With the rapid development of information technology, the era of big data has come. In many fields including industry, commerce, and medicine, countless information is generated every day. This massive information can generate new value after induction, sorting, and analysis. In the medical field, the digital collection and storage of data are increasing year by year, and people have recognized the power of data. To some extent, data is productivity. More and more attention has been paid to various databases for certain medical purposes, such as Surveillance, Epidemiology, and End Results, Medical Information Mart for Intensive Care, Global Burden of Disease, China Health and Nutrition Survey, National Health and Nutrition Examination Survey, etc. In the face of such a large amount of medical information, various data mining technologies are widely used to process and analyze big data in the medical field, including a proportional hazards model, generalized linear expression, linear expression, a competitive risk model, the random forest algorithm, decision trees, and support vector machines, neural network, etc. The combination of these databases and data mining plays an important role in the prevention, diagnosis, treatment, and prognosis of the disease.
Medication plays an important role in medical treatment. While medication brings benefits to patients, it also brings risks or harms. Traditional clinical trials for medication consume huge financial costs and manpower costs. A large amount of medication treatment information is generated in the daily clinical work. The utilization of the information has very high-cost effectiveness for medication research. However, there is little information about medication in various medical databases. This is mainly due to the variety of medications, the complexity of medication treatment, and the difficulty in presenting the data structure of medication use. These make data mining in pharmaceutical research difficult. The unavailability of clinical information about medication is a great waste of resources. Correspondingly, compared with data mining in medicine, there are fewer types of research and achievements in pharmaceutical data mining. Therefore, the purpose of this research topic is to explore how to use big data for efficient pharmaceutical research, to provide help for the establishment of a better database, and to develop data mining technology for pharmaceutical research.
We welcome the original research, reviews, and mini reviews, including but not limited to:
• The establishment method of a database for drug prevention, treatment, and adverse reactions.
• Optimization of pharmaceutical data structure in a database.
• Data mining practice for pharmaceutical research.
Note: Drugs in the Research Topic refer to ones with a single active ingredient. We do not accept studies involving drugs with multiple active ingredients or unknown active ingredients.
With the rapid development of information technology, the era of big data has come. In many fields including industry, commerce, and medicine, countless information is generated every day. This massive information can generate new value after induction, sorting, and analysis. In the medical field, the digital collection and storage of data are increasing year by year, and people have recognized the power of data. To some extent, data is productivity. More and more attention has been paid to various databases for certain medical purposes, such as Surveillance, Epidemiology, and End Results, Medical Information Mart for Intensive Care, Global Burden of Disease, China Health and Nutrition Survey, National Health and Nutrition Examination Survey, etc. In the face of such a large amount of medical information, various data mining technologies are widely used to process and analyze big data in the medical field, including a proportional hazards model, generalized linear expression, linear expression, a competitive risk model, the random forest algorithm, decision trees, and support vector machines, neural network, etc. The combination of these databases and data mining plays an important role in the prevention, diagnosis, treatment, and prognosis of the disease.
Medication plays an important role in medical treatment. While medication brings benefits to patients, it also brings risks or harms. Traditional clinical trials for medication consume huge financial costs and manpower costs. A large amount of medication treatment information is generated in the daily clinical work. The utilization of the information has very high-cost effectiveness for medication research. However, there is little information about medication in various medical databases. This is mainly due to the variety of medications, the complexity of medication treatment, and the difficulty in presenting the data structure of medication use. These make data mining in pharmaceutical research difficult. The unavailability of clinical information about medication is a great waste of resources. Correspondingly, compared with data mining in medicine, there are fewer types of research and achievements in pharmaceutical data mining. Therefore, the purpose of this research topic is to explore how to use big data for efficient pharmaceutical research, to provide help for the establishment of a better database, and to develop data mining technology for pharmaceutical research.
We welcome the original research, reviews, and mini reviews, including but not limited to:
• The establishment method of a database for drug prevention, treatment, and adverse reactions.
• Optimization of pharmaceutical data structure in a database.
• Data mining practice for pharmaceutical research.
Note: Drugs in the Research Topic refer to ones with a single active ingredient. We do not accept studies involving drugs with multiple active ingredients or unknown active ingredients.