Study EHR Risk Stratification Tools

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

This study evaluates whether adding machine learning-based risk information to electronic health record (EHR) lab result messages helps older adults better understand their risk of developing diabetes and influences their emotional responses, quality of life, and healthcare use.

Eligible participants are adults aged 65 years and older with a UCLA primary care provider and a hemoglobin A1c level in the range (5.7-6.0%). Participants are identified automatically at the time their lab results are processed and are randomly assigned to receive either standard lab result messages or modified messages that include a "very low risk" label generated by a machine learning model.

All participants who are randomized are invited to complete two surveys: one shortly after their lab result is posted in MyChart and a follow-up survey approximately 30 days later. The study also uses de-identified EHR data to examine patterns of healthcare utilization and progression to diabetes. Provider comments related to lab result messaging will be analyzed to explore differences in response patterns between the two groups.

Study Overview

• Status: Not yet recruiting
• Conditions: Prediabetes; Health Communication; Patient Comprehension
• Intervention / Treatment: Device: Hemoglobin A1c Lab Result Communication Tool

Detailed Description

Prediabetes thresholds based on hemoglobin A1c were originally developed using younger, healthier populations and may not reflect the slower and more variable glycemic changes observed in older adults. Evidence from large community-based cohorts suggests that adults aged 65 years and older with A1c values in the prediabetes range are often more likely to return to normal glycemia than to progress to diabetes, creating uncertainty for patients and providers when interpreting lab results.

Machine learning models developed using de-identified UCLA Health EHR data from multiple annual cohorts between 2020 and 2024 demonstrated strong performance in predicting progression to diabetes. The final model uses a CatBoost architecture and incorporates approximately 94 routinely collected clinical variables to generate patient-specific risk scores. Model performance was evaluated across yearly cohorts, and the selected model is locked for the duration of the study without updating or adapting to new data.

The study follows a real-world, randomized deployment design in which eligible individuals in the lowest 15% of model-predicted risk within the eligible study population are identified automatically at the time lab results are processed and assigned to either modified or standard lab result messaging. De-identified EHR data and free-text provider comments are used to examine healthcare utilization, disease progression, and provider response patterns over time.

All participants who are randomized are invited to complete two surveys. The first survey is administered shortly after receipt of the laboratory result and is designed to assess immediate patient understanding of the result and emotional responses such as anxiety or reassurance. A second survey is administered approximately one month later and uses validated instruments to measure health-related quality of life, food-related quality of life and eating behavior, and perceived burden of healthcare. Both study arms receive the same surveys, allowing comparison of patient-reported outcomes between standard and modified laboratory result messaging. Surveys are distributed only to participants who have been randomized to either modified or standard laboratory result messaging. Therefore, no additional eligibility criteria apply for survey participation beyond randomization.

By embedding model-generated risk information directly into routine EHR workflows, this study aims to generate evidence on whether precision-based communication can support more individualized, patient-centered care and inform future implementation across broader patient populations and clinical use cases.

• Study Type: Interventional
• Enrollment (Estimated): 1200
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Katelyn Nguyen Assistant Clinical Research Coordinator; Phone Number: 310-267-5250; Email: katenguyen@mednet.ucla.edu

Study Locations

• United States
  • California
    • Los Angeles, California, United States, 90049
      • UCLA Health System
      • Contact: Katelyn Assistant Clinical Research Coordinator; Phone Number: 310-267-5250; Email: csarkisian@mednet.ucla.edu
      • Contact: Catherine Sarkisian, MD; Phone Number: 3102068272; Email: csarkisian@mednet.ucla.edu
      • Principal Investigator: Catherine Sarkisian, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Age 65 years or older
• Most recent hemoglobin A1c in the prediabetes range (5.7-6.0%)

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.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Personalized Lab Result Messaging; Participants receive modified electronic health record (EHR) lab result communications in the patient portal (MyChart) and provider-facing EHR interface that include a qualitative "very low risk" label generated by a machine learning-based tool, along with brief explanatory text providing context about their current results and indicating a low level of concern at this time.	Device: Hemoglobin A1c Lab Result Communication Tool; A behavioral intervention delivered through a personalized Electronic Health Record (EHR)-integrated lab result communication tool designed to improve emotional and cognitive responses to lab results among adults aged 65+. The tool applies behavioral science principles such as risk personalization, simplified messaging, and visual framing to reduce patient anxiety, enhance understanding, and support informed decision-making.
No Intervention: Standard Lab Result Messaging; Participants receive standard electronic health record (EHR) lab result communications without any machine learning-generated risk labeling or explanatory text providing additional context about level of concern.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Prediabetes- Related Healthcare Utilization	Total count of prediabetes-related healthcare utilization defined as the sum of outpatient visits to endocrinology, repeat hemoglobin A1c tests, and new prescriptions for diabetes-related medications following the index A1c result.	365 days after result

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of Repeat Hemoglobin A1c Tests	Total number of repeat hemoglobin A1c laboratory tests performed after the index test. This measure reflects follow-up glycemic testing and serves as an indicator of diabetes-related monitoring and healthcare utilization.	365 days after result
Number of Prescriptions for Diabetes-Related Medications	Total number of prescriptions issued for medications commonly used for glycemic management (e.g., metformin) following the index hemoglobin A1c result. This outcome captures initiation of pharmacologic treatment related to diabetes risk.	180 days after result
Total Number of Outpatient Healthcare	Total count of outpatient visits across all specialties following the index A1c result	180 days after result
Numbers of Referrals to Endocrinology	Total number of outpatient referrals to an endocrinologist occurring after the index hemoglobin A1c laboratory result. This measure is used to quantify diabetes-related specialty care utilization potentially associated with interpretation of the laboratory result communication.	14 days after initial result
Number of Referrals to Nutrition Services	Number of participants with an electronic referral order placed to clinical nutrition services documented in the electronic health record after release of the hemoglobin A1c result.	14 days after initial result
Number of Referrals to Diabetes Education	Number of participants with an electronic referral order placed to diabetes education services documented in the electronic health record after release of the hemoglobin A1c result.	14 days after initial result
Number of Completed Endocrinology Visit	Number of participants who complete an outpatient endocrinology encounter documented in the electronic health record after laboratory result notification. Visit completion will be identified using encounter records associated with endocrinology clinic services.	180 days after result
Completed Nutrition Services Visit	Number of participants who complete an outpatient visit with clinical nutrition services documented in the electronic health record following laboratory result notification. Completion will be determined using encounter data associated with nutrition services.	180 days after result
Completed Appointments to Diabetes Education	Number of participants who complete an outpatient visit with diabetes education services documented in the electronic health record following laboratory result notification. Completion will be determined using encounter data associated with diabetes education.	180 days after result
Number of Patient MyChart Messages	Count of MyChart Test Result Messages	7 days after viewing lab result
Numbers of Phone Calls Received after A1c Results	Count of telephone encounters to ordering provider	7 days after viewing lab result

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Self-Reported Quality of Life	Patient-reported quality of life assessed using survey responses evaluating overall physical, mental, and health-related well-being following receipt of lab result communication.	30 days after initial survey invitation
Self-Reported Physical Function Following Lab Result	Self-reported physical function asking about ability to perform activities such as household chores, stair climbing, walking, and running errands following receipt of lab result communication. This measure uses structured survey items to evaluate whether receipt of A1c lab result communication is associated with changes in exercise.	30 days after initial survey invitation
Self-Reported Dietary Behaviors Following Lab Result	Patient-reported dietary behaviors following receipt of lab result, including eating patterns, appetite, satiety, and food-related changes or restrictions due to concerns about lab results. These behaviors are assessed to understand potential impacts on health and weight-related decision-making. This measure uses structured survey items to evaluates whether receipt of A1c lab result communication is associated with changes dietary behaviors.	30 days after initial survey invitation
Patient Understanding and Anxiety Related to Lab Result Communication	Patient-reported understanding of lab report and emotional response to result communication, including perceived clarity, reassurance, and level of concern, assessed using structured survey items designed to measure comprehension and anxiety following receipt of laboratory result messaging.	7 days after results
Number of Incidence of Diabetes	Proportion of participants who progress from prediabetes to diabetes based on electronic health record data, defined by meeting diagnostic criteria for diabetes during follow-up. This outcome is included to monitor long-term clinical safety and progression.	3 years

Collaborators and Investigators

• Sponsor: University of California, Los Angeles
• Collaborators: National Institute on Aging (NIA)

Study record dates

Study Major Dates

• Study Start (Estimated): April 1, 2026
• Primary Completion (Estimated): October 1, 2026
• Study Completion (Estimated): September 1, 2029

Study Registration Dates

• First Submitted: May 20, 2025
• First Submitted That Met QC Criteria: May 20, 2025
• First Posted (Actual): May 29, 2025

Study Record Updates

• Last Update Posted (Actual): May 8, 2026
• Last Update Submitted That Met QC Criteria: May 6, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: Prediabetes; Risk Stratification; Machine Learning; Electronic Health Record; Predictive Modeling; Lab Result Communication; Patient Comprehension
• Additional Relevant MeSH Terms: Endocrine System Diseases; Metabolic Diseases; Glucose Metabolism Disorders; Diabetes Mellitus; Nutritional and Metabolic Diseases; Prediabetic State
• Other Study ID Numbers: IRB-24-6052; P30AG073104 (U.S. NIH Grant/Contract)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes