Cytel Blog

As a part of Cytel’s "New Horizons Webinar Series", Alind Gupta, Senior Data Scientist, presents case studies from his research on applying machine learning for predictive analysis and evidence generation.

The biopharmaceutical and healthcare industries now collect more data than ever before due to advances in the variety of information sources combined with the ability to store vast quantities of diverse data. Sophisticated machine learning (ML) and AI techniques allow us to access and analyze any combination of a multitude of data sources. The way that traditional controlled sources are viewed is being adapted in light of new evidence that emerges from real-world data. In his presentation, Alind introduces us to the concept of ML and Causal Inference and discusses case studies from randomized clinical trials and real-world data.

Click the button to register for the on demand webinar.

Platform trials are a new type of clinical trials where multiple interventions can be evaluated simultaneously against a common control group within a single master protocol. Platform trial designs are an extension of adaptive trial designs that are sometimes referred to as a multi-arm, multi-stage (MAMS) design, as multiple interventions (‘‘multi-arm’’) undergoing multiple interim evaluations (‘‘multi-stage’’) are part of the design features.

This autumn Cytel has been holding a number of webinars on Platform Trials, ranging from a discussion with Cyrus Mehta on statistical innovations to incentivize more sponsors to consider platform trials, to next week's event with Jason Connor (Confluence) on the use of Bayesian methods for these innovative trial designs. 

In a recent webinar Jay Park, Director of Trials Research for Cytel in Canada, presented a webinar to review the concept of platform trials and discuss important design considerations for platform trials. Jay is the author of several leading papers on Platform Trials, including one in CA: A Cancer Journal for Clinicians, the journal with the world's highest impact factor. He has also produced a complimentary primer on the subject which you can download here.

Continue reading this blog to get a summary of his talk. Click the button to access the on demand webinar.

An extraordinary amount of global research is underway as the COVID-19 pandemic continues to evolve and spread throughout the world. There are over 800 registered global clinical trials taking place to develop life-saving treatments and vaccines for patients. The World Health Organization is also facilitating collaboration and accelerated efforts on an unprecedented scale. In these difficult times, sponsors must utilize innovative tools and approaches to design their clinical trials in order to provide promising results for all patient populations as quickly and efficiently as possible. 

A successful virtual panel discussion was conducted by Cytel on the ongoing COVID-19 Trials, on April 15. For the second complimentary virtual panel discussion held on April 23, Cytel partnered with Certara, to present, “COVID-19: Trials, Designs and Tools for Promising Results”. It began with challenges faced by clinicians and drug developers, followed by examples of tools and trial designs currently being used to help sponsors of COVID-19 trials. Continue reading for a summary of the panel discussion.

Get free access to COVID-19 Panel slides and recording.

In our previous blog, we spoke with Alind Gupta, who works as a Machine Learning Researcher at Cytel in Canada. The interview gives you a deep dive into black-box models and transparent machine learning, and how the latter is becoming more important in clinical research today.

On March 21, Cytel conducted a webinar with Alind on, “Transparent Machine Learning in Oncology”. Alind presented our continuing work in immuno-oncology using Bayesian network models for predicting safety and survival outcomes, extrapolating from limited follow-up data and validating with external real-world data for key subgroups. Continue reading for key highlights from the webinar.

Register now to get free access to webinar slides and recording.

Cytel is hosting a webinar on Transparent Machine Learning in Oncology, on April 21, 2020. Our speaker, Alind Gupta, Machine Learning specialist, will provide insights on a particular transparent ML method called Bayesian networks, and how we have been using it for HEOR and other real world applications in oncology trials. As the adoption of machine learning is on the rise, we speak to Alind about the differences between black-box models and transparent machine learning, and how the latter is becoming more important in clinical research today. Alind also speaks about the application of ML on real-world data and how it is going to evolve in the coming years.

Machine learning (ML) aims to discover patterns from data that can be used for prediction, but the use of “black-box” ML models in healthcare research and decision-making has been limited, due to clinical liability and lack of trust from stakeholders. FDA guidelines for ML-based devices mandate transparency to assure continual safety and efficiency as notable recent failures have prompted increasing ML research into bias, fairness and causality. This has ramifications for all therapeutic areas but particularly within oncology.

Since 1953, when the discovery of the structure of DNA was made, we have seen great advancements in genomics. Particularly, in the last few years, the industry has seen a rapid rate of adoption in biomarkers and how they can be used to improve biomedical interventions. Trial investigators have been showing interest in biomarker-guided trials such as basket trials and umbrella trials, developed under the master protocol framework. As a result, we have been seeing a rapid rate of adoption of these innovative trial methods.

In our previous blog, we spoke with Jay Park, Director, Cytel, about the concept of master protocols, their importance and future growth potential. On March 19, Cytel conducted a webinar with Jay on “Key Design Considerations for Basket Trials and Umbrella Trials”. This webinar introduced two master protocol types and explored their extension to design in various contexts from the HIV epidemic in global health to expedited oncology trials. Continue reading for key highlights from the webinar .

Register now to get free access to webinar slides and recording.

Further regulatory guidance has been released concerning the implications of the Coronavirus disease (COVID-19) on clinical trials.

On March 25th the Biostatistics Working Party (BSWP) of the European Medicines Agency (EMA) Committee for Human Medicinal Products (CHMP) published a draft points to consider guidance document on the actions that sponsors of affected clinical trials should take to help ensure the integrity of their studies, and the interpretation of the study results, while safeguarding the safety of trial participants as a first priority.

On March 20th the European Commission, the European Medicines Agency (EMA) and the Heads of Medicines Agency (HMA) published new recommendations for sponsors on how to manage the conduct of clinical trials in the context of the COVID-19 pandemic. Extraordinary measures may need to be implemented and trials adjusted due to quarantine, limited access to hospitals, and healthcare professional focus on critical tasks. Here is a review of selected elements of the guidance, interpretations and recommendations.

The FDA issued a guidance yesterday on how the COVID-19 Pandemic may affect the conduct of clinical trials. Below are some key messages from the guidance along with some interpretations and recommendations.