Patient Navigation, Population Health Management
Conditions
Keywords
Population Health, Care Navigation, Medicare Advantage, Artificial Intelligence, Clinical Decision Support, Care Management, Health Services Research, Chronic Disease Management, Risk Stratification, Preventative Care, Health Care Utilization, Health Care Costs
Brief summary
ASCEND-MA is an embedded, health-services study of at-risk Medicare Advantage members attributed to Intermountain Health in Utah. Participants are quasi-randomized based on their medical-record-number parity to either AI-supported, nurse-reviewed proactive care navigation or usual care. The study will evaluate whether the program changes cumulative payor-paid healthcare spending over 12 months.
Detailed description
An additional ancillary, separately consented consumer-experience sub-study will sample roughly 45 intervention-arm participants for surveys and interviews about the acceptability, burden, and perceived usefulness of the care-navigation workflow.
Interventions
OTHERAI-Supported Rising-Risk Care Navigation
AI-supported proactive care navigation involves the generation of guideline-informed candidate care-navigation actions from protocol-authorized structured data, human-in-the-loop review by a nurse, and then delivery of the approved suggestion through existing care-management or clinical workflows. The nurse may accept, modify, reroute, or reject each candidate before participant outreach or care-team routing. Reassessment is planned approximately every 90 days and may change intervention delivery, but not assigned-group membership.
Sponsors
Intermountain Health Care, Inc.
Study design
Allocation
NON_RANDOMIZED
Intervention model
PARALLEL
Primary purpose
HEALTH_SERVICES_RESEARCH
Masking
NONE
Intervention model description
Eligible participants are quasi-randomized 1:1 at the individual level using medical-record-number parity.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
•.Enrolled in an eligible Medicare Advantage plan and attributed to Intermountain Health in Utah. * Continuous Medicare Advantage enrollment for at least 6 months before the index date. * PRM Rising-Risk score (an internally derived prediction model) of at least 0.70 and Current-Risk score below 0.95 at index * Predicted year-over-year cost increase of at least 30%. * At least one targeted chronic condition: diabetes mellitus, heart failure, chronic obstructive pulmonary disease, chronic kidney disease, hypertension, or hyperlipidemia.
Exclusion criteria
* Hospice enrollment at index. * End-stage renal disease requiring chronic dialysis at index. * Active oncology treatment at index. * Long-term institutional residence, including skilled-nursing-facility residence, at index. * Primary language cannot be supported through patient-directed outreach and no feasible alternative care-team communication pathway is available.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Cumulative payer-paid health care spending per participant | 1 year | Mean cumulative payer-paid health care spending (in U.S. dollars) recorded in claims per participant. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Rate of All-Cause Acute-Care Episodes | 1 year | Inpatient admissions, emergency department visits, and observation stays will be combined into acute-care episodes, with related encounters counted once. |
Countries
United States
Outcome results
None listed