The era of big data has brought a big revolution that will transform the way we live, work, and think. In medical field, as the development of social economics and medicine since 21 century, the human disease spectrum has been changing, the disease type has been increasing, and the complexity of the etiology, diagnosis and treatment of disease have been gradually increasing. In order to improve the healthy level, and explore the law of disease occurrence and development, we should constantly research to find discipline in enormous knowledge by fully mining and using the big medical data. It will be helpful to improve the level medical information management. And it can be supportive to the diagnosis, treatment, clinical practice and decision-making. We did the review under the background of big data, and the mean contact of this review is about the origin, meaning, classification, features of big data as well as the research process, application and future development of data mining, especially clinical data mining.
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.
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.
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.
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.
As an interdisciplinary subject of medicine and artificial intelligence, intelligent diagnosis and treatment has received extensive attention in both academia and industry. Traditional Chinese medicine (TCM) is characterized by individual syndrome differentiation as well as personalized treatment with personality analysis, which makes the common law mining technology of big data and artificial intelligence appear distortion in TCM diagnosis and treatment study. This article put forward an intelligent diagnosis model of TCM, as well as its construction method. It could not only obtain personal diagnosis varying individually through active learning, but also integrate multiple machine learning models for training, so as to form a more accurate model of learning TCM. Firstly, we used big data extraction technique from different case sources to form a structured TCM database under a unified view. Then, taken a pediatric common disease pneumonia with dyspnea and cough as an example, the experimental analysis on large-scale data verified that the TCM intelligent diagnosis model based on active learning is more accurate than the pre-existing machine learning methods, which may provide a new effective machine learning model for studying TCM diagnosis and treatment.
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 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.
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.