This session will showcase methods to minimize the cycle time for database build. The session will highlight a simple method to leverage standard metadata to iteratively prototype the clinical database while the protocol matures. We’ll explore emerging methods that build upon this concept to further reduce cycle times and increase quality.

Medical and Clinical data review is crucial to clinical development, assuring patient safety, determining drug efficacy, and assessing data quality. It involves a rigorous analysis of a wide variety of clinical data and as of today, this is largely executed using disjointed manual processes requiring integration of data from multiple sources before being able to extract actionable insights. Raw data, such as eDC, IVRS, Lab, etc., needs to be transformed into a standardized, user-friendly data model that can be visualized through different systems for review and discrepancy management by different functions. With the accelerated increase and complexity of clinical data sources we need to modernize and mature our digital environments to manage data flow and data review activities in a way that we can take full advantage of automation, get to near real-time access to data and provide the capability for integrated review processes and collaboration across the departments. Besides functional benefits, the platform will realize significant cost and time efficiencies and prepare for future capabilities driving risk based medical and clinical data review with Artificial Intelligence and Machine Learning capabilities.

The current generation of the software systems used in Clinical Research are siloed and moving the data from one system to another needs connectors and data movement. When the final submission is prepared, or any other major event such as Database lock for a study is performed, there is a lot of coordination and management to align all the functions. How can we build the next-generation of interconnected systems to alleviate these issues, and streamline processes to have a smooth flow of data with proper controls while providing enhanced functionality, user experience, and flexibility to individual functional areas

Site selection is one of the known bottlenecks for clinical trials. We created Site Intelligence Hub to overcome some of the challenges and to accelerate the process of study start-up.

The data and analytics space continues to evolve rapidly, and leaders often get overwhelmed by the technical jargon like Big Data, Machine Learning, Artificial Intelligence, etc. This talk explores different case studies that highlight the successes and challenges of enabling advanced analytics in clinical development.

This session will describe Pfizer's AI journey through the lens of clinical data, use cases, implementation, and key to success. Clinical Data Management for the Vaccine Study presented an opportunity for ML/NLP to assist in saving valuable time reconciling data. The foundation for a Smart Data Quality strategy was expanded to other TAs thanks to the solution's Pattern Recognition and Clinical Inference capabilities that will be explained in detail.

Large language models are enabling a new realm of capability for Natural Language Transformation and Generation. The ability for computer systems to translate, transform, and even generate text will accelerate with a high value return many of our clinical processes.  We'll outline FOCAL – the Framework for Operational Clinical AI Language Tools that we are building at AbbVie.

Pharmaceutical companies can leverage systematic analyses of the data streams generated during clinical trials to improve future clinical trials. However, traditional analytical approaches cannot handle variables' sparsity or high-dimensional relationships. We have been developing TrialGraph – a technology solution to intelligently optimize tasks, including side effect prediction. During this session, I will share our lessons learned and best practice recommendation in building enterprise-scale analytic solutions to accelerate clinical development.

Accelerating speed of delivering medicines to the people who need them starts with understanding the end to end data flow. This includes organizational models that have capabilities to describe data with its biases and leverage metadata to support the speed of finding necessary information contained in the data. The solution starts with a holistic Data Strategy that lives at the intersection of Clinical Strategy and Digital Strategy.

One of the most powerful applications of artificial intelligence is a form of pattern recognition that can operate at scale, using inputs that humans find difficult or impossible to evaluate. This allows measurement of safety and efficacy in clinical trials using fewer subjects, with greater confidence in the result than is possible with traditional methods. This, in turn, enables decision-making in early development that saves resources and reduces the risk of expensive late-stage failures. We will discuss the opportunities for sponsors to improve their trials using AI tools, with illustrative examples.

Estimating enrollment rates accurately is a critical function of portfolio and study planning but accurate estimations are notoriously difficult. Artificial intelligence can be used to generate recruitment rate predictions that mitigate risk and uncertainty. This presentation outlines methods, approaches, experimental results, and practical considerations for using machine learning to predict enrollment rates for clinical trials.

Clinical Studies Adjudication (CSA) has been providing study teams and external committees with an easy way to set up, manage and submit clinical event assessments since 2011. We have made major enhancements to automate workflow and reduce event prep time. We have incorporated our Document Redaction Tool which uses Machine Learning to identify and redact PHI and other confidential information. With a new dashboard to help prioritize tasks, the CSA’s improved functionality will help users spend less time browsing screens and more time managing events so they can get adjudicated on time.

I will introduce our journey to advanced analytics from traditional reporting. The motivation, challenges, initial successes, and lessons learned will be shared.

This presentation will explain the strategic approach and various use cases for the application of AI throughout the Clinical Development environment at Merck.