We are at a tipping point in the adoption of Clinical Research 2.0. The evolution of risk-based quality management (RBQM), wider adoption of artificial intelligence (AI) and regulatory updates have set the scene for a new holistic approach to data management.
We are in a position where we have the computer power to build this bright future. Now we need the people power.
In 2023, the Tufts Center for the Study of Drug Development, in collaboration with CluePoints and PwC, shared data from an industry- wide survey on RBQM adoption and attitudes. The top perceived RBQM adoption challenge (69%) was a lack of cross-functional awareness. This demonstrates the need for education around the benefits of new techniques, technologies, and processes. Clinical Research 2.0 relies on the industry’s ability to understand, accept and manage change throughout 2024 and beyond.
Driving RBQM Adoption
Last year marked a major milestone for RBQM with the publication of the final draft version of ICH E6 (R3). It ties together the concepts of quality by design (QbD) and RBQM to create a holistic, end-to-end clinical trial methodology.
Over the past 12 months we have seen the industry move from “talking the talk” to “walking the walk” regarding the application of AI and machine learning techniques in Clinical Development.
If we look at the example of AI- assisted medical coding, deep learning (DL) natural language processing (NLP) models can now provide researchers with the correct corresponding dictionary term in seconds, with over 90% accuracy. In risk detection, NLP algorithms can screen reams of free text, entered by users during signal management, and flag signals that either lack the required documentation, or for which the root cause selected by the user is unreliable. This allows study teams to prioritize signal review and ensure effective follow-up and documentation of findings.
Pharmaceutical and biotech companies are also building large language models (LLMs) to assist in tasks such as writing protocols and designing risk assessments. Such applications can shave months off study set up timelines, thus accelerating the overall development pathway.
The Clinical Research 2.0 Toolkit New techniques and technologies are producing a paradigm shift that includes replacing 100% source data verification (SDV) with centralized monitoring and data analytics, using RBQM to focus on critical to success data, and utilizing AI to drive efficiency and quality.
In the future, generative AI could be used to simulate control groups, or “synthetic arms”. This could significantly streamline study initiation, particularly in indications where a control group is hard to recruit or retain.
Andy Cooper, CEO of CluePoints, says new techniques and technologies are presenting us with opportunities to streamline data management.
To genuinely seize the opportunities that AI, greater RBQM adoption and the developments of Clinical Research 2.0 offer, organizations must promote cross-sector collaboration and education, and raise awareness of the benefits of a holistic approach to data management.
In an understandably conservative industry, where patient safety is the priority, the adoption of new technology and processes can be slow, particularly if their effectiveness and value are poorly understood. So, we must educate the market on the benefits of these tools and the advantages to both the industry and patients alike.
To unlock the true potential, we need to collaborate with regulators to develop more guidance on the use of technology, such as AI, to aid adoption. Only then can we truly seize the opportunities offered by the Clinical Research 2.0 toolkit.
