An AI Approach for Addressing Clinical Data Quality
Featuring Dr Jennifer Bradford, Director of Data Science at PHASTAR
Complete the form to view this video
You may need to disable pop-up blocker
Abstract: 'An Al Approach for Addressing Clinical Data Quality'.
High quality clinical data is a key factor in the success of a clinical trial, it provides the basis for the analysis, submission, approval, labelling and marketing of a compound. An essential process in the collection and management of clinical data is data cleaning to ensure the data is consistent and accurate. Errors during data entry will and do happen with the most common being spelling errors, transcription errors, range errors, and text errors affecting coding. Automated edit checks exist, and these prevent the entry of inaccurate information however, they do not detect all potential data entry issues. With data quality at the heart of clinical trial success clinical data management teams also employ a manual approach to data cleaning; raising queries to the clinical trial site to resolve any potential issues or inconsistencies. On some studies there can be high numbers of manually generated queries and understanding the context of these may help us improve the automated edit checks or put additional checks or processes in place to help identify potential data issues earlier. We describe the application of machine learning to historic manual queries across different studies to understand common issues across and within studies enabling a targeted approach to process optimisation for clinical data cleaning.
About the speaker:
As Director, Data Science, Jennifer works closely with other functions within the company and external clients to lead the delivery of innovative data science solutions. Previously she worked for the Advanced Analytics Group at AstraZeneca and later Cancer Research UK (CRUK), working in collaboration with the Christie hospital on electronic data capture, app development and wearables data analytics. She has a degree in Biomedical Sciences from Keele University and a bioinformatics Masters and PhD from Leeds University.