Blog
Product updates, guides, and engineering notes from the team.
How to Evaluate Patient-Facing Medical Imaging AI Tools
A practical framework for assessing patient-facing AI that explains imaging reports without crossing into diagnosis or treatment advice.
AI Should Explain Uncertainty, Not Hide It
Patient-facing medical AI should preserve uncertainty, negation, measurements, and recommendations instead of turning cautious clinical language into false certainty.
A DICOM File Is Not a Patient Experience
Giving patients access to medical images is important, but a folder of DICOM files does not by itself provide understanding, context, or a clear next step.
What Patient-Facing Medical AI Should Never Do
Responsible patient-facing medical AI starts with clear prohibitions: no diagnosis, no treatment changes, no hidden uncertainty, and no claim to replace a clinician.
Why Radiology Reports Are Difficult for Patients to Understand
A practical look at why radiology reports feel difficult to read, what each section is designed to do, and how patients can prepare better questions for their clinicians.
What AI Can—and Cannot—Explain About Medical Imaging Reports
AI can make radiology language easier to navigate, but explanation is not diagnosis. Learn the appropriate role, limits, and safety boundaries of patient-facing imaging AI.
Five Principles for Responsible Patient-Facing Medical Imaging AI
A practical governance framework for designing patient-facing medical imaging AI around clear purpose, faithful communication, human oversight, privacy, and continuous evaluation.