Minset mCoder has achieved SOTA on MDACE
Most healthcare AI can generate codes.
Very little can defend them.
At Minset, that’s the problem we’re solving.
We’re excited to share that mCoder has achieved state-of-the-art performance on MDACE—a public benchmark designed not just to test accuracy, but whether an AI system can tie every code back to supporting clinical evidence. 📊
Specifically, mCoder surpassed all known prior peer-reviewed results, including on the most challenging full-label MDACE setting, where models must select from a 70,000+ ICD-10 code space.
This matters because in real revenue cycle operations:
✅ accuracy gets you paid
🛡️ defensibility keeps you paid
That’s the bar for autonomous coding and where we’re focused.
📰 The full press release announcement:
https://www.prnewswire.com/news-releases/minset-announces-its-autonomous-medical-coding-ai-mcoder-achieves-state-of-the-art-performance-on-mdace-a-leading-public-benchmark-for-automated-medical-coding-302771746.html
