Using AI to predict costs for enrolling patients in a care management program

Evaluation of MA Proactive Care Program Using Cost Prediction Model With Randomized Waitlist

This study tests whether an AI tool can help identify Medicare Advantage patients at UCLA Health who might have high healthcare costs so they can get better support through a special care management program.

Quick facts

• Phase: Not applicable
• Study type: Interventional
• Enrollment: 5000 (estimated)
• Ages: 18 Years and up
• Sex: All
• Sponsor: University of California, Los Angeles (Academic / other)
• Locations: 1 site (Los Angeles, California)
• Trial ID: NCT06916247 on ClinicalTrials.gov

What this trial studies

This study evaluates an AI Cost Prediction model designed to identify Medicare Advantage patients at UCLA Health who are likely to incur high healthcare costs. The model aims to enroll these patients into a complex care management program called Proactive Care, which provides personalized care navigation and case management. By randomizing the enrollment process, the study will compare outcomes between patients enrolled through the AI model and those on a waitlist, thereby assessing the effectiveness of this predictive approach. The goal is to reduce healthcare utilization and improve patient outcomes through targeted interventions.

Who should consider this trial

Good fit: Ideal candidates for this study are Medicare Advantage patients enrolled in a UCLA Managed Care Plan who are identified by the AI model as having high predicted healthcare costs.

Not a fit: Patients currently enrolled in any UCLA care management program or those who have been in such a program within the last 12 months may not benefit from this study.

Why it matters

Potential benefit: If successful, this approach could lead to more efficient use of healthcare resources and improved health outcomes for high-risk patients.

How similar studies have performed: Other studies have shown promise in using predictive models for patient enrollment in care management programs, indicating a potential for success with this approach.

Eligibility criteria

Inclusion Criteria:

* At least 18 years of age
* Enrolled in a UCLA Managed Care Plan
* Cost prediction model identifies patient as having high predicted costs over the next 12 months

Exclusion Criteria:

* Currently enrolled in any UCLA care management program
* Enrolled in any UCLA care management program in the last 12 months
* Already has an active referral to a care management program

Where this trial is running

Los Angeles, California

• UCLA Health — Los Angeles, California, United States (Recruiting)

Study contacts

• Principal investigator: Richard K Leuchter, MD — University of California, Los Angeles
• Study coordinator: Richard K Leuchter, MD

Conditions Chronic Disease; High utilization; Complex care management; Cost prediction model