I used Claude Code to get a second opinion on my MRI(antoine.fi)
458 points by engmarketer 19 hours ago | 593 comments
tl;dr: After an orthopedist diagnosed a Grade III partial-thickness subscapularis tendon tear and began aggressive treatment (including shockwave therapy and a homeopathic injection), the author ran their DICOM MRI files through Claude Code (Opus) for a second opinion, which instead found an intact tendon with only mild tendinosis. A follow-up arbitration run by Claude sided with the "no tear" reading at moderate-to-high confidence. The author acknowledges they can't fully trust either verdict but is now skeptical of the clinic's intervention-heavy plan.
HN Discussion:
  • Radiologists warn that current AI models are unreliable at interpreting MRI images and shouldn't be trusted
  • AI offers comfort and accessibility for second opinions despite trust concerns about both AI and doctors
  • Doctors often have financial incentives pushing unnecessary interventions, validating skepticism of aggressive treatment
  • Shoulder abnormalities are extremely common incidental findings, supporting skepticism of the original tear diagnosis
  • ~Medical diagnosis is inherently non-deterministic and expecting consistent readings misunderstands medicine