Improving AI Agreement for Quality Assurance Scorecard

A global biopharmaceutical company leveraged the Authenticx Quality Solution to automate their quality assurance evaluations with customized scoring rubrics. At initial launch, agreement scores were low, averaging 63% across all skills.

Authenticx in Action   

Authenticx analysts reviewed the quality assurance scorecard to assess how the rubric could be updated to raise agreement scores to a more reliable level, while the Authenticx team maintained a cadence of human-evaluated quality scores.  

To address gaps, the team developed a system of tagging classifiers to improve labelling consistency and better inform the Authenticx Smart Predict AI model. Then the AI model and human analyst scores were recalculated for agreement.  

Results  

After fine-tuning, the AI model saw significant improvement, with an average increased agreement score of 89% across all quality assurance skills! 

With quick engagement, the team drove the improved agreement scores from 63% to 89% with approximately 300 calls evaluated over the span of 3 weeks.  

A strong agreement score strengthens confidence in data reporting, which is helping this global biopharmaceutical company utilize Authenticx to improve their quality assurance program with AI automation.  

About Authenticx

Authenticx was founded to analyze and activate customer interaction data at scale. Why? We wanted to reveal transformational opportunities in healthcare. We are on a mission to help humans understand humans. With a combined 100+ years of leadership experience in pharma, payer, and healthcare organizations, we know first-hand the challenges and opportunities that our clients face because we’ve been in your shoes.

Want to learn more? Contact us!

Or connect with us on social! LinkedIn | Facebook | Twitter | Instagram | YouTube