Venkat Sethuraman co-wrote this post with Jessica Rine, Sharma R D and Francine Leech

The 10th-annual Summit for Clinical Operations Executives (SCOPE) took place Feb. 18-21 in Orlando, and it drew more than 3,000 participants from life sciences companies around the world. The conference covered advanced and innovative solutions in clinical trial planning, management and operations.

While the attendees represented different functional areas within clinical operations, they were united around a common question: How can data be used to bring value, provide actionable insights and enhance the clinical trial process?

We identified four key trends from the conference that will shape the industry in years to come:

  1. Using technology to improve site selection and management: Low recruitment and poor site performance continue to be a recurring issue. Many life sciences companies are planning or building innovative solutions to apply a data-driven approach to identify and monitor sites. Life science companies, including AstraZeneca and Janssen, shared their visions to apply data-centric approaches to feasibility and site selection. In the next few years, we expect most life sciences companies will build this capability. They’ll also put processes in place to improve site selection and management, freeing up opportunities to refocus on strategic initiatives and innovative opportunities. In addition, several companies have started integrating disparate structured and unstructured data sets (internal and external), such as public clinical registries, real-world data sources, regulatory intelligence, and internal clinical trial management data. Such data sets will help companies make better decisions regarding augmented feasibility and site selection.

  1. Optimizing protocols to improve recruitment and reduce amendments: Companies are realizing that there are ways to enhance clinical trial protocols by involving new and different stakeholders in the protocol generation process. Bringing in patients and site personnel to simulate visits allows companies to make essential changes to improve recruitment and retention. Using EMR data to understand a patient population can help companies test eligibility criteria. These processes can reduce timelines and lead to savings on costly protocol amendments.

    Another key trend related to this topic is digitizing historical protocols to drive decisions related to patient and site burden, complexity, cost and the value of the protocol against the industry. Many companies have started enabling this capability to further optimize endpoints and schedules of activity.

  1. Structuring clinical trial data to enable advanced analytics: Several speakers covered topics related to the importance of having integrated, structured clinical trial data, and the power that can afford an organization. By building platforms like clinical data lakes with common standards of data harmonization, companies can leverage that data to perform advanced analytics. They can also generate insights about their own clinical programs at the study and portfolio level that were previously anecdotal or conjectural. With advancements in cloud-based data storage and compute power, data lakes have become very popular. Many companies have started their journey by using data lakes to provide faster and more reliable insights that are customized to different functional areas.

    Another use case that received greater attention this year was the integration of EDC and EHR data which has the potential to reduce monitoring costs, eliminate unnecessary duplication of data, reduce the possibility of transcription errors, and promote real time access for data review. Few companies presented their vision and roadmap during the summit, but we believe, most of the key players in the industry will adopt this capability in the near future.

  1. Increasing use of artificial intelligence and machine learning in clinical research: As artificial intelligence and machine learning become more advanced, companies are leveraging this technology to help design and execute better clinical trials. Using AI to mine EMR systems, pharmaceutical companies can understand how eligibility criteria will impact their ability to recruit for a trial. Additionally, sites can demonstrate that they have the right patient populations to participate. Machine learning is also helping companies analyze clinical data, leading to better endpoint selection and clinical trial design. From an operations standpoint, companies are leveraging machine learning to automate clinical data mapping and anomaly detection, which has been proven to reduce manual intervention and increase data quality over time.

The most important trends to emerge from the SCOPE summit were around data, machine learning and advanced analytics. In 2019, 80% of healthcare data remains unstructured. In the next 10 to 15 years, we believe that companies will build structure around their clinical trial data, enabling them to make more powerful, data-driven decisions.



BLOG POST: If AI Is the Engine and Patient Data Is its Fuel, Then Who’s in the Driver’s Seat?

BLOG POST: The State of AI Adoption in Pharma

BLOG POST: How Do Doctors Feel About Robots in the Exam Room?


Topics: data science, artificial intelligence, SCOPE, clinical trial design, machine learning, RWE, pharma companies, data strategy, artificial intelligence & pharma, clinical data, RWD, clinical trial data