Tricks of the Trade—Easing the Burden of Data Abstraction - 2023 Quality Summit Presentation (Non-CE)-Tricks of the Trade

Video Transcription

Video Summary

The discussion focused on two different approaches to easing the burden of data abstraction in the healthcare industry. The first speaker, Serena Felcher, discussed the use of AI approaches to data abstraction. She explained that by using artificial intelligence and machine learning algorithms, it is possible to automate the process of abstracting data from medical records, saving time and reducing errors. Serena explained that her hospital, Sutter Medical Center, implemented an EHR-based data registry repository and integrated it with their AI systems. This allowed them to seamlessly transfer data from their data warehouse to the registry, saving time and effort in the abstraction process. The second speaker, Lisa Foster, discussed the manual approaches to data abstraction. She emphasized the importance of setting up abstractors for success, providing them with the right resources, and ensuring they have access to the necessary training modules. Lisa explained how her team leverages their EMR system to create custom reports and streamline the case finding process. She also highlighted the value of submitting data early and often, as it allows for real-time process improvement and identification of any issues. Both speakers emphasized the importance of accuracy and review in the data abstraction process, particularly when dealing with discrepancies in medical records. They stressed the need for collaboration between data abstractors and IT professionals to ensure the accuracy of AI algorithms and to address any discrepancies in the data. Overall, the speakers provided insights into the different approaches to easing the burden of data abstraction and the potential for AI to revolutionize the process.

Keywords

data abstraction

healthcare industry

AI approaches

artificial intelligence

machine learning algorithms

medical records

EHR-based data registry repository

manual approaches

abstractors

EMR system