Developer uses Claude Code to get a second opinion on an MRI report

Category: Agentic coding
Status: discussion
Sources: author write-up, discussion
Summary: A developer described pointing Claude Code at their own shoulder MRI report and clinical history, using the agent to cross-reference findings against published clinical practice guidelines and question a recommended treatment. The post is a personal workflow account, not a study, and works from the text report rather than the raw image data.
Comments: A self-identified radiologist cautioned that a full 3D MRI dataset is needed to weigh in and noted current frontier models are unreliable on medical imaging itself; others warned of a coming pattern of patients second-guessing clinicians with AI, the successor to symptom-Googling. Usernames are not verified identities.
Why it matters: It shows practitioners using coding agents as general document-reasoning tools outside software, and the failure modes that follow when output is unverified.