Clinical trials are becoming increasingly expensive, time-consuming and complex, prompting sponsors to seek more efficient ways to conduct their business. Risk-based quality management (RBQM) answers this call.
It’s a data-driven approach that accelerates the drug development path without compromising safety—and one that’s enhanced by the use of technologies like artificial intelligence (AI).
AI, ML and Healthcare
Machine learning (ML) uses computer algorithms to achieve AI, i.e. computer learning and mimicking human cognitive skills. ML models are designed to extract knowledge from large data sets and use that knowledge to make predictions about new or unseen data. It is particularly well-suited to tasks that cannot be solved with simple rule-based solutions, meaning it naturally applies to healthcare where solutions rely on complex processes.
As the healthcare sector continues on its path to digital transformation, it is generating massive amounts of data, driving growing interest in health-related machine learning applications.
Deep learning, which uses large neural networks to process complex structured and unstructured data, for example, has recently been used to scanning electronic health records to monitor medical devices and to predicts kidney damage. Computer vision, another application of deep learning, is streamlining microbiological testing and breast cancer screening. ML is also being implemented in the clinical trial arena, including in the application of RBQM.
Recommended by ICH E6 (R3), RBQM is a way to identify, visualize, manage and document the risks that could affect the outcome of a clinical trial. Instead of the resource-intensive process of monitoring, recording, and verifying every trial parameter, it allows investigators to follow the most critical safety and efficacy data.
It works by replacing baseline data verification (SDV) with powerful methods to detect risks in clinical trials. Centralized statistical monitoring uses statistical algorithms to highlight atypical data patterns or risk signals in near real-time. It allows sponsors and CROs to identify, investigate and correct problems such as fraud, careless data entry, or problems with study or study equipment before they can affect the integrity of the trial.
The result is more efficient studies that protect participant safety and ensure data integrity.
ML and RBQM: Perfect data-driven partners
Clinical trial data are so numerous and complex that making sense of them can be a daunting challenge for the human mind. Yet this is where deep learning models, which learn from complex and massive amounts of data, excel.
Deep learning can power RBQM tools, extracting and analyzing information to highlight relevant insights. The modality has the flexibility to work with different data formats, workflows and processes, meaning it can extract text from research documents, clinical notes and research reports and combine it with clinical data, for example. It can also use what it learns from previous studies in new programs. It can extract knowledge from external clinical databases or clinical corpora to inject medical knowledge into model predictions.
Moreover, ML models are not static. With the addition of human-in-the-loop approaches that allow clinicians to highlight areas of data to focus on and suggest actions, they are continually learning and refining their insights.
The possibilities are almost endless. But to succeed, anyone embarking on an ML-driven RBQM journey must clearly define their goal and what they expect their solution to discover. This requires strong domain understanding and industry collaboration.
RBQM Advanced Training Opportunities
From a practical perspective, ML-driven RBQM can help research teams reduce their manual review efforts and provide them with meaningful and targeted data insights. It can automate key tasks, such as risk grouping and setting up centralized trial monitoring, and extract valuable insights from past trials, enabling sponsors and CROs to efficiently plan, manage and document their trials.
It can also make surveying more efficient by distinguishing between different types of risk signals. RBQM systems raise a risk flag or alert when data patterns indicate a potential problem. These are then used to monitor and track investigations that determine if corrective action is needed, resulting in multiple free text entries from different users documenting their findings. But deep learning models can analyze this text data and flag signals that represent a real problem. It allows teams to prioritize the review of alerts and ensure the most effective follow-up and documentation of findings.
The industry-leading RBQM platforms handle a large volume and variety of data from different organizations, meaning there are always new opportunities to develop scalable, robust ML solutions. The sector, for example, is currently working to extend machine learning capabilities to data management and clinical review. The goal is to make time- and resource-intensive data management tasks such as data cleaning, medical and AE coding, and raw clinical data mapping into SDTM more efficient.
Over the years, the pharmaceutical industry has built a gold mine of data on these activities. This information can now be used to train ML, especially deep learning models, to present pharma teams with AI-driven proposals that can be reviewed, then accepted or rejected. Clinical review relies primarily on clinical experience and as such will benefit greatly from extensive training that can mine data for medical knowledge acquisition and learn from complex human decision-making processes.
No matter the project or application, such approaches have one ambition – to use ML to present research teams with the right insights to make better and faster decisions, optimize processes and free up time to focus on the most important.
The key features of ML have the power to significantly improve the way we monitor and manage clinical trials by empowering RBQM teams, data managers and clinical reviewers.
They are driving a revolution in research that promises to enable more efficient development of life-changing drugs – but only if we ensure the careful design needed to deliver meaningful insights.
Photo: mrspopman, Getty Images