States’ Use of Program Integrity Tools in Medicaid Home Care

KFF · Medicaid home and community-based services (aging and disability) · United States (48 responding states)

Publisher: KFF
Original publication: 2026-10-05
Source retrieved: 2026-10-30

What happened

KFF's 24th annual survey of state Medicaid home care officials (April to August 2026) found 12 states currently use AI-enabled tools for program integrity and data monitoring, one (California) is piloting, and eight plan to adopt, 21 states in all. Use is most common in waivers for people with I/DD and for adults 65+ and people with physical disabilities. North Carolina uses AI to build fraud-detection algorithms in its aged/physical-disability waiver; Missouri uses AI to aggregate critical incidents and grievances. Nearly all states already analyze EVV and claims data.

Why it matters

Shows AI arriving in aging and disability services mainly as a fraud, waste and abuse tool layered on EVV and claims data, while KFF cautions that added oversight can raise administrative burden and limit provider participation.

Evidence and measured results

State self-reported survey; Florida and South Carolina did not respond and Minnesota skipped the question; KFF did not ask what the AI tools are, how accurate they are, or what they produced.

Limitations and uncertainty

Adoption-status survey, not an effectiveness study. 'AI-enabled' is state-defined. No vendor, accuracy or false-positive data.

Put this evidence to work

Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-29; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.

Sales

Role takeaway

Customer problem: State Medicaid HCBS programs face federal pressure on home care fraud while needing to protect access for older adults and people with disabilities.
Stakeholders: Medicaid program integrity director
HCBS waiver managers
State aging and disability agency
EVV program lead
Medicaid Fraud Control Unit liaison
Discovery questions: What AI-enabled tools, if any, are in use and on which waivers?
How complete and timely is your EVV data?
How are flags reviewed and how often are they overturned?
How do you monitor provider participation and access after new controls?
Value hypothesis: Bounded hypothesis: better flag review and measured false positives can make AI program integrity tools defensible without harming access.
Potential engagement: An assessment of one waiver's EVV and claims data readiness, plus a flag-review workflow design with access-impact metrics.
Unsupported claims: AI will recover a specific dollar amount
AI tools in these 12 states are proven effective
More scrutiny has no access cost

Pre-sales engineering

Role takeaway

Fit: Fits analytics and anomaly detection on EVV and claims data; not a care-delivery tool.
Architecture and integration: Integrate with the EVV aggregator, MMIS claims, care plans and service authorizations; add incident and grievance aggregation.
Prerequisites: Machine-readable EVV data
Claims-to-EVV linkage
Care plan and authorization data
Constraints: Survey shows adoption status only
State-specific waiver structures
Live-in and family caregiver EVV exemptions vary by state
Security: Role-based access to recipient-level home care data; audit trail for every flag and action.
Proof of value: Measure precision of AI flags against investigator outcomes
Track provider participation before and after
Sample recipients affected by flags for access issues

Delivery

Role takeaway

Work: Pilot AI-assisted flagging in one waiver with human review, provider appeal paths and access monitoring.
Dependencies: EVV vendor cooperation
Program integrity staff capacity
CMS guidance on HCBS integrity
Ownership: Medicaid program integrity unit, with HCBS waiver program managers.
Skills and adoption: Investigators learn to triage AI flags; waiver staff learn to interpret access metrics.
Governance checkpoints: Human review before payment action
Provider notice and appeal
Quarterly access-impact review
Acceptance criteria: Proposed: flag precision reported quarterly
Proposed: no unexplained drop in active providers in the pilot waiver
Proposed: every payment action traceable to a human decision
Risks: False positives against legitimate caregivers
Provider exit reducing access
Opaque vendor models

Implementation considerations

Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.

Architecture and integration

What must connect, and where does the AI sit in the workflow?

AI sits on top of machine-readable EVV files and claims data that 48 states already maintain; EVV and claims data quality is the real prerequisite.

Governance

Who approves, reviews and stays accountable for outcomes?

KFF notes there are generally no metrics for unmet need, so states adding AI-driven scrutiny lack a way to measure access harms.

Security and privacy

What data, permissions and controls need testing?

Home care data concerns people with dementia and I/DD receiving care at home; algorithmic flags can affect vulnerable recipients and caregivers.

Accessibility and workforce

Who is affected, and what skills or accommodations follow?

Additional scrutiny may reduce provider participation, which affects direct care workforce availability.

Procurement

What should contracts, pricing and exit terms secure?

States planning adoption (AK, DE, GA, HI, MS, NH, NY, WY) are near-term procurement candidates for program integrity analytics.

Operating model

Which teams own the service once it runs?

Program integrity units, waiver program staff and EVV vendors must agree how AI flags lead to human review and payment action.

Publication history

2026-10-29Health & Human Services · Issue 018 resources

Read preserved resource versions (JSON)

Stable resource ID: kff-medicaid-home-care-program-integrity-ai-2026