News Decision-Making Support

ASCO Guidelines Added to Doximity's LLM

March 17, 2026 By ASCO AI Staff 2 min read
Share Share via Email Share on Facebook Share on LinkedIn Share on Twitter

Doximity has announced that they have reached an agreement with the American Society of Clinical Oncology (ASCO) to integrate the ASCO Guidelines into DoxGPT, the company’s evidence-backed medical AI for clinicians.

The large language model provides assistance for administrative and clinical reference tasks and is supported by PeerCheck, a physician-led initiative for peer reviewing the information provided by DoxGPT as a clinical safeguard. With PeerCheck, physicians can evaluate and improve answers that the AI tool generates to mitigate potential bias and check inaccuracies.

DoxGPT is designed for use within clinical workflows, including point-of-care decision support, documentation assistance, and synthesis of medical literature. The integration of ASCO Guidelines enables the model to draw from structured, consensus-based recommendations that are routinely updated to reflect new evidence. ASCO’s living guidelines framework allows for more rapid incorporation of emerging clinical data compared with traditional guideline update cycles. Both types of guidelines would be accessible within Doximity’s AI-powered assistant.

The platform operates within a secure environment intended to meet HIPAA requirements, with data handling processes structured to protect patient information. In addition, Doximity reports that clinician interaction with the tool, including PeerCheck feedback, contributes to ongoing refinement of responses. The inclusion of specialty-specific guidance, such as oncology recommendations from ASCO, represents an effort to align generative AI outputs with established clinical standards and reduce variability in information retrieval.

ASCO AI in Oncology is published by Conexiant under a license arrangement with the American Society of Clinical Oncology, Inc. (ASCO®). The ideas and opinions expressed in ASCO AI in Oncology do not necessarily reflect those of Conexiant or ASCO. For more information, see Policies.

Performance of a convolutional neural network in determining differentiation levels of cutaneous squamous cell carcinomas was on par with that of experienced dermatologists, according to the results of a recent study published in JAAD International.

“This type of cancer, which is a result of mutations of the most common cell type in the top layer of the skin, is strongly linked to accumulated [ultraviolet] radiation over time. It develops in sun-exposed areas, often on skin already showing signs of sun damage, with rough scaly patches, uneven pigmentation, and decreased elasticity,” stated lead researcher Sam Polesie, MD, PhD, Associate Professor of Dermatology and Venereology at the University of Gothenburg and Practicing Dermatologist at Sahlgrenska University Hospital, both in Gothenburg, Sweden.

KOL Commentary
Watch

Related Content