Sponsors and contract research organizations (CROs) must extract greater value from the data they collect if they plan to use technologies such as artificial intelligence (AI) or machine learning (ML). Why are we changing, and why is it important? It’s not easy, but if we remain in control, we must find the strength to move forward. ‘Starting a new path is scary, but with every step we take, we realize how dangerous it was to remain.’ – Roberto Benigni.
For data management and other departments, we are witnessing the evolution of AI across the world. We must be practical and cautious with regulations. These tools can be very useful: they give us real-time access to information, provide simultaneous translations, and can answer virtually any question we ask. They’re helpful and can support our daily work if we review and critically assess the information they provide.
Automating Processes
We can also automate processes not only within Data Management (DM), but across many other areas of the study. In Safety, for example, this includes narratives and coding; in Clinical, this includes tasks like eTMF quality checks. DM is emerging as a highly sophisticated area that could boost productivity by 15%, drive innovation, support critical decision-making, enhance standardization, increase efficiency, and foster harmonization. In short, leveraging AI and ML technology for data management simplify processes, save time, and improve quality.
Many companies are beginning to adopt AI for data standardization, automating the normalization of terms to ensure data remains harmonized across different therapeutic areas. This will improve consistency and support regulatory submissions. Ultimately, it allows us to ensure large-scale data quality and promotes long-term efficiency in clinical trials by reducing manual processes.
There is growing recognition that the industry needs to automate data flow. Automation, including automatic change detection, edit checks, and queries, has reduced manual processes. Data is now reviewed without spreadsheet trackers, and both data managers and vendors can review queries within the same system.
What is the Goal?
The goal is to envision an integrated data-cleaning model, where cross-functional teams can work on a single platform, view the same data, and use it to make decisions and track activities all within an integrated data quality plan. This enables a unified approach to cleaning, reviewing, and reconciling data, resulting in final data that is clean and accurate. This shift can drive clinical data management toward progressive delivery of submission-ready evidence, allowing all stakeholders to access the most relevant data. Simplifying will bring greater efficiency, acknowledging that perfection doesn't exist, which is why it's always crucial to maintain KPIs for the data.
Several EDC platforms already offer this option to enable the integration of all vendor data into a single platform.
Technology in Data Management
Lastly, while technology is essential in data management, we must assess its long-term impact on organizations. Technology should not only address immediate needs but also support future growth and adaptability. It’s important to evaluate both the benefits and the costs of implementation.
In conclusion, technology is a critical enabler of modern data management and governance frameworks. It offers solutions that improve data accuracy, security, and compliance while supporting scalability and integration. However, it is also important to strike a balance between various factors and to address challenges such as legacy systems, data silos, and cultural resistance, which are essential for successful implementation
Author:
Maria Agueda Del Cura
Senior Director, Data Management
Linical