RWD Sources – How the Genesis of Your Data Determines What Questions You Can Answer.
When considering sources of RWD, it is important to consider more than just the number of available patients. Recently released guidance from the FDA encourages researchers to build accurate, complete and traceable real-world datasets. Combining data from structured and unstructured electronic health record data, closed claims, and other sources is essential to building the patient journey.
In our October Community Forum, we will explore two different angles of RWD sourcing from the provider’s point of view:
- Tim (Verantos) will share with us novel insights into unstructured data and examples of the value that can be leveraged from such data.
- Matt (Azimuth) will share with us details and example analyses of a unique research data source derived from linking claims and EHR data hosted by the Department of Defense network.
Come and join us for what promises to be another very interesting Community Forum!
This Forum will be taking place over Zoom on 24 October at 14:00-15:00 (BST) / 9:00-10:00 (EDT).
| PHUSE collaborations are organised into a number of specialist Working Groups, each with a broad topic area. The Working Groups have specific projects designed to achieve a set of particular objectives. This page will highlight the latest news and information from our projects. Participation is open to anyone who wants to contribute and if you would like to get involved, please email workinggroups@phuse.global. |
| Community Forum: Responsive Regulation of AI in Drug Development |
|---|
Responsive Regulation of AI in Drug Development The use of artificial intelligence (AI), including machine learning (ML), technologies across all stages of the drug product life cycle may accelerate the delivery of safe and effective high-quality drugs. As this data-driven technology continues to rapidly evolve across the landscape of drug development, a responsive regulatory approach may be warranted to calibrate the requirements needed to meet safety and evidentiary standards. This responsive regulatory approach can be based on an assessment of model risk, which is estimated by examining AI models’ influence on regulatory decision-making and the potential consequences of wrong decisions if the model is inaccurate. This responsive regulatory approach is rooted in an in-depth understanding of the specific application context and calibrates regulatory requirements in accordance with model risk. Principles of trustworthy and responsible AI serve as the foundation for responsive policy development and provide valuable considerations for both AI tool developers and regulators. It is important to consider ways to continue to engage with all interested parties to remain responsive to the changing technological landscape. Scientific discussion around continuing our responsive risk-based regulation, our collaborative efforts across the AI ecosystem (i.e. academia, industry, biotech), and advancing regulatory science in this area, without adding unnecessary burden to developers or regulators, is warranted. This Forum will be taking place over Zoom on 21 November at 14:00-15:30 (BSTGMT) / 9:00-10:30 (EDT). |
| Data Transparency Winter Event 2025 |
Call for Speakers is officially open for the Data Transparency Winter Event 2025! Taking place virtually 4-6 February, this event presents an incredible opportunity to showcase your ideas, share insight and engage with a vibrant community dedicated to advancing data transparency in the industry. For the chance to make a lasting impact, within a diverse network of like-minded individuals, submit your 150-word abstract before 15 November 2024. |
| Announcement - PHUSE/FDA CSS 2025 |
In its 14th year, the PHUSE/FDA Computational Science Symposium (CSS) will be expanding its global reach! In addition to Silver Spring, Maryland, we will be running a simultaneous event in Utrecht, the Netherlands! Mark Your Calendars! The US event will be in Silver Spring, Maryland 19-21 May, and the EU event will be in Utrecht, the Netherlands 20-21 May. Please visit the PHUSE website for more information. |
The Management of ODS Regulatory Referenced Deliverables project within the Optimizing the Use of Data Standards Working Group has provided an update to two of its regulatory-referenced deliverables, the ARDG Template and the cSDRG Template. You can learn more about this project and view the previous templates for the referenced deliverables here. Please provide your comments by emailing workinggroups@phuse.global. Closing date for comments: 30 October. |
The Nonclinical Topics Working Group has just formed a new project titled Developing Predictive Models to Facilitate Interpretation of Toxicology Study Results which is now calling for volunteers. A computational pipeline to build models to predict target organs of toxicity from SEND datasets has been developed and published on GitHub under PHUSE. Project team members will evaluate the feasibility and performance of this pipeline when run on data from within their organisations. The pipeline will be updated to improve compatibility with different database systems, and efforts will be made to improve its performance across disparate data sources. Additional study interpretations – e.g. adversity of findings, NOAEL determination, clinical translatability, structure activity relationship – will be explored for development of predictive models. Successful modeling approaches will be published in peer-reviewed scientific journal articles. If you would like to volunteer or learn more about this project, email workinggroups@phuse.global. Closing date: 24 October |
The Teal Enhancements for Cross-Industry Adoption, a new project within the Data Visualisation & Open Source Technology Working Group is now calling for volunteers. Research: Conduct a detailed analysis of the current teal framework and identify areas where flexibility can be introduced. A Proof-of-Concept will be provided after research. Development: Create new functionalities that allow for the re-formatting, post-processing, and decoration of outputs generated by existing teal modules.Testing: Develop test cases to ensure the new functionalities are compatible with existing modules and meet the customisation needs of different companies.Documentation: Update the framework's documentation to include instructions on how to use the new features.Training & Support: Provide training and ongoing support to users within the pharma industry to facilitate the adoption of the enhanced teal framework. If you would like to volunteer or learn more about this project, email workinggroups@phuse.global. Closing date: 27 October |
The Risk Based Quality Management Working Group have just launched a new project titled Enhancing the Clinical Trial Risk Assessment Process which is now calling for volunteers. This project proposes beginning this project by identifying CtQ factors via a risk assessment process (characterising risk including assessment and mitigation/risk reduction strategies), which would include identifying trial-level QTLs that support CtQ factors. If you would like to volunteer or learn more about this project, email workinggroups@phuse.global. Closing date: 1 November |
The Missing Data Imputation in RWD Exploration of Multiple Techniques on Open-Source Data a new project within the Real World Evidence Working Group is now calling for volunteers. The aim of this project is to publish a white paper which shall explore multiple models available for missing data imputation and share with the wider group the potential of each model and its efficiency in dealing with different kinds of missing data. The model efficiency is compared using a single open-source simulated dataset. If you would like to volunteer or learn more about this project, email workinggroups@phuse.global. Closing date: 1 November |
The Best Practices in Data Standards Implementation Governance project within the Optimizing the Use of Data Standards Working Group has published a new white paper. This white paper presents the results of the survey along with feedback from informal discussions at PHUSE’s Computational Science Symposium (CSS) sessions in 2022 and 2023. The data and observations shared are intended to inform industry and identify further projects for exploration while also encouraging industry collaboration for areas which are found to be the most challenging. |
The SDTM ADaM Implementation FAQ project within the Optimizing the Use of Data Standards Working Group has published a new FAQ! The question they have answered is 'When to Submit an eCTD or Standardised Data Sample to the FDA'.You can view this question and the team's response via the Data Submission page. You can see all the FAQ's this project has answered so far via here. Do you have a SDTM ADaM Implementation FAQ question? You can send your questions to the team by emailing workinggroups@phuse.global. |
Working Groups Report: Includes project updates, recent and upcoming deliverables and future plans for each Working Group. | |
Monthly Mailings: The monthly newsletter. Here you will find a full update from each month of the year, easily accessible and divided into key areas of PHUSE. | |
PHUSE Blogs: Fancy a quick read? A blog is a perfect way to catch up on all things Working Groups. Get the lowdown on the latest events from across the globe and stay updated on industry topics brought to you by industry professionals. |
Initiate and lead a new project under the PHUSE Working Groups umbrella. The new project must address problems of significant relevance to computational science related to drug, biological and device development and must meet all of the guidelines for projects within the collaboration, including the following mandatory requirements:
New projects can be submitted anytime during the year, click here to submit. |