How can we improve AI for mining data from electronic medical records? – MedCity News
Data mining from electronic medical records for clinical registries seems like the ideal task to insert artificial intelligence (AI) technology — automating data mining and freeing up clinically important resources. However, replacing human data abstractors with AI alone has resulted in less-than-desired accuracy and limited confidence in the results. It might be time to rethink the approach and instead leverage the strengths and limitations of both technology and human abstractors.
This webinar discusses how a human-computer team takes advantage of the clinical expertise and complex problem-solving ability of humans for the more challenging clinical registry fields and the speed and accuracy of AI technology for the more straightforward fields. The result is more accurate, timely data for clinical registries and internal patient care projects.
Join us on July 20 at 2pm ET and in this webinar, we’ll discuss:
- The strengths and limitations of AI
- Why a human+computer approach to data mining yields the best results
- How AI methods such as machine learning and natural language processing can standardize clinical registry data
- How to make clinical registry data available in real time across hospital systems for patient care, quality initiatives, and other internal projects
To attend, please fill out the form below: