Happy New Year! As we look ahead to future successes and the new advancements in drug development that 2019 will bring, we are taking a moment to reflect on the topics that resonated most with our community on the Cytel blog in 2018. While these 6 most popular blogs encompass a variety of topics from across the data science, statistics, and statistical programming space, they all have in common a focus on innovative practices and application of statistical, data management, and data science excellence to achieve better outcomes in drug development.
Feature selection using genetic algorithm by Munshi Imran Hossain
The explosion in the availability of big data has made complex prediction models a conspicuous reality of our times. Predictive models are increasingly used to derive inference from data, and most of these models use a set of input variables, called features, to predict the output on a variable of interest. The available data can provide a large number of features, but generally, it’s preferable to use a small number of really relevant features in a model. Choosing the subset of features that will result in a model with optimum performance is the problem of feature selection. One of the popular methods for searching through the feature space is the genetic algorithm and Munshi Imran Hossain walks us through a use case in this very popular blog from 2018.
Exploring Differences Between Pinnacle 21 Community and Enterprise versions for CDISC Compliance by Angelo Tinazzi
At the CDISC EU Interchange in Berlin, Angelo Tinazzi, Director of Clinical Data Standards and Submissions at Cytel, showcased a popular poster presentation analyzing the differences between the Pinnacle 21 enterprise (P21e) and community versions. This blog shares access to the poster, and its critical review of the added value of the Enterprise commercial version, based on Angelo’s experience of introducing and using the software within Cytel.
How Can We Tackle Heterogeneity in Meta-Analysis? By Anwaya Nirphirake
The questions in clinical research are typically studied more than once independently by different researchers. Literature review is used for summarizing the results of these studies and strengthening the evidence. Systematic review is a type of literature review that collects and critically analyzes multiple research studies or papers that answer the same question. If the results of these multiple studies are diverse and conflicting then the clinical decision-making becomes difficult. To overcome this problem meta-analysis is used. Meta-analysis is a statistical procedure for combining the results of studies that are included in systematic review. While meta-analysis is a powerful technique, it may give misleading results due to issues like improper selection of studies, publication bias, and heterogeneity among studies. In this blog, Anwaya discusses strategies to overcome the problem of heterogeneity.
Life in Programming: Interview with Ajay Sathe
Ajay Sathe, CEO of Cytel’s India Operations is a well known figure in the global statistical programming community thanks to his dedication to both the technical field and mentorship of new talent in the industry. In this blog we chat with him about his work, the important role of the PhUSE association in the industry, and what excites him most about work in the biopharma sector. It’s essential reading for any statistical programmer looking for career inspiration as we set sail into 2019!
Interview with Stephen Senn: 70 Years and Still Here: The Randomized Clinical Trial and its Critics
We were fortunate to have eminent biostatistician Stephen Senn join us as a keynote speaker at our very successful EUGM in November in Darmstadt. Before the symposium, we sat down with Stephen for a wide-ranging discussion about his career in statistics, his advice for early career statisticians, his upcoming research, and the topic of his presentation at the East User Group Meeting “70 Years Old and Still Here: the Randomized Clinical Trial and its Critics”. Whether you are looking for one simple message to counteract what critics of the randomized clinical trial may say, or seeking advice on career development, this interview will give plenty of food for thought.
Infographic: 5 Key Interactions of Data Management and Statistics
At Cytel we know the positive impact that closely aligned data management and statistics functions have on the operational execution of a clinical trial. This infographic illustrates the critical interactions that need to take place between data management and statistics groups to help reduce duplication, and ensure efficiency and data quality.
What topics would you like us to write on in 2019?
We'd love to get your views on what topics you would most like to learn about from Cytel in 2019. Click the button below and complete a short form to get your voice heard and let our team know which topics are most pressing for you this year.