By NextBestFitPre-payment analytics and audits
Real-time fraud detection on all claims; more audits and prosecution.
One data system sees all billing.
Review ledgerHow this path connects
Addresses
Fraud and improper paymentsThis path
Pre-payment analytics and audits
Concrete changes if chosen
What would actually have to change in law, agencies, payment rules, or systems.
- Run real-time fraud analytics on all claims
- Fund audits and prosecution
Effects
Each effect has its own page: the evidence, the case that it is or isn't a real cost, and whom it affects.
What it fixes
- Fraud and improper payments
A unified data system sees all billing and detects suspicious claims before payment. Audits and prosecution complement detection that stops payments before they go out.
What it creates or worsens
- Adds paperwork, coordination, or complexity
Pre-payment fraud detection can flag legitimate claims incorrectly and delay their payment.
- Requires difficult enforcement
Fraudsters adapt to claims analytics, complicating detection, audits, and prosecution.
Who's affected
Who gains
- Taxpayers and public budgets
- Fraud and improper payments: Fraud and improper payments consume public funds and premiums.
- People with employer coverage
- Fraud and improper payments: Fraud and improper payments consume public funds and premiums.
Who loses
- Fraudulent operators and cybercriminals
- Fraud and improper payments: Fraudulent providers receive improper health payments.
Other ways to soften the losses
- Fast appeals for flagged claims
Where it has been tried
- Taiwan NHI: Data analytics flag unusual billing.
- Taiwan: In Taiwan (2008), data mining models applied to National Health Insurance claims to detect hospital billing fraud and abuse achieved an overall accuracy of 99% using classification tree algorithms.