Claude Code was used as a second reader for an MRI
Right shoulder pain led to an MRI, and the clinic diagnosed a more-than-50% partial tear in a shoulder tendon. The clinic started shockwave therapy and an injection soon after the scan, then suggested repeating the treatment three times. GPT 5.5 Pro reviewed the clinic materials and flagged two concerns: a recent guideline says shockwave therapy should not be used for rotator-cuff tendon problems without calcification, and Traumeel is ed in Germany as a homeopathic medicine without a stated treatment use.
The raw MRI export contained a few hundred less DICOM files totaling about 266 MB. Opus 4.8 inside Claude Code was allowed to install needed and spent about an hour analyzing the MRI. Its first report disagreed sharply with the clinic and found the tendon intact.
A second run compared the clinic report, the first AI report, and symptom-checking context from GPT 5.5 Pro; Claude Code used separate to review the case from different angles. That second report again favored no clear partial or full tear, while noting mild tendon irritation or wear. The result created a hard practical problem: the clinic plan looked too aggressive, but the AI second opinion was not trustworthy enough to replace a real medical expert.
Key points
- The clinic diagnosed a more-than-50% partial tendon tear in the right shoulder.
- GPT 5.5 Pro raised concerns about shockwave therapy and Traumeel based on the provided materials.
- Claude Code analyzed a roughly 266 MB DICOM MRI export with hundreds of files.
- Opus 4.8 first said the tendon looked intact, which directly conflicted with the clinic report.
- A second Claude with more context again favored no clear partial or full tear.