Curie Brief
Turn on cookies to sign in
Signing in saves your progress to your Curie account. We can only do that with cookies on — turn them on to continue.
NewsHealth tech company AKASA has launched an autonomous AI platform that can fully code complex inpatient hospital encounters in about 90 seconds — a task that typically takes human coders 30–60 minutes. The platform targets the notoriously complex "mid-cycle" of hospital revenue cycle management, aiming to ease workforce shortages and speed up reimbursement. Cleveland Clinic is among the early adopters.
Health tech company AKASA has unveiled an autonomous AI platform for inpatient medical coding and clinical documentation integrity — tackling what insiders call the "holy grail" of healthcare revenue cycle management. Inpatient coding is a notably complex process: a typical hospital stay generates around 60 documents and 50,000 words, which coders must translate into codes drawn from a pool of 150,000 options. Workforce shortages mean some accounts sit untouched for days after discharge.
AKASA's AI completes coding in roughly 90 seconds post-discharge with no human intervention required. The company builds custom AI models for each health system to account for differences in patient populations and documentation practices — a level of specificity it says is essential for handling complex inpatient cases. Third-party blinded evaluations showed the AI matched or exceeded human coder performance on key accuracy measures, including MS-DRG assignment and principal diagnosis.
By the Numbers:
Why it matters: As hospitals face mounting staffing shortages and billing complexity, autonomous AI coding could dramatically accelerate cash flow and reduce administrative burden. However, a recent BCBSA analysis found AI coding tools added nearly $1 billion in costs to payers over two years — signaling that the broader payer-provider tension around AI in billing remains an open and consequential question.
