CPT panel adds AI codes, rejects three; Medicare contractors propose no coverage for AI brain MRI tools; review maps rural surgical telehealth; eye AI lifts referrals
Listen to this post
read by AI voices ยท all episodesThe American Medical Association's CPT Editorial Panel created a Category I code for AI arrhythmia analysis and three Category III AI codes, and rejected three other AI proposals, according to a summary released Oct. 2.
The new temporary codes cover AI identification of ST-elevation heart attacks, a breast cancer risk score from screening mammograms and analysis of digitized prostate cancer slides, and the summary lists Jan. 1, 2027 as their effective date. The arrhythmia code takes effect in January 2028, according to the summary. Separately, two Medicare contractors, Palmetto GBA and Noridian Healthcare Solutions, proposed to stop Medicare coverage of AI software that measures brain structures on MRI in 20 states, saying the evidence of clinical utility is insufficient.
The weekend was otherwise quiet. The Federal Register's listing of CMS documents that mention artificial intelligence showed no new entries since Sept. 24. The other items are a scoping review of telemedicine in rural surgical and anesthesia care and a Shanghai study of a language model used in primary eye care.
- Regulation Oct 2, 2026The CPT Editorial Panel accepted code 93XX7 for noninvasive arrhythmia analysis and deleted Category III code 0897T, with an effective date of January 2028, according to the summary of its Sept. 17 to 19 meeting. It added Category III codes, which the AMA describes as "a temporary set of codes for emerging technologies, services and procedures", for augmentative algorithmic analysis of digitized prostate cancer slides to predict progression (X672T), an augmentative breast malignancy risk score from screening mammogram data (X628T and X629T) and an add-on code for noninvasive identification of ST elevation myocardial infarction and STEMI equivalents (X682T), each listed with a release date of Oct. 2, 2026 and an effective date of Jan. 1, 2027. The panel rejected AI proposals for multiparametric liver tissue quantification, left ventricular end-diastolic pressure measurement and electrical impedance spectroscopy of skin lesions. Proposals for AI acoustic and ECG analysis, algorithmic CT angiography and ultrasound assessment of middle ear effusion were withdrawn. The summary does not address payment rates; the panel next meets Feb. 4 to 6, 2027, according to its process calendar.
- Regulation Oct 1, 2026Two Medicare administrative contractors posted proposed local coverage determinations, the coverage rules that apply to Medicare claims in a contractor's states, finding automated detection and quantification of brain MRIs not reasonable and necessary. "There is insufficient evidence of clinical utility or validity, and use of this technology is considered investigational and therefore not covered," Noridian's proposal says; it names FDA-cleared tools such as NeuroQuant and icobrain and covers 13 Western states and three Pacific territories. Palmetto's proposal, covering Alabama, Georgia, North Carolina, South Carolina, Tennessee, Virginia and West Virginia, cites the lack of measurement standards across platforms, insufficient evidence of improved outcomes, proprietary datasets that are not interchangeable and limited diversity in training data. Comments are open Oct. 1 to Nov. 14, with open meetings Oct. 22 (Noridian) and Oct. 26 (Palmetto). CGS Administrators and National Government Services posted proposals with the same title in September 2025 and January 2026, according to CMS's coverage data.
- Evidence Oct 5, 2026Researchers led from the University of Calgary's Cumming School of Medicine screened 9,923 records and included 98 studies published from 1992 to 2024 on telemedicine in surgical and anesthetic care, according to a scoping review published Oct. 5 in npj Digital Medicine. Most studies came from the United States (61.2%), Canada (21.4%) and Australia (17.3%), and 39.8% focused on rural care, where uses centered on specialist access, preoperative triage and reduced travel; urban studies centered on postoperative follow-up, specialist consultation and preoperative screening. Telemedicine showed similar short-term clinical outcomes to in-person care, high patient satisfaction and lower travel costs, the authors reported. Video and telephone remained the main modes, with app- and web-based platforms growing from 2020, and the authors called for comparative research on costs, access and outcomes. The review does not address artificial intelligence.Source: npj Digital Medicine
- Evidence Oct 5, 2026A language model built for primary eye care, EyeSeek, was tested in community settings in Shanghai, with 84 people using it and 86 receiving care without it, according to a study by researchers from Tongji University and Shanghai Eye Hospital published Oct. 5 in npj Digital Medicine. The group using the model had higher adherence to referrals (P = 0.037) and improved health literacy, and readability analysis showed answers adjusted to grade 3 to grade 8 reading levels, the authors reported. The study was prospective but not randomized and took place at a single center, which the authors said limits generalizability. It did not report screening accuracy compared with ophthalmologists' assessments.Source: npj Digital Medicine