The American Cancer Society (ACS) announced it has revised its process for forming cancer screening guidelines to provide greater transparency, consistency, and rigor.
Aligning with new principles from the U.S. Institute of Medicine (IOM), the new methods create a single generalist group for writing the guidelines, commissioning systematic evidence reviews, and articulating the benefits, limitations, and harms associated with cancer screening tests, according to ACS.
Activities and timelines will be posted on the ACS website. Expert input will be separated from the writing of the guidelines, so an independent writing group will receive appropriate subspecialty expertise while protecting it from the appearance of professional conflict of interest, according to ACS.
In addition, the process will incorporate a systematic evidence review that will use methods consistent with IOM standards, and the guidelines group will grade the strength of its recommendations, according to the society. A formal review will conclude the process and will include opportunities for experts and professional organizations to comment on draft guidelines, ACS said.
An independent advisory group will also periodically review the guideline process itself to assure clarity, utility, and influence of the guidelines, according to ACS. A formal review and rewriting of every ACS cancer screening guideline will take place at least every five years.
The new process is outlined in a special communication in the December 14 issue of the Journal of the American Medical Association.









![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)






