Working Group Events |
|---|
Working Groups have held |
4 events this year! From Community Forums to webinars |
and the bi-annual Data Transparency Events |
, with more to come.Data Transparency Virtual events had a |
The Open Source Technology in Clinical Data Analysis (OSTCDA) project was set up with the aim to create a manuscript on the integration of open-source software solutions for clinical data management, analysis and reporting.
A significant amount of time and energy has been invested in recent years exploring the desirability (do we want it?), feasibility (can we do it?), and viability (is it worth it?) of integrating open source solutions into our clinical data pipelines which transform source data into clinical study reports and submission data packages. In this October edition of the Open Source Open Forums, we will update on the status of this initiative and continue to hear from you on what we’ve missed so far.When this manuscript is complete, we hope to put to rest some of the burning questions that we believe we now know the answers to. This will allow industry, and all the passionate people in it, to look ahead and start tackling the next horizon of challenges related to using open source solutions for clinical data pipelines. We hope you will contribute your expertise to this effort.
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.
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.
Recommendations for Adverse Event Collection and Treatment Emergent Definition
In 2019, the PHUSE Best Practices for Data Collection Initiatives project team, in conjunction with the Analysis and Display of Safety Analytics project team, conducted a survey (link) to study the variation in the collection and definition of treatment emergent adverse events (TEAEs) in clinical studies. It noted the need to pursue additional research to further harmonise industry practices. The PHUSE Adverse Event Collection Recommendations and the Treatment Emergent Definitions Recommendations project teams were formed to develop recommendations to reduce the implementation variability.
(insert number) attendees during its Winter Event. (insert min summery) |
Insert DT graphic
Community Forums |
|---|
Real World Evidence: RWD for Regulatory Decision-Making: Learnings from Use Cases and Demonstration Projects FDA guidance is clear that real world data (RWD) may be acceptable for regulatory approval when a randomised controlled trial is not feasible and the validity and trustworthiness of the real world study results are clearly demonstrated. To provide more operationalised guidance for meeting these standards, the presenters will share learnings from FDA use cases and ongoing demonstration projects. Emerging Trends & Innovation: Responsible AI in a Healthcare System As the use of artificial intelligence (AI) moves from being a curiosity to a necessity, it is clear that the benefit obtained from using AI models to prioritise care interventions is an interplay of the model’s performance, the capacity to intervene, and the benefit/harm profile of the intervention. After a brief review of the kinds of use cases that AI can serve across multiple medical specialties, we will discuss Stanford Healthcare’s efforts to shape the adoption of health AI tools to be useful, reliable and fair so that they lead to cost-effective solutions that meet healthcare’s needs. |
Webinars |
|---|
Risk Base Quality Management: Make the Most out of Innovation and Ensure it’s Done Right! Join the webinar to learn why change is not only an idea but a necessity. We will explore where old habits need to be retired and where new initiatives have proven to increase efficiency and reduce cost without impacting on quality. This Webinar took place virtually on 20 February 2025 |