{"resourceId":"kff-medicaid-home-care-program-integrity-ai-2026","versions":[{"version":"external-ee945a20aeb0d45544a3c9c5dc285bcfdcff072329e6cfd4e0722f115581099c","resource":{"id":"kff-medicaid-home-care-program-integrity-ai-2026","title":"States’ Use of Program Integrity Tools in Medicaid Home Care","organization":"KFF","sector":"Medicaid home and community-based services (aging and disability)","geography":"United States (48 responding states)","publishedAt":"2026-10-05","publicationDate":"2026-10-05","eventDate":null,"sourceName":"KFF","sourceLabel":"KFF","sourceUrl":"https://www.kff.org/medicaid/states-use-of-program-integrity-tools-in-medicaid-home-care/","evidenceClass":"independent-research","outcomeClass":"emerging","topics":["data-security","governance-procurement","operating-model"],"finding":"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.","sledRelevance":"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":"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.","architectureImplications":"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.","governanceImplications":"KFF notes there are generally no metrics for unmet need, so states adding AI-driven scrutiny lack a way to measure access harms.","securityPrivacyImplications":"Home care data concerns people with dementia and I/DD receiving care at home; algorithmic flags can affect vulnerable recipients and caregivers.","caveats":"Adoption-status survey, not an effectiveness study. 'AI-enabled' is state-defined. No vendor, accuracy or false-positive data.","streamIds":["health-human-services"],"roles":{"sales":"Sales framing: 21 states are using, piloting or planning AI for Medicaid home care program integrity, so demand exists, but the survey offers no evidence the tools work. Lead with discovery on EVV and claims data quality and how flags are reviewed, and offer a bounded assessment of false-positive impact on recipients and providers. Avoid fraud-recovery promises; KFF provides no figures and warns of access harms.","engineering":"Engineering framing: the data foundation already exists in most states: machine-readable EVV, claims-to-EVV cross-checks and billing pattern analysis. AI tools add anomaly detection or aggregation, as Missouri does with incidents and grievances. Fit depends on EVV completeness and linkage to care plans and authorizations. Validation must measure false positives and their downstream effect on payments and provider participation.","delivery":"Delivery framing: ownership belongs with the Medicaid program integrity unit in partnership with HCBS waiver managers. Delivery should define how AI flags route to human investigators, how providers contest them, and how access impacts are monitored, since KFF notes states lack unmet-need metrics. Start in one waiver population and expand only after reviewing flag accuracy and provider feedback."},"roleDetails":{"sales":{"customerProblem":"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"],"discoveryQuestions":["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?"],"valueHypothesis":"Bounded hypothesis: better flag review and measured false positives can make AI program integrity tools defensible without harming access.","potentialEngagement":"An assessment of one waiver's EVV and claims data readiness, plus a flag-review workflow design with access-impact metrics.","unsupportedClaims":["AI will recover a specific dollar amount","AI tools in these 12 states are proven effective","More scrutiny has no access cost"]},"engineering":{"fit":"Fits analytics and anomaly detection on EVV and claims data; not a care-delivery tool.","architectureIntegration":"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.","proofOfValue":["Measure precision of AI flags against investigator outcomes","Track provider participation before and after","Sample recipients affected by flags for access issues"]},"delivery":{"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.","skillsAdoption":"Investigators learn to triage AI flags; waiver staff learn to interpret access metrics.","governanceCheckpoints":["Human review before payment action","Provider notice and appeal","Quarterly access-impact review"],"acceptanceCriteria":["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"]}},"retrievedAt":"2026-10-29T22:06:00-05:00","enrichedAt":"2026-10-29T22:20:00-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Additional scrutiny may reduce provider participation, which affects direct care workforce availability.","procurementImplications":"States planning adoption (AK, DE, GA, HI, MS, NH, NY, WY) are near-term procurement candidates for program integrity analytics.","operatingModelImplications":"Program integrity units, waiver program staff and EVV vendors must agree how AI flags lead to human review and payment action.","sourceVerification":{"openedUrl":"https://www.kff.org/medicaid/states-use-of-program-integrity-tools-in-medicaid-home-care/","referenceExcerpt":"Twelve states reported currently using AI-enabled tools for program integrity and data monitoring purposes under at least one program","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}