ACP 2026 Recap for Primary Care: Mammography, AI Scribes, and Obesity Medications

The American College of Physicians (ACP) held its Internal Medicine Meeting 2026 April 16–18 at the Moscone Center in San Francisco, bringing together more than 5000 clinicians, educators, and researchers from around the world. At the heart of the gathering was the annual scientific plenary session, New in Annals of Internal Medicine: Hear it First from the Authors, where lead investigators unveiled three late-breaking studies published simultaneously in ACP's flagship journal. This year's presentations covered ACP's new guidance statement on mammography screening for breast cancer, the use of AI for medical documentation, and the effect of weight loss medications on body composition. Taken together, the 3 studies address some of the most pressing questions facing primary care physicians today — from navigating evolving cancer screening recommendations and the hype surrounding AI-assisted clinical tools, to understanding the implications of the rapidly expanding use of GLP-1 receptor agonists and related medications. Below are summaries of each study presented at the plenary.

ACP Issues New Mammography Screening Guidance¹

ACP's new guidance statement recommends that women at average risk between the ages of 50 and 74 undergo biennial mammography screening for breast cancer, while women ages 40 to 49 should engage in shared decision-making with their physician about the benefits and potential harms of screening — including false positives, overdiagnosis, and radiation exposure. For women with dense breasts, ACP suggests doctors consider supplemental digital breast tomosynthesis, advising against the use of supplemental MRI or ultrasound, with decisions informed by potential benefits and harms, availability, patient values and preferences, and costs.

Human Clinicians Outperform AI Scribes on Clinical Note Quality²

Researchers compared recordings of five standardized primary care visits and asked 11 AI scribe tools and 18 human clinicians to generate clinical notes, finding that in every case and by every measure — accuracy, thoroughness, usefulness, organization, and comprehensiveness — human notes scored better than AI-generated ones. Investigators cautioned that while AI scribe tools may reduce administrative burden, they should be regarded as draft documentation tools that require careful review and editing, and are not a substitute for clinician-authored notes.

Incretin-Based Weight Loss Medications Raise Concerns About Muscle Loss³

A systematic review of 36 randomized controlled trials found that while GLP-1 and GIP/GLP-1 receptor agonists — including liraglutide, semaglutide, tirzepatide, and dulaglutide — reduced total weight, body fat, and visceral fat in adults with overweight or obesity, the proportion of weight lost from muscle-related tissue was a notable concern. The researchers stressed the need for clinicians to proactively counsel patients about muscle-related losses associated with weight reduction and to incorporate muscle-preserving strategies alongside pharmacotherapy.

References:

1. Qaseem A, Harrod CS, Balk EM, et al. Screening for Breast Cancer in Asymptomatic, Average-Risk Adult Females: A Guidance Statement From the American College of Physicians (Version 2). Ann Intern Med. Published online April 17, 2026. doi:10.7326/ANNALS-25-05116
2. Reddy A, Gunnink E, Wheat C, et al. Rapid Evaluation of Artificial Intelligence Technology Used for Ambient Dictation in Primary Care: Comparing the Quality of Documentation of Artificial Intelligence-Generated and Human-Produced Clinical Notes. Ann Intern Med. Published online April 17, 2026. doi:10.7326/ANNALS-25-02772
3. Batsis JA, Gavras A, Gross DC, et al. Effect of Incretin-Based and Nonpharmacologic Weight Loss on Body Composition: A Systematic Review. Ann Intern Med. Published online April 17, 2026. doi:10.7326/ANNALS-25-00478