dc.description.abstract | In the highly competitive and increasingly globalized pharmaceutical industry, the development of data-based analytical methods and the application of data analysis techniques have become prioritized objectives for major pharmaceutical companies. Pharmaceutical R&D is a complex and time-consuming process traditionally focused on laboratory experiments.
However, in recent years, data-based approaches have gained significant attention and application in pharmaceutical R&D. These data-based methods include data analysis, machine
learning, and artificial intelligence, among other technologies, which can transform large amounts of data into valuable insights and provide essential data support for drug discovery, optimization, and evaluation.
This study uses a case company′s research product, a pharmaceutical drug for treating iron deposition, as an example to explore the application and value of data analysis methods based on data-driven approaches in the pharmaceutical research and development process. The study introduces the basic process of pharmaceutical R&D and discusses the differences in results generated by data analysis methods. It also introduces the design and application of Bootstrap, a commonly used statistical software in pharmaceutical companies. Furthermore, the
study conducts data processing, analysis, and result comparison using both traditional statistical methods and Bootstrap statistical software based on the research data provided by the case company.
In pharmaceutical research, conducting in vitro dissolution profile comparison tests primarily aims to predict the pharmacokinetics outcomes of drugs in vivo bioequivalence trials.
Based on research findings, the application of the statistical software Bootstrap has been shown
to address the issue of large coefficients of variation resulting from data processing using traditional statistical methods, especially in cases with small sample sizes, non-normal distribution, or the presence of extreme values. This statistical approach not only increases the reliability of the data but also effectively resolves the differences between sample data and population data. As a result, it has become an accepted statistical method by many pharmaceutical research companies and regulatory authorities. Utilizing appropriate data analysis methods can significantly enhance the drug development process, increase market competitiveness, and reduce the risk of failure | en_US |