AI Playbook for Workers Compensation Fraud — Claimant Network

A self-insured employer's TPA has flagged 22 workers compensation claims in 14 months that share three attorneys, two treating physicians, and a pattern of late reporting (average 9 days after alleged injury). Total incurred: $1.4M. Six claimants have prior WC claims with different employers.

When to use this playbook

• Use this playbook when the decision looks like the situation above: A self-insured employer's TPA has flagged 22 workers compensation claims in 14 months that share three attorneys, two treating physicians, and a pattern of late reporting (average 9 days after alleged injury).
• It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Workers Compensation Fraud — Claimant Network".
• Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

• 22 claim files (FROI, medical records, attorney correspondence)
• Prior claims history for all 22 claimants across all employers
• Treating physician billing records for the two flagged physicians
• Attorney-claimant relationship map
• Employer's incident reporting records

Attachments: Documents (Documents)

You are a fraud investigator analyzing a workers compensation fraud network. I am attaching:

Work only from the attached source files. If a conclusion is not supported, say so.

Produce:
1. Map the network: which claimants share attorneys, physicians, or prior claims? Identify the hub connections.
2. Analyze the injury patterns: are the injury types and body parts concentrated in ways inconsistent with the job duties of the claimants?
3. Flag medical billing from the two physicians for treatment patterns inconsistent with the injury types: excessive MRIs, extended PT, or opioid prescriptions.
4. Assess the late reporting pattern—9-day average vs. industry standard 2-day—and identify what the claimants were doing in the gap period.
5. Tell me whether to refer this to the state WC fraud bureau, what a special investigation unit needs to prioritize, and whether the employer has a subrogation claim.

Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.

What to expect

• Claimant-attorney-physician network map
• Injury pattern analysis vs. job duty
• Medical billing anomaly register
• Late reporting gap analysis
• Referral checklist and subrogation assessment

Review before you act

• Validate this output against source files before relying on it: Map the network: which claimants share attorneys, physicians, or prior claims? Identify the hub connections.
• Validate this output against source files before relying on it: Analyze the injury patterns: are the injury types and body parts concentrated in ways inconsistent with the job duties of the claimants?.
• Validate this output against source files before relying on it: Flag medical billing from the two physicians for treatment patterns inconsistent with the injury types: excessive MRIs, extended PT, or opioid prescriptions.
• Validate this output against source files before relying on it: Assess the late reporting pattern—9-day average vs. industry standard 2-day—and identify what the claimants were doing in the gap period.
• Confirm every cited figure, date, counterparty, or requirement against the attached originals — models compress and can drop a qualifier.
• Treat disagreement between models as a review item, especially on classification, materiality, and recommended next action.
• Do not authorize an operational, clinical, legal, credit, or enforcement action solely because the models agree.