AI takes on cancer diagnosis: can a computer match expert pathologists?
NCT ID NCT07307157
First seen Jun 25, 2026 · Last updated Jun 27, 2026 · Updated 1 time
Summary
This study compares a new AI system, called COSMO, against 30 board-certified pathologists to see who can more accurately diagnose brain, lung, and kidney cancers. Both the AI and the pathologists will review the same 300 de-identified tissue images. The goal is to see if AI can help improve cancer diagnosis.
What this could mean
Our plain-language read of the trial. This is informational only — not medical advice or a prediction.
Active substance
COSMO AI system (digital pathology software)
What this could lead to
If successful, this could show that AI can help pathologists diagnose cancer subtypes more accurately and consistently, potentially speeding up diagnoses.
What could go wrong
This is a small, early-stage study with only 30 pathologists and 300 cases. The AI may not perform as well in real-world settings or on different types of cancer.
Disclaimer
Read more
Show less
This is a summary of
the original study
.
Summaries may miss details or leave out important information. Before applying or accepting participation, make sure you have read and understood the full study. Curemydisease.com takes no responsibility whatsoever for anything missed, misunderstood, or acted upon as a result of our summary — we know it does not capture everything.
This is a summary of the original study . Summaries may miss details or leave out important information. Before applying or accepting participation, make sure you have read and understood the full study. Curemydisease.com takes no responsibility whatsoever for anything missed, misunderstood, or acted upon as a result of our summary — we know it does not capture everything.
Get updates
Get notified about this study
Sign up to get updates when this study changes or when new studies for BRAIN CANCER are added.
By submitting, you agree to our Terms of use
Conditions
The condition(s) this trial relates to.
As listed by the trial registrant
The condition terms exactly as the trial's registrant entered them.
Contacts and locations
Show contact details
Enter your email to view the contact information for this study.
By submitting, you agree to our Terms of use
Locations
-
Harvard Medical School
Boston, Massachusetts, 02115, United States