed. Results A total of 59 610 patients were enrolled, including 27 726 in the control group and 31 884 in the intervention group. Compared with before the operation of the PDA information system, the total annual operation increased by 4 158 cases (15.00%), and the average turnover of per operation room increased (17.10%). The average anesthesia opening time is 14.52 minutes earlier. The average operation opening time is 18.25 minutes earlier. Except for gastrointestinal center surgery, thoracic surgery, neurology surgery, trauma center surgery, intensive care unit ward surgery, biliary and pancreatic surgery, hepatosplenic surgery, and other types of surgery (P>0.05), other types of surgeries were statistically significant differences in the operation duration before and after other operations (P<0.05). Conclusions The PDA information system developed based on "VariFlight" quantifies the quality of surgical operations more finely. It can effectively improve the operation efficiency and economic benefits of surgery, shorten the operation time, contribute to the construction of medical research databases.
ObjectiveTo explore the methods of data management and statistical analysis for longitudinal big data collected from mobile health management applications (APP). MethodsThe data management process and statistical analysis method were proposed by summarizing the characteristics of the data from mobile health management APPs. The methods would be clarified by a practical case: an APP recording female menstruation. ResultsThe data from health management APPs belong to longitudinal big data and the original record of the APP should be reprocessed or computed before conducting statistical analysis. A two-step data cleaning procedure was suggested for data management of the original records and reprocessed data, and longitudinal models such as mixed models was recommended for statistical analysis. ConclusionsThe data from health management APPs could be used for medical research via specific data management and statistical analysis after removing suspicious data. Cloud computing could be a viable method to improve efficiency of the big data analysis of health management APPs.
This paper expounds the classification and characteristics of healthcare-associated infections (HAI) surveillance systems from the perspective of the informatization needs of HAI monitoring, explains the determination requirements of numerator and denominator in the surveillance statistical data, and introduces the regular verification for auditing the quality of HAI surveillance. The basic knowledge of machine learning and its achievements are introduced in processing surveillance data as well. Machine learning may become the mainstream algorithm of HAI automatic monitoring system in the future. Infection control professionals should learn relevant knowledge, cooperate with computer engineers and data analysts to establish more effective, reasonable and accurate monitoring systems, and improve the outcomes of HAI prevention and control in medical institutions.
ObjectiveTo discuss the scientific research and application value of the new China Association Against Epilepsy (CAAE) EEG reporting system, and to explore the model of establishing EEG database of tertiary comprehensive epilepsy center. MethodsA retrospective study was performed on outpatients who underwent EEG examination at the Epilepsy Center of Tsinghua University Yuquan Hospital from May 2021 to May 2022, and who also received EEG reports using the CAAE new EEG reporting system. We integrated the data of these 6380 patients with the previous database of our Epilepsy Center, and combined the two for the preliminary big data analysis. Results Among 6380 patients, normal EEG was reported in 2253 cases (35.3%) ,abnormal EEG in 4031 cases (63.2%), no definite abnormality in 96 cases. According to age groups, there were 3290 cases in children (51.0%), 1372 cases in adults (22.0%), 753 cases in adolescents (12.0%), 730 cases in infants (11.0%) and 235 cases in infants (4.0%).A total of 1466 (23.0%) patients were recorded with paroxysmal events, including 874 (60.0%) epileptic events. 517 (35.0%) non-epileptic events. ConclusionThe new EEG reporting system can provide a large number of researchable EEG data to guide clinical work, and it is an important tool for data sharing and big data research in the future.
As a science which focuses on evidence, the decision making process of evidence medicine encounters an opportunity for development in the big data era. The starting point is shifting forward from evidence to data. The big data technology is playing an active role in evidence's collection, process and utilization. Evidence is more objective, righteous, authentic, transparent and easier to collect. Thus, to initiate evidence-based medicine research in the big data era and to structure an evidence-based medicine intelligent service platform, a full-scaled strategy should be developed in order to improve the quality of evidence. To promote the complete publicity of clinical research data, structuralized clinical data standard should be constructed. To provide a pathway to patients' follow-up data, portable and wearable monitoring devices should be popularized. To avoid risks from utilization of clinical research big data, regulations of clinical data usage should be implemented.
ObjectiveTo analyze the clinical application and safety of Shenmai injection.MethodsWe collected clinical data of 30 012 patients using Shenmai injection from 26 hospitals nationwide from September, 2009 to June, 2013. The SPSS 15.0 software was used to analyze demographic characteristics, diagnostic information, and clinical application of the injection.ResultsAmong all patients, 14 270 were females (47.55%), 8 218 were aged 45-60 (27.38%), and 10 452 were aged 61-75 (34.83%). The primary use of Shenmai injection was as an adjuvant treatment of chemotherapy for cancer patients, and the top 3 cancers were lung cancer (1 533, 5.11%), breast cancer (1 509, 5.03%) and gastric cancer (847, 2.82%). The second important use of Shenmai injection was the treatment of coronary heart disease (5 703, 19.00%), of which the most common single dose was 50 mL (14 406, 48.00%), followed by 100 mL (10 804, 36.00%) and 200 mL (600, 2.00%). The solvents were used in 18 902 patients (62.98%), and the 5% glucose injection was used most frequently (84.64%). The adverse effects (AEs) rate was 0.15%, and 57.78% AEs occurred within 24 hours of infusion. The most common AEs were damage of the cardiovascular system, followed by damaging of blood system and respiratory system.ConclusionsShenmai injection has a wide range of applications and can be used in treatment of numerous diseases in the real-world, and the AEs have been linked to off-label uses.
According to the characteristics of the diversified employment system of general hospitals, we have independently developed a set of personnel information platforms suitable for our hospital's operating model and work-flow which achieved establishing a novel big data management model for big personnel. After a year of trial operation, the big data management of personnel has completely covered the target management and requirements of the hospital, covering basic quality, public services, teaching work, medical work, scientific research, and other dimensions of information, which helped the hospital constructed a systematically networked and full-coveraged, personnel information system with strong early warning functions and incentives, enabling the reasonable utilization rate of human capital and continuous improvement of the quality of talent training.
Big data technology is an inevitable result of the information age, which not only promotes the development of biomedical science, but also opens up new paths for the development of traditional Chinese medicine (TCM). This paper introduced the application status of big data technology in the field of TCM in recent years, and put forward some thinkings and prospects so as to provide new insights and methods for the future development direction of TCM.
The application scenarios and conditions of the burden of disease were sorted out, and the survey databases related to disease surveillance at home and abroad and the GBD research of IHME were introduced. Through the collection of literature, five cases of the burden of disease application of health big data were summarized, and their construction modes were described in detail based on different types of databases. We pointed out the problems and challenges faced by the application of health data, and put forward some ideas and prospects for future research on the application of the burden of disease of health big data.