AKASA on October 2, 2026 announced the launch of an autonomous AI platform for the mid-cycle of the healthcare revenue cycle, expanding the South San Francisco company from AI-powered prebill review into autonomous inpatient medical coding and clinical documentation integrity (CDI).
AKASA, which describes itself as a leader in generative AI for the healthcare revenue cycle, said its customers represent more than $180 billion in aggregate net patient revenue and roughly 10% of U.S. inpatient discharges, approximately 1 in 10. The company said inpatient volume processed through its AI products had grown almost 6x in the year preceding the launch, attributing the expansion of its health system customer base to those products.
AKASA said it fine-tunes AI models for individual health systems, accounting for differences in patient populations, clinical criteria, documentation practices, and care complexity, an approach the company said supports complete documentation and accurate coding that better reflects the care delivered. CEO and co-founder Malinka Walaliyadde cast the launch as an industry milestone. “For years, an autonomous mid-cycle has been a holy grail in our industry,” he said. “Today, AKASA is making it real.”
Why Mid-Cycle Automation Has Been Difficult
The mid-cycle is the stage of the revenue cycle where a patient’s clinical record is translated from documentation into the codes that drive reimbursement, quality reporting, risk adjustment, and the integrity of the patient record. The announcement describes that work as highly complex and resource-intensive, and still predominantly manual.
That complexity, the company said, has made reliable automation difficult. The announcement points to a 2025 peer-reviewed study in npj Health Systems that reported medical coding error rates of up to 20%, and to a July 2026 U.S. Government Accountability Office review that identified verifiable accuracy as a central challenge for healthcare organizations adopting AI for medical notes and coding.
According to the company, a coder typically takes 30 to 60 minutes to code a single inpatient encounter, and workforce shortages and capacity constraints can leave health systems waiting several days after a patient’s discharge before a coder even starts on the account. AKASA’s product materials frame the current interval from discharge to coded at three to four days, against 90 seconds with its system.
How the Autonomous Coding Platform Works
Per AKASA’s autonomous inpatient coding documentation, the system reads the complete patient chart (discharge summaries, operative notes, progress notes, consults, labs, imaging, and medications) and works each encounter from start to finish, assigning the full code set independently across all specialties. Every code links back to the exact chart language supporting it, with the rationale and confidence behind it, which the company said builds an audit trail and lets validation take seconds.
Health systems set the operating boundaries. Customers define thresholds, service line rules, payer mix, and audit sampling, and the system codes only what the organization has approved it to code, with ICD-10-CM/PCS built in. The platform works alongside existing electronic health record and billing systems, so moving toward autonomy does not require replacing them. Coding happens at discharge, when the chart closes; AKASA claims this lowers discharged-not-final-coded (DNFC) volume, reduces accounts receivable days, and accelerates cash collection without adding headcount.
AKASA said it tested the system through third-party blinded evaluations in which its AI and expert human coders coded the same inpatient encounters, representing 65% to 85% of inpatient volume at most health systems. Independent reviewers, not told whether each code set came from the AI or a human, found the AI matched or exceeded expert coders on key accuracy measures, the company reported: MS-DRG assignment, principal diagnosis, clinical quality capture, and present-on-admission accuracy. AKASA said the AI completes coding in less than 90 seconds after discharge, and it markets the product as the first autonomous solution built specifically for inpatient coding.
CDI, Deployment, and Early Response
Beyond coding, AKASA is extending the platform upstream into CDI, describing a unified AI layer across clinical documentation, coding, and prebill review intended to keep documentation complete. The company said that as it rolls out the autonomous mid-cycle it will work with health systems on customized deployment plans to scale autonomous volume based on need, and that it will soon introduce outpatient facility encounters to the platform.
Cleveland Clinic has used AKASA’s prebill review products across coding and CDI and intends to explore the autonomous mid-cycle offerings, according to the announcement. “Our revenue cycle work is especially time-intensive because we care for many medically complex patients,” said Rohit Chandra, chief digital officer at Cleveland Clinic. “With autonomous coding, we seek to improve speed and precision in these challenging processes under a compliance-first approach to this work.”
Jeff Francis, chief financial officer and vice president of finance at Nebraska Methodist Health System, which has worked with AKASA for several years, described autonomy as the natural next step for health systems, pointing to revenue integrity, denials, write-offs, and how quickly his organization gets paid. Julie Yoo, a general partner at Andreessen Horowitz, said healthcare cannot meet the scale of demand ahead through human labor alone, and characterized AKASA’s technology as frontier AI built for the specific demands of complex clinical documentation and inpatient coding.
AKASA said its custom models are trained on each health system’s own clinical documentation, case mix, and coding decisions, and that its solutions range from AI that supports CDI and coding teams to fully autonomous workflows that code encounters end to end.
Credit: Source link
