Practitioner essays from our clinical leads, applied-AI engineers, and operations partners. New pieces published roughly every other week, drawn from active client work (anonymized).
A close look at the three concurrent-coding workflows that separate top-decile MA plans from the middle of the pack. We deconstruct a recent client’s recapture lift from 81.4% to 90.6% across 18 months.
What worked, what broke, and the supervision pattern that finally made unattended denial triage stick across 11 provider organizations. With agent escalation thresholds and observed throughput numbers.
Tukey outlier deletion is in. Here’s how to recalibrate your gap-closure investment portfolio for the new cut-point regime.
The CMS-HCC v28 transition has changed coder workflow at the line level. Eleven items every payer ops leader should validate before the next sweep.
Three categories of edits eat the gap between current and theoretical max first-pass rates. The fix is mostly configuration discipline, not platform replacement.
When you let an agent act unattended, what’s the right oversight cadence? A framework drawn from clinical CDI review patterns.
How we’ve stood up 80–250 abstractors inside a client operation in two weeks, four times. The pre-work that makes the difference.
Concurrent CDI workflows are getting reshaped by AI-drafted queries. Where it helps, where it overreaches, and how to keep physicians engaged.
Why 50 is the smallest sample that’s big enough to mean anything — and what its confidence intervals actually tell you.
Subscribe to The Health Brief: one signal-dense email every two weeks from the Lumiknox desk — regulatory updates, operations benchmarks, and field observations from active engagements. No promotions, no recycled content. Unsubscribe with one click.
