Cancer Oriented Understanding and Navigation Via Supportive and Educational Language Models (COUNSEL)

A randomized, open-label behavioral study designed to evaluate the feasibility, acceptability, and early impact of a large language model (LLM)-based artificial intelligence (AI) tool to support patient understanding following an initial oncology consultation.

Inclusion Criteria: 1. Age ≥18 years. 2. Histologically or cytologically confirmed diagnosis of localized prostate cancer 3. Newly diagnosed and planning to undergo or recently completed a radiation or surgical oncology consult at University of California, San Francisco (UCSF) 4. Eastern Cooperative Oncology Group (ECOG) performance status of 0-2 5. English-speaking and able to participate in study teleconferences 6. Ability to understand and willingness to sign a written informed consent document 7. Access to a device and internet connection sufficient for teleconference participation Exclusion Criteria: 1. Prior definitive treatment for prostate cancer (e.g., surgery, radiation, or systemic therapy) 2. Cognitive, sensory, or language impairment that would interfere with the ability to understand, participate in, or complete the study procedures 3. Inability or unwillingness to participate in two study-related teleconferences 4. Current enrollment in another interventional clinical trial that may interfere with study participation 5. Inability to comply with protocol requirements (e.g., completing surveys or using the information-tracking log)