Where do we stand with clinical trial digitalisation?

R&D
Human finger pushes touch screen

Digitalisation is happening all around us, including in tech-enabled clinical research and development. As researchers dive deeper into transformative science to create precision medicines, there are related clinical trial complexities to address and little room for inefficiencies. With the integration of tech-enabled solutions in recent years, R&D stakeholders have provided patient-centred, data-driven clinical trial outcomes with improved efficiency, in spite of growing drug development challenges.

Artificial intelligence, machine learning models, automation, connected devices, cloud data storage, intuitive study platforms, and other advances are allowing clinical trials to be future-ready from end-to-end, which benefits all involved. Below, we discuss key focus areas within digitalisation that R&D stakeholders are finding useful.

R&D technology trends snapshot

In clinical development, we are seeing interest in digitised trial design and operating models to:

  • Improve decision-making. Stakeholders are using digitised solutions and analytics to make informed decisions about asset identification, indication prioritisation, study design and planning, and patient enrolment.
  • Reduce burdens of participation. Telemedicine, wearables, sensors, and other devices allow patients to participate in trials offsite and reduce site staff burden.
  • Enhance data flow from collection through analysis. The volume and complexity of data is increasing as remote data collection (e.g., devices, electronic clinical outcomes assessment) and eSource technologies increase. Centralised automated data flow increases focus on holistic data review, allowing better oversight and monitoring of patients.
  • Streamline operational processes/collaboration while increasing sustainability. Automation is reducing manual administrative tasks, which improves trial efficiency and compliance and allows site teams to focus on clinical care responsibilities. Automated review of clinical data analytics and signals enables earlier risk identification. Further, the integration of automation and other advanced technologies creates more opportunities for sustainable trial practices.
  • Create stronger oversight and collaboration between R&D stakeholders with interoperable ecosystems. Improving integration of clinical systems is optimising clinical workflows, data sharing and collaboration between sponsors, researchers, sites, and CROs and enhancing trial and data oversight.

Let’s take a closer look at some of the benefits of trial digitalisation.

Digitised trial design and planning

Trial sponsors are eager to reduce the “white space”, the time needed to transition between clinical research phases, without compromising data quality. Engaging early with trial sponsors, ideally a year or more before study start-up activities, helps ensure they have the opportunity to make data-driven decisions about study design (e.g., eligibility criteria or endpoints) that can affect operational efficiency downstream. Noteworthy ways tech-enabled solutions are improving trial design and planning include:

  • Iterating trial design ideas to assess multiple scenarios and show sponsors the impact their design choices might have later. This provides early insight into potential operational risks and allows sponsors to make trade-offs. For example, technology might improve patient participation, but increase burdensome tasks and costs at sites. Analytics can uncover these potential risks so sponsors can make data-informed decisions.
  • Conducting and fine-tuning protocol analysis via advanced analytics and AI-driven algorithms before finalisation. This allows sponsors to compare their protocols to other protocols for similar phases, therapeutic areas, diseases, etc., and potentially reduce amendments and delays during trials. The ability to apply patient-centric insights from real-world data and other sources to analytics can also help predict successful recruitment and patient satisfaction. For example, an AI-driven algorithm can score protocol elements to quantify patient burden.
  • Relying on expansive, global real-world data and AI to thoughtfully build data-driven optimised enrolment strategies through advanced study planning and enrolment optimisation platforms. Historically, trial sponsors have used traditional statistical approaches to gauge and plan for enrolment rates and develop scenarios for trial planning. But real-world data and AI allow sponsors to quickly explore a range of scenarios, with models based on time and cost. As studies progress, real-time data supports plan revisions and new projections, helping study teams get ahead of potential challenges and course-correct as needed.

Digitised operating models for streamlined sustainable trial practices

Alongside trial sponsors and CROs aiming to rapidly improve global wellness, stakeholders are increasingly focused on transformation toward more environmentally sustainable clinical trial practices. Digitising clinical trial activities is helping to streamline operations while also minimising the environmental impact:

  • In recent years, intuitive cloud-based decentralised clinical trial platforms and other technologies have helped effectively coordinate research and workflows to support patient, site, and study team communication while taking on study activities (e.g., coordinating visits and remotely monitoring data) without compromising patient data. These tech-enabled solutions have helped reduce in-person site visits for patients and clinical research associates. CRAs can monitor data remotely while reducing travel to and from sites and conserving resources (e.g., CRA time). In some cases, travel to sites can be reduced by up to 30%.
  • With centralised monitoring capabilities, sponsors can leverage targeted analytics using AI/ML to mine incoming data remotely and consistently gauge risk-mitigation to course-correct quicker and with environmental sensitivity.

Digitalisation also allows a more seamless flow from electronic medical records to electronic data capture. That and the rapidly increasing use of connected devices and wearable technologies in clinical trials has made holistic views of data available to CRAs and site and study teams at any time to identify risks and make adjustments.

This tech-enabled data flow also reduces the need to manually input data, as well as the need for paper documents and their review.

Digitised clinical data flow ecosystem

In today’s clinical trials, it is possible for tens of millions of data points to be generated and collected for analysis from connected devices, electronic clinical outcomes assessments, electronic data capture and similar sources. According to the Tufts Center for the Study of Drug Development, Phase III trials alone are estimated to generate an average of 3.6 million data points, which is approximately three times the data volume collected in late-stage trials in 2011. Because sponsors must continue to comply with regulations and standards, this increased volume and complexity creates new challenges. An end-to-end data flow ecosystem is needed to effectively manage and protect the data and deliver high-quality outcomes.

Key components of a streamlined data flow ecosystem include:

  • Protecting and monitoring sponsors’ digital data assets. To ensure data integrity throughout the clinical trial process — from data collection through statistical analysis — data must automatically flow into a secure data lake where it immediately triggers review by study personnel. Automated data flow facilitates real-time signals, triggers, and data insights, which ultimately maintains patient safety and safeguards the sponsor’s data assets.
  • Connecting trial-related data assets. Storing all data (e.g., structured, unstructured, etc.) in a data lake provides a single repository to streamline the operational effectiveness of processes to support the patient, site, and sponsor. This includes the integration of narratives, data regarding third-party vendor effectiveness, and site data that supports remote monitoring.
  • Establishing standardisation. Given data volume and variety, it is critical to apply a methodology of rules across all types to standardise analysis. This ensures high quality and regulatory adherence, which protects the sponsor’s data assets.
  • Automating with AI/ML. This streamlines data flow and processes from acquisition to final analysis so the study team can review the data and follow up with sites and sponsors to ensure patients are well-supported.

Enabling dynamic risk-based quality management

End-to-end digital data flow ensures connected and transparent trial operations. Digital data and analytics streamline operational processes, and data is fully visible through dashboards, giving the study team a holistic view into the trial at any time.

Efficient and continuous data flow is a critical step to facilitating risk-based quality management. Continuous data flow enables the team to quickly identify risks and trends to initiate faster action to prevent and mitigate risk in real-time across the trial. It also streamlines decision-making while ensuring patient safety, reducing site burden, and protecting data assets.

Looking ahead

As scientific findings become more intricate and precise, it is inevitable that related clinical trials will need to address these complexities and adopt innovative approaches to keeping important research on track for patients without adding to sponsors’ timelines and budgets. Tech-enabled solutions are addressing the unique needs of today’s clinical trials, enhancing efficiencies by unravelling data complexity, driving actionable outcomes, and allowing informed decision-making throughout the entire drug development lifecycle.

R&D stakeholders who continue to embrace trial digitalisation will collect more insights to fine-tune solutions and approaches to ensure they innovate at a rate that matches the complexity of tomorrow’s R&D.

About the authors

Sabrina SteffenSabrina Steffen serves as the head of innovation & data strategy, data sciences, safety & medical at IQVIA. Steffen has worked in clinical research for 20 years within data management, risk-based monitoring, data strategy, process improvement, and innovation. She has led the data strategy and innovation team for nine years, overseeing large-scale process and technology transformations, starting from inception through delivery and change management, to achieve fully embedded technology-enabled processes.

Julia SundariJulia Sundari, senior sirector of digital strategy and innovation at IQVIA, brings 30 intentional and passionate years in the industry and experience in innovative approaches, such as risk-based monitoring, remote monitoring, and systems interoperability at IQVIA. Currently, Sundari directs a portfolio of initiatives advancing research trials with a global team of clinical research, analytics, and digital scientists. She has led PRIDE, one of IQVIA’s largest employee resource groups, and is dedicated to increasing sustainable clinical trial monitoring models for the industry’s future.