Healthcare Billing Anomaly Records
This dataset provides detailed records of healthcare billing events flagged for potential fraud or errors, including anomaly types, severity, financial details, and review statuses. It enables robust revenue cycle analytics, compliance monitoring, and supports investigations into improper billing practices. The structured schema facilitates integration with fraud detection systems and regulatory reporting.
Sample rows
preview · 8 of 200 rows · all 21 columns| anomaly_idstring | anomaly_severitystring | anomaly_scorefloat | procedure_codestring | billing_event_idstring | patient_idstring | provider_idstring | facility_idstring | service_datedate | billing_datedate | diagnosis_codestring | billed_amountfloat | paid_amountfloat | payer_typestring | anomaly_typestring | flagged_bystring | flagged_timestampdatetime | review_statusstring | reviewed_bystring | reviewed_timestampdatetime | notesstring |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| A0001 | high | 87.4 | CPT99213 | B10001 | P20001 | PR3001 | F4001 | 2023-06-18 | 2023-06-19 | E119 | 143.25 | 143.25 | insurance | upcoding | ml_model | 2023-06-19T14:12:41 | under_review | blank | blank | ML model flagged high upcoding risk. Provider PR3001 under review. |
| A0002 | medium | 59.1 | CPT99214 | B10002 | P20002 | PR3002 | F4002 | 2023-06-21 | 2023-06-22 | I10 | 202.5 | 0 | self-pay | missing_documentation | rules_engine | 2023-06-22T09:35:00 | pending | blank | blank | Documentation incomplete for billed procedure. |
| A0003 | low | 18.8 | HCPCSJ1885 | B10003 | P20003 | PR3003 | blank | 2023-06-20 | 2023-06-23 | blank | 0 | 0 | other | other | rules_engine | 2023-06-23T10:22:19 | pending | blank | blank | blank |
| A0004 | critical | 99.8 | CPT93000 | B10004 | P20004 | PR3004 | F4003 | 2023-05-30 | 2023-06-03 | R079 | 82 | 0 | government | duplicate_billing | manual_review | 2023-06-04T08:00:00 | confirmed | REV_Team01 | 2023-06-05T09:12:00 | Duplicate billing confirmed by QA; flagged as critical. |
| A0005 | medium | 53.2 | CPT80050 | B10005 | P20005 | PR3005 | F4004 | 2023-06-01 | 2023-06-02 | E669 | 176.4 | 0 | insurance | unbundling | rules_engine | 2023-06-02T15:11:11 | under_review | blank | blank | Possible unbundling detected. Awaiting further review. |
| A0006 | low | 27.7 | CPT99212 | B10006 | P20006 | PR3006 | F4002 | 2023-06-04 | 2023-06-06 | J189 | 70 | 0 | self-pay | missing_documentation | rules_engine | 2023-06-06T16:09:22 | pending | blank | blank | blank |
| A0007 | medium | 46.9 | CPT85025 | B10007 | P20007 | PR3007 | F4005 | 2023-06-08 | 2023-06-08 | D649 | 118.5 | 118.5 | insurance | unbundling | rules_engine | 2023-06-08T11:28:40 | under_review | blank | blank | Potential unbundling of standard panel. |
| A0008 | high | 91.2 | CPT70450 | B10008 | P20008 | PR3001 | F4006 | 2023-06-03 | 2023-06-05 | S060X0A | 250 | 0 | government | medically_unlikely_edit | ml_model | 2023-06-06T09:50:12 | resolved | QA_Team04 | 2023-06-07T08:30:00 | Exceeded typical billing for this service type. |
| A0009 | medium | 66 | CPT96372 | B10009 | P20009 | PR3008 | F4007 | 2023-06-10 | 2023-06-11 | Z79899 | 85 | 85 | insurance | duplicate_billing | ml_model | 2023-06-11T16:33:20 | under_review | blank | blank | Possible duplicate detected; flagged by ML. |
| A0010 | critical | 99.7 | CPT12345 | B10010 | P20010 | PR3009 | blank | 2023-06-14 | 2023-06-16 | F329 | 0.01 | 0 | other | other | manual_review | 2023-06-16T19:03:03 | confirmed | LabQA | 2023-06-17T10:00:00 | Edge: near-zero amount flagged as critical outlier. |
| A0011 | low | 24.5 | CPT71020 | B10011 | P20011 | PR3010 | F4008 | 2023-06-15 | 2023-06-16 | J189 | 75.85 | 0 | self-pay | missing_documentation | rules_engine | 2023-06-16T13:10:10 | pending | blank | blank | Self-pay patient missing required forms. |
| A0012 | high | 88.5 | CPT36415 | B10012 | P20012 | PR3011 | F4009 | 2023-06-16 | 2023-06-19 | E039 | 50 | 0 | government | unbundling | ml_model | 2023-06-19T09:44:27 | confirmed | REV_Team02 | 2023-06-20T09:25:00 | High-risk unbundling, confirmed by team review. |
| A0013 | critical | 100 | CPT00000 | B10013 | P20013 | PR3012 | blank | 2023-05-23 | 2023-06-01 | blank | 99999.99 | 50000 | other | upcoding | manual_review | 2023-06-02T12:00:00 | dismissed | YearEndQC | 2023-06-03T09:00:00 | Edge: outlier transaction, invalid code. |
| A0014 | high | 85.6 | CPT99215 | B10014 | P20014 | PR3013 | F4010 | 2023-06-19 | 2023-06-21 | E119 | 210 | 0 | insurance | upcoding | ml_model | 2023-06-22T08:23:07 | under_review | blank | blank | Suspected upcoding, flagged by ML model. |
| A0015 | medium | 48.9 | HCPCSJ9202 | B10015 | P20015 | PR3014 | blank | 2022-12-22 | 2023-01-02 | C509 | 250 | 0 | government | unbundling | manual_review | 2023-01-04T17:55:00 | resolved | EdgeQA | 2023-01-06T13:00:00 | Delayed billing, long lag detected. |
| A0016 | medium | 70.3 | CPT99203 | B10016 | P20016 | PR3015 | F4011 | 2023-06-18 | 2023-06-19 | R509 | 185 | 185 | insurance | duplicate_billing | ml_model | 2023-06-19T10:18:18 | pending | blank | blank | Potential duplicate, patient P20016. |
| A0017 | medium | 41.6 | CPT99214 | B10017 | P20017 | PR3016 | F4012 | 2023-06-11 | 2023-06-13 | E779 | 200 | 0 | self-pay | missing_documentation | rules_engine | 2023-06-13T12:46:22 | pending | blank | blank | Self-pay: missing documentation for procedure. |
| A0018 | high | 84.2 | CPT80061 | B10018 | P20018 | PR3017 | F4013 | 2023-06-15 | 2023-06-16 | E780 | 135 | 0 | insurance | upcoding | ml_model | 2023-06-16T17:10:55 | under_review | blank | blank | Upcoding pattern detected by ML. |
| A0019 | high | 92.7 | CPT93010 | B10019 | P20019 | PR3018 | F4014 | 2023-06-13 | 2023-06-14 | I10 | 95 | 0 | government | medically_unlikely_edit | manual_review | 2023-06-15T08:00:00 | resolved | QA_Team05 | 2023-06-16T10:45:00 | Exceeded billing limits; resolved after review. |
| A0020 | low | 8.1 | HCPCSJ1050 | B10020 | P20020 | PR3019 | blank | 2023-06-01 | 2023-06-04 | blank | 0 | 0 | other | other | rules_engine | 2023-06-04T12:10:10 | pending | blank | blank | blank |
What the 200 rows show
from the 200-row sampleLow (anomaly severity) stands out: mean anomaly_
- 68.2median anomaly_
score - 3flagged_
by values - 4payer types
- 5review statuses
- 6anomaly types
- 95.0median billed_
amount
Median 68.2, from 0.50 to 100.0.
- string 14
- float 3
- date 2
- datetime 2
Columns
21 columns in three groups| column | type | description | example |
|---|---|---|---|
| Text 14 columns | |||
anomaly_id | string | Unique identifier for each flagged billing anomaly event.unique | A0001 |
billing_event_id | string | Unique identifier for the original billing event associated with the anomaly. | B10001 |
patient_id | string | Unique identifier for the patient involved in the billing event. | P20001 |
provider_id | string | Unique identifier for the healthcare provider or practitioner responsible for the billing event. | PR3001 |
facility_id | string | Unique identifier for the healthcare facility where the service was provided.optional | F4001 |
procedure_code | string | Standardized code (e.g., CPT, HCPCS) for the medical procedure or service billed. | CPT99213 |
diagnosis_code | string | Primary diagnosis code (e.g., ICD-10) associated with the billing event.optional | E119 |
payer_type | string | Type of payer responsible for the payment (e.g., insurance, self-pay, government).insurance · self-pay · government · other · optional | insurance |
anomaly_type | string | Category of the anomaly detected (e.g., upcoding, duplicate billing, unbundling, medically unlikely edit).6 values | upcoding |
anomaly_severity | string | Severity level of the anomaly (e.g., low, medium, high, critical).low · medium · high · critical | high |
flagged_by | string | Source or system that flagged the anomaly (e.g., rules_engine, ML_model, manual_review).rules_engine · ml_model · manual_review · other | ml_model |
review_status | string | Current status of the anomaly review process (e.g., pending, under_review, confirmed, dismissed, resolved).pending · under_review · confirmed · dismissed · resolved | under_review |
reviewed_by | string | Identifier of the reviewer or team who last updated the review status.optional | REV_Team01 |
notes | string | Additional comments or notes regarding the anomaly, investigation, or resolution.optional | Unbundled panel billing. |
| Numbers 3 columns | |||
billed_amount | float | Total amount billed for the event, in the facility's local currency.0 or more | 143.25 |
paid_amount | float | Amount paid by insurer or patient for the billing event.0 or more · optional | 143.25 |
anomaly_score | float | Numerical score indicating the likelihood or risk level of the anomaly (e.g., 0-1 or 0-100).0 to 100 · optional | 87.4 |
| Dates and times 4 columns | |||
service_date | date | Date when the billed service was provided. | 2023-06-18 |
billing_date | date | Date when the billing event was recorded or submitted. | 2023-06-19 |
flagged_timestamp | datetime | Date and time when the anomaly was flagged. | 2023-06-19T14:12:41 |
reviewed_timestamp | datetime | Date and time when the review status was last updated.optional | 2023-06-05T09:12:00 |
Use it for
A healthcare dashboard
Anomaly_
score by anomaly_ severity and a breakdown of procedure_ code. Excel, Power BI or Tableau. Why do the 30 low rows have a mean anomaly_
score of 14.3? A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
- Anomalies200A000187.4highA000259.1mediumA000318.8low
A software demo
Believable anomalies with billing_
event_ id, patient_ id and provider_ id to fill a screen in front of a buyer.
This dataset200 rows21 columns
Yours1,000 rows21 columns
blueprint · healthcare-billing-anomaly-records
Behind this dataset
Same schema. As many rows as you need.
These 200 rows came out of a blueprint — 21 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.
Rules it was built with
- Each record linked to claim and patient ID.
- Classified as anomaly or non-anomaly by ruleset.
- Includes payer and service code details.
- Reasons for anomaly are categorized.
Open the blueprint in Data Factory
1 credit per row. Preview 20 rows free. Buy rows for the full run.
- Exports
- CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
- Licence
- yours to use, including commercially
- API slug
- healthcare-billing-anomaly-records