AKASA Launches Autonomous AI Platform for Inpatient Coding
AKASA announced in a press release an autonomous AI platform for inpatient medical coding and clinical documentation integrity. The platform expands the company’s prebill review software into autonomous workflows for the middle stage of the healthcare revenue cycle.
AKASA says the platform can code complex inpatient cases across medical specialties without human intervention. It completes coding in less than 90 seconds after patient discharge, compared with the 30 to 60 minutes that the company says a human coder typically needs.
The company says blinded evaluations by third parties found its system matched or exceeded human coders on measures including diagnosis related group assignment, principal diagnosis, clinical quality capture and accuracy for conditions present on admission. AKASA plans to add outpatient facility encounters and will create deployment plans with individual health systems.
AKASA says its customers account for about 10% of inpatient discharges in the United States and more than $180 billion in combined net patient revenue. The company trains models for each health system using its clinical documentation, patient mix and coding decisions.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Life Sciences
Oct 5 XtalPi Advances Hair Loss Drug Into IND Enabling Studies Oct 5 Signia Launches MaX AI Hearing Aid Platform in US Oct 5 Viome Signs Agreement to Explore Molecular AI Model in Bhutan Oct 5 Quotient Sciences and Acesion Apply AI to Atrial Fibrillation Drugs Oct 2 Avimer Bio and CNIO Detail AI Method for Protein Cage DesignLife AI Weekly
Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Blue Cross Analysis Links Hospital AI to $942 Million in Added Costs
Atman Health Wins ARPA-H Award to Build Heart Failure AI
AdminaHealth Adds AI Data Assistant to Enterprise Billing Suite
Penguin Ai Launches Revenue Cycle AI Platform
ARPA-H Awards UpDoc Up to $9.2 Million for Clinical AI
Daily AI Brief: the AI news that matters, in your inbox.