Garbage In - Garbage Out: The Critical Role of Data Quality in Clinical Research

In this lecture, we shall explore the challenges posed to clinical research (clinical trials, studies, and patient registries) by compromised data quality, and the technical solutions developed to tackle them. The importance of specialized user-friendly, real-time, regulatory-approved Electronic Data Capture (EDC) systems, together with tailored data management processes, will be discussed, emphasizing how software and algorithmic solutions can help ensure data accuracy, reliability, and integrity. We shall showcase CLADE-IS, a unique system for clinical data management ranging from databasing to the use of ensemble learning, developed through in-house R&D at the Institute of Biostatistics and Analyses, a Masaryk University spin-off.

CLADE-IS has been rigorously evaluated and recently approved by an international auditing team, resulting in the awarding of the prestigious ECRIN certification to the spinoff—the only certified data center in Central and Eastern Europe. This certification, coupled with the system's proven usability and scalability, has already positioned the spinoff as a strong partner in co-managing large international clinical trials. Finally, we will delve into how CLADE-IS ensures high data quality through a combination of processes like Data Reviews, Central Statistical Monitoring, Risk-Based Monitoring, and Data Augmentation, supported by a multidisciplinary team including data engineers, data scientists, data managers, and data analysts.