ABSTRACT
Patient diagnosis and treatment data are scattered in various clinical systems related to electronic medical records(EMR). The data can be better applied to the emergency prevention and control, medical research and government supervision only through unified integration. The authors analyzed the construction level of the EMR system in medical institutions, and sorted out the problems faced by directly extracting the diagnosis and treatment data of patients through the EMR system, including the lack of patient-centered integration of data, insufficient application depth of the EMR system, insufficient data standardization, lack of data and so on. Public health emergencies posed a severe challenge to the extraction of EMR data.For medical institutions with different information construction levels, the authors gave a feasibility analysis of data extraction by classification and time period, and suggested that medical institutions should fundamentally strengthen the understanding of information, establish data standard system and realize data integration and unified management.
ABSTRACT
This paper studied the correlation between traditional Chinese medicine (TCM) prescription and disease based on machine learning.This paper selected TCM literature abstract data in the TCM category of the China National Knowledge Infrastructure (CNKI) database by crawler technology.After data cleaning,lexicon building,word segmentation and other related basic pre-treatment work,it uses natural language processing technique to extract the feature of the web text data,constructs the Support Vector Machine (SVM) classification model,and extracts the relation between TCM prescription and disease.The results showed that among 1073581 abstracts,204780 sentences,which included both TCM prescription and the disease according to dictionaries,were filtered.The SVM classification model whose feature is constructed by constituency parser is in a better accuracy,which achieved 87％.Applying the SVM model in filtered sentences,this study obtained the relation triples between TCM prescription and the disease.It was concluded that by using the method of machine learning to extract relation on abstract data from the CNKI database,the extracted relation triples of TCM prescription and disease will take a positive effect on the research of disease treatment by TCM prescription.
ABSTRACT
Prevalence of obesity in Malaysia has been steadily rising over the last two decades. Therefore, the efforts towards curbing this problem is becoming increasingly necessary. The main objective of this cross-sectional study was to evaluate the effectiveness of obesity projects conducted by the NGOs funded by the Malaysian Health Promotion Board (MHPB). In this study, the secondary data from the final reports of 22 obesity projects were analyzed to evaluate its effectiveness. All the information in the final report was transferred into the formative evaluation forms prepared by MHPB. The effectiveness of obesity projects was determined through the level of achievement of health literacy by using 21 indicators validated data extraction tool based on the RE-AIM Model. Projects which achieved 15 to 21 marks are considered to be of high quality, 8 to 14 marks are considered to be of moderate quality and 0 to 7 marks are categorized as low quality. Using the Cohen’s Kappa test to assess the inter-rater reliability towards 21 indicators validated data extraction tool based on the RE-AIM Model, it was found that there was very high level of inter-rater agreement (K = 0.868). From the 22 obesity projects studied, none was considered to be of high quality, 21 projects were found to have a moderate quality and 1 project was found to be of low quality. There was no significant difference on the percentage achievement of health literacy between different duration of project undertaken (p > 0.05). Based on the health screening of 1982 project participants, 333 (16.8%) are overweight and 354 (17.9%) are obese. In conclusion, although majority of the projects were successfully carried out by the NGOs. A follow-up study is needed to monitor lifestyles change which may eventually lead to reduction in the prevalence of obesity in the community where the projects were executed