Healthcare Fraud Detection Dataset with ICD-10 and CPT Codes

Realistic medical insurance claims data includes standardized ICD-10 and CPT procedure codes. The dataset originates from the Kaggle platform, but its author, size, and last update date are unspecified. Its primary purpose is to support the development of models for detecting fraudulent or anomalous billing patterns.

Use Cases

• Train anomaly detection models based on patterns in ICD-10 diagnosis codes.
• Develop classifiers to flag suspicious claims based on combinations of CPT procedure codes and diagnoses.
• Analyze billing patterns to identify potential upcoding or unbundling of services.
• Benchmark fraud detection algorithms using realistic, code-based medical claims data.

Strengths

• Includes realistic medical claims data, a domain with high practical relevance.
• Features standardized medical coding systems (ICD-10, CPT), which aid in feature engineering and model generalization.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kaggle