Healthcare
20 columns
200 rows
8 formats

Medical Billing Code Prediction

This dataset provides comprehensive, labeled clinical visit records including patient demographics, provider information, diagnosis and procedure billing codes, and billing outcomes. It is designed for automating and improving medical billing processes, supporting predictive analytics, and enabling robust healthcare revenue cycle management.

last updated 20 Aug 2025
by GoMask

The brief that made it

Automated billing code prediction for healthcare providers

Sample rows

preview · 8 of 200 rows · all 20 columns

visit_idstring	visit_typestring	billing_amountfloat	secondary_diagnosis_codestring	patient_idstring	provider_idstring	visit_datedate	chief_complaintstring	diagnosis_codestring	procedure_codestring	procedure_descriptionstring	secondary_diagnosis_descriptionstring	secondary_procedure_codestring	secondary_procedure_descriptionstring	patient_ageinteger	patient_genderstring	insurance_typestring	payment_statusstring	diagnosis_descriptionstring	notesstring
VISIT0001	outpatient	175	blank	PAT1001	PROV2001	2024-06-18	Annual physical examination	Z00.00	99385	Initial comprehensive preventive medicine evaluation	blank	blank	blank	34	female	private	paid	Encounter for general adult medical examination	Patient advised to follow up in one year for next routine checkup.
VISIT0002	outpatient	120	blank	PAT1002	PROV2002	2024-05-21	Persistent cough	J41.0	99213	Office or other outpatient visit for evaluation	blank	blank	blank	27	male	private	paid	Simple chronic bronchitis	Prescribed inhaler; advised to return if symptoms worsen.
VISIT0003	outpatient	95	blank	PAT1003	PROV2003	2024-06-12	Skin rash	L30.9	99212	Office visit for problem-focused evaluation	blank	blank	blank	22	female	medicaid	paid	Dermatitis, unspecified	Topical corticosteroid cream prescribed; follow-up in two weeks.
VISIT0004	telehealth	135	G47.00	PAT1004	PROV2001	2024-06-10	Insomnia and anxiety	F41.1	99443	Telephone evaluation and management service	Insomnia, unspecified	blank	blank	41	female	private	paid	Generalized anxiety disorder	Medication adjustment discussed; recommend CBT referral.
VISIT0005	inpatient	17200.5	I10	PAT1005	PROV2004	2023-11-03	Hip fracture after fall	S72.001A	27130	Total hip arthroplasty	Essential (primary) hypertension	93010	Electrocardiogram interpretation	82	female	medicare	pending	Fracture of right femur	Patient admitted for surgery; discharge planning with PT scheduled.
VISIT0006	emergency	12850	E78.5	PAT1006	PROV2005	2023-10-14	Chest pain and shortness of breath	I21.9	92928	Percutaneous coronary intervention	Hyperlipidemia, unspecified	93005	Electrocardiogram, tracing only	70	male	medicare	partial	Acute myocardial infarction, unspecified	Patient stabilized, transferred to cardiology for observation.
VISIT0007	outpatient	160	blank	PAT1007	PROV2002	2024-05-29	Follow-up for type 2 diabetes	E11.9	83036	Hemoglobin A1c test	blank	blank	blank	58	male	private	paid	Type 2 diabetes mellitus without complications	Labs ordered; patient instructed on dietary modifications.
VISIT0008	telehealth	110	blank	PAT1008	PROV2006	2024-04-09	Depressed mood	F32.9	99444	Online evaluation and management	blank	blank	blank	36	male	private	paid	Major depressive disorder, single episode, unspecified	Started SSRI; follow-up scheduled in four weeks.
VISIT0009	emergency	1490	R56.9	PAT1009	PROV2003	2022-09-22	Seizure episode	G40.909	95812	Electroencephalogram, extended	Unspecified convulsions	blank	blank	14	male	medicaid	pending	Epilepsy, unspecified, not intractable	Observed for 12 hours; neurology consult completed.
VISIT0010	inpatient	20400	E11.9	PAT1010	PROV2004	2024-06-02	Stroke symptoms	I63.9	70450	CT scan, head or brain	Type 2 diabetes mellitus without complications	93000	Electrocardiogram, complete	77	female	medicare	pending	Cerebral infarction, unspecified	Patient admitted to neurology; rehabilitation consult placed.
VISIT0011	outpatient	65	blank	PAT1011	PROV2001	2024-06-01	Blood pressure check	I10	99211	Office or other outpatient visit, minimal	blank	blank	blank	52	male	private	paid	Essential (primary) hypertension	BP readings recorded; medication unchanged.
VISIT0012	outpatient	80	blank	PAT1012	PROV2002	2024-05-20	Routine immunization	Z23	90471	Immunization administration, single vaccine	blank	blank	blank	5	female	medicaid	paid	Encounter for immunization	Vaccines administered; mother instructed on fever management.
VISIT0013	emergency	700	blank	PAT1013	PROV2003	2023-03-09	Asthma attack	J45.909	94060	Bronchodilation responsiveness	blank	blank	blank	10	male	medicaid	paid	Unspecified asthma, uncomplicated	Patient stabilized in ED; prescription updated.
VISIT0014	inpatient	6200	E86.0	PAT1014	PROV2005	2024-05-30	Acute abdominal pain	K35.80	44970	Laparoscopic appendectomy	Dehydration	blank	blank	25	male	self-pay	partial	Acute appendicitis, unspecified	Surgery successful; patient observed for 48 hours, then discharged.
VISIT0015	telehealth	95	blank	PAT1015	PROV2006	2024-05-26	Medication refill request	Z76.0	99443	Telephone evaluation and management service	blank	blank	blank	56	female	private	paid	Encounter for issue of repeat prescription	Prescription renewed; patient reminded of medication side effects.
VISIT0016	outpatient	150	blank	PAT1016	PROV2001	2024-06-19	Lower back pain	M54.5	97110	Therapeutic exercises	blank	blank	blank	44	male	private	pending	Low back pain	Recommended PT referral; follow-up in two weeks.
VISIT0017	outpatient	175	F41.9	PAT1017	PROV2002	2024-04-15	Allergic rhinitis	J30.9	95004	Allergy testing, percutaneous	Anxiety disorder, unspecified	blank	blank	31	female	private	paid	Allergic rhinitis, unspecified	Patient given antihistamines; instructed on allergen avoidance.
VISIT0018	outpatient	150	blank	PAT1018	PROV2003	2024-06-18	Routine pap smear	Z12.4	88142	Cytopathology, cervical or vaginal	blank	blank	blank	28	female	private	paid	Encounter for screening for malignant neoplasm of cervix	Results pending; advised to return for results in two weeks.
VISIT0019	telehealth	95	blank	PAT1019	PROV2004	2024-05-22	Follow-up for depression	F33.1	99443	Telephone evaluation and management service	blank	blank	blank	25	male	private	paid	Major depressive disorder, recurrent, moderate	Patient reports improvement; continue current regimen.
VISIT0020	outpatient	110	blank	PAT1020	PROV2005	2024-06-07	Sprained ankle	S93.401A	97140	Manual therapy techniques	blank	blank	blank	20	male	medicaid	paid	Sprain of unspecified ligament of right ankle	Recommended RICE protocol; follow-up if not improved.

What the 200 rows show

from the 200-row sample

Inpatient (visit type) stands out: mean billing_amount is 13,172, against 852.1 for the rest.

135.0median billing_amount
3patient genders
4payment statuses
5insurance types
12providers
40median patient_age

Mean billing_amount by visit_type200 rows

billing_amount200 rows, in bands of 2,500

Median 135.0, from 60.0 to 21,500.

secondary_diagnosis_code59 rows with a value · 141 left blank

I107
E11.96
E86.05
E78.53
R06.023
T81.43
G47.002
V89.2XXA2
R10.92
J30.12

20 columns by typefrom the column list below

string 17
integer 1
float 1
date 1

Columns

20 columns in three groups

blueprint · 20 columns
column	type	description	example
Text 17 columns
`visit_id`	string	Unique identifier for the clinical visit recordunique	VISIT0001
`patient_id`	string	Unique identifier for the patient associated with the visit	PAT1001
`provider_id`	string	Unique identifier for the healthcare provider conducting the visit12 providers	PROV2001
`visit_type`	string	Type of visit (e.g., outpatient, inpatient, emergency)outpatient · inpatient · emergency · telehealth · other	outpatient
`chief_complaint`	string	Primary reason for the clinical visit as described by the patientoptional	Persistent cough
`diagnosis_code`	string	Primary diagnosis billing code (e.g., ICD-10)	Z00.00
`diagnosis_description`	string	Text description of the primary diagnosisoptional	Dermatitis, unspecified
`procedure_code`	string	Primary procedure billing code (e.g., CPT)	99385
`procedure_description`	string	Text description of the primary procedure performedoptional	Total hip arthroplasty
`secondary_diagnosis_code`	string	Secondary diagnosis billing code, if applicableoptional	G47.00
`secondary_diagnosis_description`	string	Text description of the secondary diagnosisoptional	Insomnia, unspecified
`secondary_procedure_code`	string	Secondary procedure billing code, if applicableoptional	93010
`secondary_procedure_description`	string	Text description of the secondary procedure performedoptional	CT scan, head or brain
`patient_gender`	string	Gender of the patientmale · female · other · unknown	female
`insurance_type`	string	Type of insurance coverage for the visitprivate · medicare · medicaid · self-pay · other · optional	private
`payment_status`	string	Status of billing payment for the visitpaid · pending · denied · partial · unknown · optional	paid
`notes`	string	Additional clinical or billing notes relevant to the visitoptional	Patient advised to follow…
Numbers 2 columns
`patient_age`	integer	Age of the patient at the time of visit0 to 120	34
`billing_amount`	float	Total amount billed for the visit0 or more	175
Dates and times 1 column
`visit_date`	date	Date of the clinical visit	2024-06-18

Use it for

A healthcare dashboard
Billing_amount by visit_type and a breakdown of secondary_diagnosis_code. Excel, Power BI or Tableau.
Why do the 35 inpatient rows have a mean billing_amount of 13,172?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Visits200
VISIT0001175outpatie…
VISIT0002120outpatie…
VISIT000395outpatie…
A software demo
Believable visits with patient_id, provider_id and visit_date to fill a screen in front of a buyer.

This dataset200 rows20 columns

Yours1,000 rows20 columns

blueprint · medical-billing-code-prediction

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 20 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

Visit summary features included
ICD/CPT code mapped per case
Multi-label outputs supported
Synthetic and privacy-compliant

Rows1,000 rows10,000 rows100,000 rows1,000,000 rows

Open the blueprint in Data Factory

1 credit per row. New accounts start with 25 free credits.

Exports: CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence: yours to use, including commercially
API slug: medical-billing-code-prediction

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Use it for

A healthcare dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Healthcare

What should your data show?