This pattern soon emerged after talking to the director of clinical data at events in Basel, New York, London and Copenhagen. Despite being thousands of miles apart, the focus on simplified and standardized data is clear. This common point is the result of increased complexity in clinical landscapes, with more and more companies utilizing practical innovations to simplify research execution.
The FDA recently issued guidance to encourage actual clinical trials for specific situations. By adding design elements to studies similar to conventional clinical practice, more patients, including patients from different populations, can access participation, register and contribute to clinical research.
Clinical leaders’ insights help to move forward to five trends toward practical innovation that will impact the future of clinical data management.
Prioritize your strategy
Although regulators have been recommending risk-based models for some time, many organizations are still seeking to fully review the security of model and source data verification (SDV). However, clinical leaders believe that risk-based quality management (RBQM) can quickly realize value in trials and take action to gain benefits. Some are already adding advanced solutions and highly skilled clinical data managers to accelerate the transition from data inspection to data science.
A global biopharmaceutical is combining risk-based examinations with technology to enable Clinical Research Assistant (CRA) to see the requirements of SDV without downloading reports or applying macros to spreadsheets. This can eliminate thousands of patients’ visits and hours of clinical data working.
An emerging approach based on risk is to use historical trend data for proactive problem management. Data analysis can show trends and how they develop and determine how problems are solved. This requires early input and alignment across functions and teams, as well as mitigation plans and procedures to manage risks. The goal is that when a new trial begins, the team will have access to audit and monitor data to identify inconsistencies and share signals.
Adopting a risk-based approach has the potential to provide measurable value for clinical trials. Positive problem detection can provide higher data quality, centralized data review can improve resource efficiency, and faster database lock-in times can accelerate the market.
Moving from data management to data science
The Association for Clinical Data Management (SCDM) notes that biopharmaceutical companies need to adopt more scientific clinical data approaches and transition clinical teams from managing data to scientifically applied data. As companies leverage automation, the data manager role is shifting from collecting and cleaning to providing insights and predicting results. However, the shift to data science presents challenges, especially the need to clean and coordinate data.
To enable data science, data management and other features such as clinical operations and drug daemons can be used together to simplify data flow. Especially with the growing number of data sources in trials, data managers can prioritize high-value activities to drive the scope of data science, which can have a significant impact on productivity.
Despite the ongoing transition from data management to data science, while maintaining the highest quality levels, clear KPI and performance goals are needed to be established at the beginning and end of each study. There are other development areas, including optimizing patient data flow, integrating data quality and audits using AI, ML and advanced analytics, and enabling digital and automated analytics to enable data science. Embracing this shift will require data managers to focus more on analytics and interpretation than completing the checklist.
Go all out to intelligent automation
Smart Automation seeks the best approach (whether it is AI, rules-based or otherwise) to optimize efficiency and manage the risk of each use case. Its focus is just to provide value, not to generate hype.
By adopting a rule-based automation approach, no human supervision is required. More and more companies are investing in automation to increase capabilities that can quickly generate revenue while building foundations. This can include feedback loops and integration of high-speed APIs that can be applied in the future. Another example is using rule-based automation to speed up data cleaning, conversion, and reporting. This approach helps increase trust in data and reduces manual work for data managers.
Today, biopharmaceuticals are using automation for data cleaning to speed up database lock-in time. Rule-based automation provides the most significant cost and efficiency gains in the medium term. In the long run, many leaders believe that Genai will be the co-pilot in clinical research. AI may make tips on suggesting to determine fraud or predict compliance. Building a clean data base powered by intelligent automation will improve quality and provide the useful data needed to power AI use cases in the future.
Focusing MDR and data standards on important things
Using a metadata repository-driven solution (MDR) solution, the clinical data team combines research design, data collection, analysis, and submission. As electronic data capture (EDC) becomes the primary application used in data collection, it is increasingly believed that all (or nearly all) data collection metadata should be stored in a system to automate research construction.
The fact is that collecting data in repositories has proven to be challenging for organizations that extend metadata management. This may be due to the reliance on spreadsheets.
It turns out that an emerging strategy is to focus MDR on what’s important: Research design metadata is common, shared and critical for data management and statistics. For example, when evaluating common study design metadata between data collection and data analysis, there are 25 attributes (more than 1,000) of downstream programming and analysis of EDC metadata.
Alternatively, the research design can start with MDR, and during the data collection phase, the team confirms the standardized data definition. This allows data management and statistics to work in parallel to provide the same definition. Moving the method from comprehensive MDR to simplified standards can speed up the path from research build to database locks. Taking this more pragmatic approach means that clinical teams can deliver value faster.
Make patient selective reality
Only 3% of doctors and patients in the United States have participated in clinical trials of new therapies. The result of low participation is that almost 80% of studies fail to meet the enrollment schedule, resulting in expensive delays.
The rise of decentralized clinical trials (DCTs) is discussed and debated around the occurrence of trials, rather than the impact on overall trial experiences such as patients, study locations, regulators, data managers, etc. The industry is shifting. Clinical leaders do not focus on patient selectivity, rather than on location. An important development is because dispersed tools are a standard way of operation in which patients decide how to participate in research (whether at home, on-site or in the clinic) in a timely and effective manner.
Sponsors are considering a more comprehensive approach to trial experience to ensure patients are not overwhelmed by the number of devices and tools. Establishing a clear “Bring Your Own Equipment” (BYOD) policy can facilitate while maintaining data quality and safety during trials.
The clinical data leader also began to reduce the burden on patients by asking study participants for less data. This is established during the protocol design phase. First, think about the tangible benefits of patients before introducing new applications (e.g., Econent) and use investigations to gain a deeper understanding of the patient experience and identify improvements.
Pragmatically simplify and standardize clinical trials
As clinical trials become more and more complex, life sciences are increasingly adopting practical innovations. Taking a pragmatic approach means a flexible clinical team will go beyond legacy practices without risking quality. To do this effectively, the participation of the research website will be more customized to understand and support their goals in treating patients in the process of making data flow a reality.
Prioritizing risk-based management, data science, intelligent automation, standards and patient selectivity is critical to the industry keeping up with market changes. In certain situations, the FDA guidelines that encourage “practical trials” in certain situations are moving in the right direction. Sponsors and CROs can begin designing elements that closely reflect standard clinical practice, preparing for the future of more patients joining and participating in clinical research.
Photo: Deidre Blackman, Getty Images
This article passed Mixed Influencer program. Anyone can post a view on MedCity News' healthcare business and innovation through MedCity Remacence. Click here to learn how.
