Please wait a minute...

当期目录

    01 January 2019, Volume 5 Issue 1
    Previous Issue    Next Issue
    Topic:Big Data on Health Care
    Personal holo-healthinfo profile: a promising potential of health big-data applications and developments in China
    Xiaotao JIN, Guangyu WANG, Anpeng HUANG
    2019, 5(1):  3-11.  doi:10.11959/j.issn.2096-0271.2019001
    Asbtract ( 669 )   HTML ( 117)   PDF (1213KB) ( 862 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    As a well-known, aging issue is a big social-economic challenge in China. To address this challenge, health big-data was expected to bring new services, new technologies, new modes, a new ecosystem, and so on, for high-quality health and medical services. In return, this gain can help digital economics. Firstly, policy background of Chinese health big-data developments was introduced. And then, a personal holo-healthtinfo profile model was proposed. Finally, how to extend this model to promote our daily life quality efficiently and effectively was discussed.

    Medical data governance: building the data foundation for intelligent analysis of high quality medical big data
    Tong RUAN, Jiahui QIU, Zhixing ZHANG, Qi YE
    2019, 5(1):  12-24.  doi:10.11959/j.issn.2096-0271.2019002
    Asbtract ( 1125 )   HTML ( 189)   PDF (1475KB) ( 3267 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The various problems of medical data governance and data availability in the context of real-world research on a specific disease type were analyzed. The definitions and concepts of the data governance were provided, such as hospital data governance, regional data governance, data governance of disease-specific alliances, governance of medical annotation data and knowledge-based data. Here, the common methodologies and personality methodologies of data governance were summarized. Furthermore, the technologies of master data management, metadata management and data quality control in data governance were further discussed. Finally, the basic framework of medical big data standards was given, and the medical data quality was simply evaluated which based on the existing data governance evaluation standards.

    Deep learning based patient representation learning framework of heterogeneous temporal events data
    Luchen LIU, Jianhao SHEN, Ming ZHANG, Zichang WANG, Haoran LI, Zequn LIU
    2019, 5(1):  25-38.  doi:10.11959/j.issn.2096-0271.2019003
    Asbtract ( 569 )   HTML ( 42)   PDF (1736KB) ( 830 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Patient representation embeds patients' longitude records from multiple sources into continuous low-dimension vectors, which can be used to predict whether a disease will happen in the future. However, the problem is very challenging since patients' history records contain multiple heterogeneous temporal events. The visiting patterns of different types of events vary significantly, and there exist complex nonlinear relationships between different events. A novel model for learning the joint representation of heterogeneous temporal events was proposed. The model adds a new gate to control the visiting rates of different events which effectively models the irregular patterns of different events and their nonlinear correlations. Experiment results with real-world clinical data on the tasks of predicting death and abnormal lab tests prove the effectiveness of the proposed approach over competitive baselines.

    Research and application of artificial intelligence in medical imaging
    Dong HAN, Qihua LI, Wei CAI, Yuwei XIA, Jia NING, Feng HUANG
    2019, 5(1):  39-67.  doi:10.11959/j.issn.2096-0271.2019004
    Asbtract ( 1325 )   HTML ( 176)   PDF (12471KB) ( 1463 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In recent years, artificial intelligence (AI) has become the research hotspot in both academic and industrial societies, and has been applied to biometrics, natural language processing (NLP), finance and healthcare, et al., with huge success. The most recent progress of research and application of AI in medical imaging was introduced, including intelligent imaging system, intelligent image processing and analysis, radiomics and the combination of medical image and NLP, et al. The importance and feasibility of developing full-pipeline AI techniques were elaborated, and the related innovative work from both academic and industrial societies in recent years was introduced. Research of AI in medical imaging is still in its early stage and much more work needs to be done in the future, which will make this research area a long-term international hotspot.

    Intelligent diagnosis model and method of palpation imaging breast cancer based on data mining
    Xudong ZHANG, Shengli SUN, Hongchao WANG
    2019, 5(1):  68-76.  doi:10.11959/j.issn.2096-0271.2019005
    Asbtract ( 409 )   HTML ( 41)   PDF (1141KB) ( 631 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In order to assist the medical staff to diagnose breast cancer more effectively by palpation imaging technology, intelligent diagnosis model and method of palpation imaging breast cancer were established. Based on clinical data for early breast cancer screening and risk assessment, machine learning algorithms of decision tree, neural network, SVM, logistic regression, Bayesian network and five voting methods were adopted to distinguish breast tumor, or positive and negative outcome in algorithms. The positive sample data was incremented by the SMOTE algorithm, intelligent diagnosis model was established, and model can automatically diagnose breast tumors. Palpation imaging intelligent diagnosis model of breast cancer correctly screens all cases of breast cancer confirmed by pathology, and the accuracy of the model is as high as 98%. The intelligent diagnosis model is excellent as a screening modality for the detection of breast cancer.

    Exploration and applications of distributed database in financial area
    Lei LIU, Zhijun GUO, Haixin MA, Qiong ZHAO, Huiqi HU, Peng CAI, Hongtao DU, Aoying ZHOU, Zhanhuai LI
    2019, 5(1):  77-86.  doi:10.11959/j.issn.2096-0271.2019006
    Asbtract ( 567 )   HTML ( 75)   PDF (1199KB) ( 1756 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The rapid development of the financial technology has put forward great challenge to the database systems in bank. Specific system features, such as high performance, scalability, high availability and fault tolerance, were demanded. The traditional database systems are difficult to meet these requirements at the same time. In response to these challenges and meet the need of government, which calls for the “independent control of those core technology”, the Bank of Communications focuses on developing a new generation of database systems that support mission-critical banking transactions. A distributed database system with high performance, scalability, high availability and fault-tolerant characteristics was implemented by developing the lightweight distributed election protocol and distributed transaction, and it was applied to a number of important applications.

    Study on operation analysis and decisionmaking for sharing-bicycles
    Hong ZHANG, Dixin ZHOU, Chuanqi CHENG, Yu SHA
    2019, 5(1):  87-97.  doi:10.11959/j.issn.2096-0271.2019007
    Asbtract ( 394 )   HTML ( 53)   PDF (1907KB) ( 819 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Aiming at the problem of unbalanced distribution and unreasonable scheduling in the process of sharing-bicycles operating, based on the data of sharing-bicycles riding record for ten regions in a city, spatio-temporal statistics, regression deduction analysis and swarm intelligence algorithm were synthetically applied to analyze the spatio-temporal distribution characteristics and the optimization of path scheduling based on ant colony algorithm of sharing-bicycles was studied. At the same time, a optimal allocation scheme of sharing-bicycles based on satisfaction degree was designed. Finally, a regressive model of the number of bikes and taxi passengers was established to discuss the influence of sharing-bicycles on the taxi market. The research resultshave important guiding significance for solving the problems existing in the process of running and improving the operational efficiency and management level of sharing-bicycles.

    Analysis of HIV high-risk population characteristics with Baidu Tieba data
    Shiyao XIAO, Wei LYU, Saran CHEN, Shuo QIN, Ge HUANG, Mengsi CAI, Yuejin TAN, Xu TAN, Xin LU
    2019, 5(1):  98-108.  doi:10.11959/j.issn.2096-0271.2019008
    Asbtract ( 1164 )   HTML ( 106)   PDF (1572KB) ( 998 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The textual content and temporal pattern of online activities for users gathered in the “Fear of HIV Bar” of Baidu Tieba were analyzed. LDA topic model was used to analyze the main differences between topics discussed among HIV-infected people and non-HIV-infected people. A machine learning method based on key words was used to distinguish the sexual orientation of users who start a discussion in “Fear of HIV Bar”, and calculate the epidemic rate of HIV among groups with different sexual orientations. The techniques used in this paper can be supplemented as an important tool for high-risk populations research. In addition, this paper can be applied to assess the epidemic of HIV in populations with different sexual orientations by using machine learning technique to intelligently classify the sexual orientation of a user, which is of great significance for the public health agencies.

Most Download
More...
Most Read
More...
Most Cited
More...
Links
More...