Home › Trials › NCT06995378
Clinical trial Recruiting at 1 site Interventional Ages 65 and up

Personalized lab results for older adults with prediabetes using machine‑learned risk labels

Official title: Evaluation of Patient and Provider Facing EHR-embedded Risk Stratification Tools

Run by University of California, Los Angeles · NCT06995378 · Data updated 2026-11-12

This trial tests whether adding a machine‑learned “very low risk” label to EHR lab messages helps adults 65 and older understand their prediabetes risk and feel better about their health.

Quick facts

Study typeInterventional
Ages65 Years and up
SexAll
Enrollment1200 (estimated)
SponsorUniversity of California, Los Angeles
Academic / other
Locations1 site (Los Angeles, California)
StatusRecruiting
StartedMay 27, 2026
Main results expectedNovember 2026
Study endsSeptember 2029
Registry record updatedJuly 9, 2026
Trial IDNCT06995378 on ClinicalTrials.gov

Is this trial a fit for you?

Likely a good fit

Adults aged 65 and older with a UCLA primary care provider and a qualifying A1c in the 5.7–5.9% range.

Probably not a fit

Patients with A1c 6.0% or higher, without UCLA care, or who do not engage with the MyChart messaging may not benefit.

A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.

What this trial studies

In a real‑world, randomized design, eligible older adults with a UCLA primary care provider and a hemoglobin A1c of 5.7–5.9% are assigned to receive either standard lab result messages or messages enhanced with a machine‑generated very low risk label. The study uses de‑identified EHR data and two surveys (shortly after the lab result and about 30 days later) to assess understanding, emotional response, quality of life, and healthcare utilization. A CatBoost‑based risk model, built from de‑identified UCLA data and locked for the study duration, informs the labeling. The trial examines whether clearer risk communication can influence patient behavior and progression to diabetes in an older population.

Why it matters

Potential benefit: If successful, patients may better comprehend their risk and experience improved well‑being and appropriate healthcare engagement.

How similar studies have gone: Prior work suggests risk communication can affect understanding and behavior, though use of a machine‑learned risk label in EHR messaging is relatively novel.

Who can join: the full rules

Show full inclusion / exclusion criteria 
Inclusion Criteria:

* Age 65 years or older
* Hemoglobin A1c in the prediabetes range (5.7- but not including 6.0%)

Exclusion Criteria:

* Have lab results outside the defined inclusion range
* No UCLA primary care provider
* Age \<65 years
* Eligibility for Surveys:

All randomized participants are eligible to receive study surveys. No additional eligibility criteria apply for survey participation.

HgbA1c of 6.0 or above is not eligible.

Where it's running

  • UCLA Health System
    Los Angeles, California, United States     Recruiting

Study contacts

Similar studies

Other studies for the same condition or treatment. Recruiting studies are listed first.

How to take part

  1. Review the eligibility criteria above with your treating physician.
  2. Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
  3. Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.
View on ClinicalTrials.gov ↗ Find more trials like this →
Browse more
Prediabetes 131Health Communication 3Patient Comprehension 2University of California Los Angeles 1874
Last reviewed 2026-11-14 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.