ABSTRACT
In December 2018,the National Health Commission and nine relevant departments joindy formulate and issue the "Special Three-Year Program for Prevention and Control of Endemic Diseases (2018-2020)",six major actions and requirements are clarified,and the direction for scientific prevention and control of endemic arsenic poisoning in the new era is pointed out.In order to improve the level of prevention and control of endemic arsenic poisoning,innovation in thinking and technology are required.The emergence of big data related technologies provides an important way and mode to break through the bottleneck of prevention and control in endemic arsenic poisoning.Based on the requirements of prevention and control of endemic arsenic poisoning under new circumstances and the new characteristics of medical research of the era of big data,this paper focuses on combing and analyzing the scientific problems that need to be solved at the current stage of endemic arsenic poisoning,and providing reference for promoting the optimization of prevention and control strategies on endemic arsenic poisoning.
ABSTRACT
Diabetes is a chronic noncommunicable disease,which is can't be cured,and only can be suppressed by long-term treatment and self-management.The clinical decision support system can simulate the thinking process of diabetes specialists in disease diagnosis,and can provide the regular medical treatment plans and recommend the optimal plans to doctors.Most of the existing clinical decision support systems are based on clinical guidelines,rule-based and case-based reasoning as well as ontology-based systems.The big data technology can acquire and process multiple heterogeneous data,and provide a more scientific personalized treatment plan.In recent years,a variety of big date processing methods have been applied to the clinical diagnosis of diabetes based on decision tree,neural network,fuzzy logic,support vector machine,APRIORI association rules and multidimensional analysis,and timing mining.However,these methods are still in preliminary stage.The framework of diabetes clinical decision support system based on big data technology was analyzed,and the future diagnostic and treatment methods were forecast.
ABSTRACT
OBJECTIVE: To evaluate the effectiveness of using the Clinical Medication Decision Support (CMDS) software in a children's hospital, discuss the potential improvement methods and provide references for researches on rational drug use software applied in pediatric medications. METHODS: Problematic prescriptions screened by CMDS from 06/15/2014 to 06/30/2014 were collected. The data were processed and analyzed using microsoft excel. RESULTS: Among the 68834 issues, 51.2% of them were a-bout incorrect dosage and administration. Among the 294 drugs reported by CMDS with issues on dosage and administration, 37.1% had no information for dosage of pediatric use in the drug labels; 74.5% of the issues on dosage and administration corresponded to drugs with complicated pediatric dosage scenarios; while most of these issues had no clinical significance based on further clinical analysis. CONCLUSION: Application of rational drug use software for general purpose in children's hospitals may have specific problems such as difficulty in handling complicated drug dosage scenarios for children. These problems can be solved by leveraging big data technology.