How do AI, VR help doctors deliver care? CPT code tells the tale

Andis Robeznieks , Senior News Writer

One way to assess creativity in medicine is to look at how physicians are incorporating technology such as telehealth, virtual reality (VR) and augmented intelligence (AI), often called artificial intelligence, into their practices.

Help Move Medicine

Medicine doesn’t stand still, and neither do we. AMA members don’t just keep up with medicine—they shape its future.

And one way to do that is to look at all the digital health-related additions being inserted into the Current Procedural Terminology (CPT®) code, often described as the “language of medicine.”

“It’s a very fascinating area,” said neonatologist and AMA member David Kanter, MD, during the AMA Outpatient CDI Workshop and CPT and RBRVS 2023 Annual Symposium.

More physicians are finding ways to incorporate AI into their practices.

In 2021, the CPT Editorial Panel adopted a taxonomy to describe health services or procedures delivered via AI. The document’s guidance, contained in Appendix S of the CPT code set, took effect a year ago.

Related Coverage

As remote patient monitoring expands, so does CPT to describe it

The new AI taxonomy provides guidance for classifying various AI-powered medical service applications, such as machine learning or algorithm-based solutions, into these three categories.

Assistive—This involves the machine detecting clinically relevant data without analysis or generated conclusions. Physician interpretation is required.

Augmentative—This is when the machine analyzes or quantifies data in a clinically meaningful way, but still requires interpretation by a physician or other qualified health care professional.

Autonomous—The machine interprets data and independently generates clinically meaningful conclusions without physician involvement.

New Category III codes that incorporate the use of AI that were added to the CPT code set are:

  • 0731T to report AI facial phenotypic analysis.
  • 0740T and 0741 to report AI insulin titration.
  • 0764T and 0765T to report AI cardiac function services
  • 0777T to report AI-assisted epidural placement.

Facial phenotypic analysis involves uploading pictures of the faces of patients—usually infants and children—into a database with photos of patients with genetic malformations or genetic syndromes to assist in a diagnosis to identify a genetic cause of a patient’s symptoms and signs.

For insulin titration, the AI algorithm—with the assistance of the patient's physician—uses a sample from a patient with type 2 diabetes to calculate a recommended dose for effective glucose control.

Clinical use of virtual reality

New Category III codes that involve using VR technology added to the CPT code set are:

  • 0770T to report VR-mediated therapy.
  • 0771T0774T to report VR procedural dissociation services.

The add-on code, 0770T, covers expenses for the software typically used in VR-mediated therapy involving skill building for social communication, emotional regulation and daily functional skills in people with neurodevelopmental and mental health disorders such as autism spectrum disorder, said Dr. Kanter. The codes 0771T–0774T cover using a computer-generated VR audiovisual immersive environment to modify a patient’s perception of pain in order to avoid higher levels of sedation so that they can respond to verbal commands and stimuli, he added.

Related Coverage

CPT code set moving at the speed of digital health innovation

“People are being very creative with virtual reality technology to assist patients in ameliorating anxiety, pain and discomfort during invasive procedures,” said Dr. Kanter, a Florida neonatologist and member of the CPT Editorial Panel and the AMA-convened Digital Medicine Payment Advisory Group.

Typically, the technology is used in pediatric endoscopy, radiological imaging and changing wound dressings, he said.

Other presenters outlined information on new and revised digital medicine codes for remote monitoring, non-face-to-face interprofessional consultations, autonomous retinal imaging, computer-based musculoskeletal assessment, and the scanning of microscope slides for digital pathology.