ASSESSMENT AND ASSURANCE OF DATA AND SYNTHETIC DATA FOR REGULATORY DECISION SUPPORT
INSAFEDARE
Assessment and Assurance of Data and Synthetic Data
for Regulatory Decision Support
INSAFEDARE Project
The aim of INSAFEDARE is to provide advanced technologies that address the challenges and exploit the opportunities surrounding real world and synthetic data-driven validation of medical devices in support of cost-effective and high assurance regulatory decision-making. INSAFEDARE is investigating how synthetic datasets can be used to establish assurance in advance of formal certification processes, thereby reducing risks for device developers and enabling more efficient resource usage by medical regulatory bodies. The project will develop technologies for the discovery, integration, and query of multiple datasets, as well as support for the sustainable, dynamic, and through-life surveillance of devices, capturing the impact of new evidence offered by newly published datasets.
Assurance of Large Data-based Validations
INSAFEDARE aims to comprehensively analyse the existing regulatory framework concerning digital health innovation, identifying its gaps and limitations. The primary objective is to enhance understanding of regulatory use cases driven by advancements in digital health. Additionally, we intend to develop a robust safety and quality assurance framework specifically tailored for data used in regulatory decision-making processes and clinical studies. Our goal is to define a forward-thinking hybrid framework that integrates real-world and synthetic data and aligns with current regulatory and legal obligations. By addressing these objectives, we aspire to contribute to the evolution of regulatory practices in the dynamic landscape of digital health innovation.
Advanced Research and Technology Development
INSAFEDARE includes deep exploration of Machine Learning methodologies for crafting privacy oriented synthetic datasets. Our objectives include providing explicit guidance on assuring the integrity of Big Data and Machine Learning-driven digital health interventions, emphasizing the incorporation of statistical evidence. Additionally, INSAFEDARE aims to create a reliable heritage query tool capable of seamlessly integrating diverse datasets. Furthermore, an analysis will be performed to assess the compatibility of data-centric approaches with privacy, FAIR (Findable, Accessible, Interoperable, and Reusable), and open science principles, ensuring adherence to regulatory standards. By achieving these goals, we aspire to fortify the ethical and effective application of data-driven technologies in the realm of digital health.
Delivery to Practice
Our primary focus is on cultivating a Co-Production based Publicly Available Guidance for assuring and validating data-driven applications. This initiative involves continuous development and maintenance to ensure relevance and accuracy. Simultaneously, INSAFEDARE will create a comprehensive syllabus and training materials dedicated to the assurance of synthetic and real-world data within regulatory frameworks. The project will also develop specialized tools that facilitate efficient, sustainable, and through-life regulatory support for digital health innovations and interventions. The combination of these objectives collectively strive to establish a robust foundation for the effective and ethical integration of data-driven technologies in the evolving landscape of healthcare.
Latest Project News
