AI helps doctors remember what patients want at end of life

NCT ID NCT07147023

First seen Oct 31, 2025 · Last updated Jun 20, 2026 · Updated 39 times

Summary

This study tests whether an AI tool can accurately summarize serious illness conversations between doctors and patients with advanced cancer. The AI-generated summaries are emailed to clinicians to help them keep track of patient goals and preferences. Researchers will check the summaries for accuracy and ask doctors and patients for their feedback.

Disclaimer Read more

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 CANCER are added.

Our safety recommendation!

By submitting, you agree to our Terms of use

Contacts and locations

Locations

  • Brigham and Women's Hospital

    Boston, Massachusetts, 02115, United States

  • Dana-Farber Cancer Institute

    Boston, Massachusetts, 02115, United States

What this could mean

Our plain-language read of the trial. This is informational only — not medical advice or a prediction.

Active substance

Large Language Model (AI) generated summaries of serious illness conversations

What this could lead to

If successful, this could help doctors quickly understand a patient's care preferences, improving end-of-life communication and alignment with patient goals.

What could go wrong

This is a small pilot study with only 60 participants, testing accuracy and feasibility—not whether it improves outcomes. AI summaries may miss or misinterpret key details.

Conditions

The condition(s) this trial relates to.

cancer Death neoplasm

As listed by the trial registrant

The condition terms exactly as the trial's registrant entered them.