Insurance · Data integration + AI scoring

Proof of concept

Flagging suspicious claims before payout.

A proof of concept for a health insurance claims company that checks every claim against the patient's own medical record.

Client: A company that processes health insurance claims on behalf of patients.

Before

Every claim was checked by hand, one at a time. Reviewers had no quick way to see whether an expensive test or procedure matched the doctor's prescription or the patient's history. Claims that didn't add up were often paid anyway.

What we built

A proof of concept that links each claim to the patient's medical records, history and prescriptions. Business rules and a scoring model compare what was claimed with what the record supports, and flag any claim where the test or procedure doesn't fit the diagnosis, the prescription or the patient's history.

What we found

Most unsupported claims weren't hidden. They were simply never compared with the patient's record. Joining the data was what made them visible.

After

  • In testing on historical claims, the model caught around 30% of the suspicious claims before payout.
  • Reviewers spend their time on the riskiest claims instead of checking every one.
  • Each flag shows why: the claimed test next to the prescription and history it doesn't match.

Stack

  • Databricks
  • Python
  • SQL
  • Logistic regression

Illustrative

One claim side by side with the patient's record, with the mismatch highlighted and a risk score.Illustrative, with demo data. The claim lists a specialist scan. The patient's record shows a blood test prescription and nothing related in the history. The claimed test and the prescription are highlighted as a mismatch, and the claim's risk score reads high.ClaimPatient recordClaimed testSpecialist scanPrescriptionBlood testHistoryNothing relatedThe claimed test doesn't fit the recordRisk scoreHigh
Each claim sits next to the patient's record, so a claim that doesn't fit stands out before payout.

More case studies

Ready to see where your data stands?