RESUMEN
Objective:To explore the risk factors for atrial fibrillation(AF)in elderly Chinese patients with severe valvular heart disease(VHD).Methods:This was a cross-sectional study and consecutively enrolled 978 elderly patients with severe VHD diagnosed in 18 Class A tertiary hospitals across the country from September 2021 to March 2022, including 322(32.9%)patients with concurrent AF.Clinical and echocardiographic data were collected to analyze the risk factors for AF.Results:Among VHD patients, compared with the non-AF group, the AF group was older, had a higher female ratio, higher diastolic blood pressure, higher proportions with cerebrovascular disease and chronic kidney disease, lower serum low density lipoprotein cholesterol and higher serum creatinine, amino-terminal A-type natriuretion peptide and glycosylated hemoglobin.As for echocardiographic parameters, the left atrial diameter was larger, the left ventricular end-diastolic diameter, interventricular septum thickness, and left ventricular posterior wall thickness were smaller in the AF group than in the non-AF group.All of the differences were statistically significant(all P<0.05). The results of multivariate Logistic regression analysis showed that the left atrial anteroposterior diameter increased( OR=1.166, P<0.01), the left ventricular end-diastolic diameter decreased( OR=0.929, P<0.01), and advanced age( OR=1.051, P<0.05)was an independent risk factor for elderly VHD patients with concurrent AF. Conclusions:In elderly patients with severe VHD, advanced age, an increased left atrial anteroposterior diameter, and a decreased left ventricular end-diastolic diameter were independently associated with AF.Therefore, evaluation of cardiac structure and regular follow-up should be performed in elderly patients with severe VHD for early intervention to reduce the incidence of AF.
RESUMEN
Objective@#To explore the valuable thematic information and sentiment distribution in patients′ medical service complaint texts based on topic modeling and sentiment analysis, and investigate the main driving factors affecting patients′ service experience and satisfaction.@*Methods@#Topic mining was carried out on the offline patient complaint text set of a tertiary hospital in South China from 2013 to 2017. The seed word set extracted from 1 000 sampled texts was used to guide semi-supervised Latent Dirichlet Allocation training of texts. Relevant subject categories were extracted and subject characteristics were graded emotionally.@*Results@#in the end, 30 subject categories were extracted from the 8 000 complaint texts, and the sentiment score of the subject characteristics was consistent with the sentiment tendency of the actual data set. However, the satisfaction was relatively low in " toilet" , " ward" , " hygiene" and other subjects, and the main complaint subjects included " attitude" , " examination" , " ward" among others.@*Conclusions@#Based on the theme distribution, combined with the results of emotional analysis and the specific clinical environment, strengthening management in the medical service sector with a large negative emotional score can guide the hospital management practice and service improvement process, and help to improve the patients′ perception experience and emotional experience.
RESUMEN
The effectiveness of regional health information platform was judged by overall assessment of its data contents, data quality, data safety and beneficial results in order to promote the mutual link and mutual communi-cation between the platforms and data centers at the provincial, municipal and county levels, speed up the data sharing and professional work cooperation, and meet the different information needs of different users.
RESUMEN
The paper analyzes the documents related to the foreign medical automatic Question Answering (QA) system,and compares the differences between automatic QA and traditional network information retrieval,describes the automatic QA system in the aspects of application researches,common tools and relevant technologies.Combining foreign related researches,it also discusses the current key problems of medical automatic QA system and the implications for China in order to offer reference for further research.
RESUMEN
Taking the diet problem of diabetic patients as an example,the paper puts forward the problems classification system based on functions in the view of users,classifies the problems put forward by patients through the Support Vector Machine (SVM) algorithm,and provides important support for the construction of the deep automatic Question Answering (QA) system.
RESUMEN
Through the retrieval of literatures about the research and application of ontology in the diabetes field in PubMed,IEEE/ IET Electronic Library,ACM,WANFANG,CNKI,VIP and other Chinese and English databases,as well as the search engines Google Scholar and Baidu Scholar,the paper shows the current situations and summarizes the main study contents.The result shows that the study achievements of ontology in the field of diabetes increase rapidly and there are obvious advantages in semantic comprehension in recent decade.
RESUMEN
The paper introduces the common methods for automatic de-identification of clinical texts,including the method based on rules,machine learning method,comprehensive method,etc.,states the challenges for clinical texts practicability,system universality and scalability of clinical texts de-identification research,analyzes the further research direction,and provides reference for researchers of this field.
RESUMEN
Objective Networked health information on diabetes updated by some websites was evaluated to provide evidence for its improvement.Methods Twenty-four domestic diabetes-related websites were identified,and primary index (media index,health information index and diabetes information index) and secondary index (practicability index and novelty index) were evaluated by using hierarchal analysis method.Results Of three primary index,compared with media and health information index,diabetes information index showed higher scores.Moreover,health information and diabetes information had strong causality.For the secondary index,practicability and novelty got relatively lower scores.The website Diabetic Club and Health for All got the highest (3.2) and the slowest scores (1.7),respectively.Conclusion At present,domestic diabetes-related websites may be far from satisfaction and need improvement in technology and human resources and more inputs.