OpenAI-powered medical coding model that outperforms physicians

Artificial intelligence startup Ambience Healthcare on Tuesday announced a brand new medical coding model that outperforms doctors by 27%.

Ambience uses AI to draft clinical notes in real-time as doctors consensually record their visits with patients. The corporate used tools from OpenAI to construct the brand new model.

The startup is a component of a fiercely competitive market that has taken off as health-care executives seek for solutions to assist reduce staff burnout and daunting administrative workloads. 

The corporate’s recent model can hearken to patient encounters and discover ICD-10 codes, that are internationally standardized classifications for various diseases and conditions. There are about 70,000 ICD-10 codes which are commonly updated and used to facilitate billing and other reporting processes in health care. 

Ambience said its recent ICD-10 model can reduce billing mistakes and help clinicians and skilled coders work more efficiently. The model notched a “27% relative improvement over physician benchmarks,” based on a release on Tuesday.  

“We’re not replacing doctors or coders,” Brendan Fortuner, Ambience’s head of engineering, told CNBC in an interview. “What we’re doing is we’re liberating them from administration, and we’re fixing mistakes that help make health care higher, safer, less expensive.”

Documenting ICD-10 codes has traditionally been a labor-intensive task in health care, but it surely’s a vital method to track outcomes, mortalities and morbidities in a standardized way, said Dr. Will Morris, the chief medical officer of Ambience.

“In the event you give it some thought from an information perspective, it’s how you may compare and contrast clinician A to B, or health system A to B,” Morris said in an interview. “It is the cornerstone for quality.”

Ambience’s technology is used at greater than 40 health-care organizations, like Cleveland Clinic and UCSF Health. It has raised greater than $100 million, based on PitchBook, from investors including Kleiner Perkins, Andreessen Horowitz and the OpenAI Startup Fund. 

The corporate is reportedly searching for fresh capital at a valuation of over $1 billion, based on a report from The Information. Ambience declined to comment on the report. 

Ambience trained its recent AI model using OpenAI’s reinforcement fine-tuning technology. This technology allows firms to tune OpenAI’s best reasoning models for very specific domains, like health care. 

To validate the model, Ambience tested it against a “gold panel” set of labels, the corporate said. The labels were established by a gaggle of expert clinicians who evaluated complex clinical cases and got here to an agreement on what the fitting codes were. 

The corporate then recruited 18 different board-certified doctors and compared their performance on ICD-10 coding accuracy to the model’s performance. That comparison showed the Ambience technology performed 27% higher than the physician baseline. 

“It shows for the primary time that an AI system can actually surpass clinician experts at a really, very vital administrative task, especially in coding,” Fortuner said. 

Ambience already has similar capabilities available for other medical codes like Current Procedural Terminology (CPT) codes, and Fortuner said it’s exploring methods to tackle other areas like prior authorizations, utilization management and clinical trial matching. 

The corporate’s recent ICD-10 model will roll out to customers over the summer.

“Getting it right at the purpose of care is a fundamental change,” Morris said.