Healthcare datasets

Patient records, medical imaging, clinical trials

221 ready-made datasets
8 formats, Excel to Parquet
First download free

What the 221 cover1 square = 1 dataset

Patient care87
Hospital operations43
Pharmacy33
Claims & billing29
Devices & wearables17
Clinical trials12

Grouped by dataset title and tags.

Showing all 24 on this page

Devices & wearables

Healthcare Device Utilization Metrics

Device details, facility location, usage duration, operator roles

This dataset provides granular, timestamped records of medical device usage across healthcare facilities, including device details, facility location, usage duration, operator roles, and operational status. It enables healthcare organizations to analyze utilization patterns, optimize resource allocation, and inform procurement or maintenance strategies for critical medical equipment.

23 cols

device_name
device_type
utilization_type
device_status
+19

Open in factory

device_name: Siemens Magnetom Aera
device_type: MRI
utilization_type: patient

Pharmacy

Healthcare Patient Medication Adherence

Patient medication adherence, combining pharmacy pickup/refill records

This dataset provides a comprehensive view of patient medication adherence, combining pharmacy pickup/refill records with self-reported adherence and intervention tracking. It enables healthcare providers and researchers to identify nonadherence patterns, evaluate intervention effectiveness, and improve patient outcomes through targeted strategies.

21 cols

adherence_score
self_reported_adherence
medication_name
medication_dosage
+17

Open in factory

adherence_score: 0.97
self_reported_adherence: always
medication_name: Atorvastatin

Hospital operations

Hospital Staff Shift Schedules

Staff roles, departments, shift timings, and location information

This dataset provides detailed records of hospital staff shift schedules, including staff roles, departments, shift timings, and location information. It enables comprehensive workforce planning, shift optimization, and compliance tracking for healthcare operations. The dataset supports analysis of staffing patterns, overtime, and holiday coverage to improve hospital efficiency and patient care.

19 cols

staff_role
shift_start_time
shift_end_time
shift_type
+15

Open in factory

staff_role: Nurse
shift_type: Day
department: Emergency

Patient care

Patient Chronic Illness Progression

Longitudinal records of patients with chronic illnesses

This dataset provides detailed, longitudinal records of patients with chronic illnesses, capturing demographic information, diagnoses, visit-level observations, treatments, laboratory results, and outcomes. Designed for healthcare research and predictive analytics, it enables tracking of disease progression, treatment efficacy, and patient outcomes over time.

28 cols

sex
race_ethnicity
diagnosis_code
provider_specialty
+24

Open in factory

sex: male
race_ethnicity: Hispanic/Latino
diagnosis_code: I50.9

Claims & billing

Healthcare Billing Anomaly Records

Anomaly types, severity, financial details, and review statuses

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.

21 cols

anomaly_type
anomaly_severity
anomaly_score
billing_date
+17

Open in factory

anomaly_type: upcoding
anomaly_severity: high
anomaly_score: 87.4

Patient care

Patient Symptom Chat Conversations

Patient-health agent chat transcripts annotated with symptoms, advice

This dataset contains synthetic patient-health agent chat transcripts annotated with symptoms, advice, triage urgency ratings, and outcomes. It is ideal for developing and benchmarking conversational health AI, triage models, and patient interaction analytics, supporting research in digital health and clinical decision support.

18 cols

chat_start_datetime
chat_end_datetime
symptom_primary
symptom_secondary
+14

Open in factory

symptom_primary: headache
symptom_duration: 2 days
symptom_severity: 2

Patient care

Genomic Variant Disease Associations

Detailed genomic coordinates, variant types, disease associations

This dataset provides a comprehensive mapping of genetic variants to disease risk, including detailed genomic coordinates, variant types, disease associations, statistical evidence, and machine learning-based pathogenicity annotations. Designed for bioinformatics and ML research, it enables advanced analysis of genotype-phenotype relationships, risk prediction, and variant prioritization for clinical or research applications.

20 cols

variant_type
disease_name
association_type
chromosome
+16

Open in factory

variant_type: SNP
disease_name: Hereditary breast cancer
association_type: risk

Pharmacy

Healthcare Prescription Pattern Analysis

Patient demographics, prescriber characteristics, drug details

This dataset provides detailed synthetic records of prescription events, including patient demographics, prescriber characteristics, drug details, and prescription parameters. Designed for healthcare analytics, it enables the identification of unusual prescribing patterns, supports compliance monitoring, and facilitates research into medication usage trends and risk management.

20 cols

prescriber_specialty
prescription_status
prescription_date
drug_name
+16

Open in factory

prescriber_specialty: Internal Medicine
prescription_status: filled
drug_name: Sertraline

Devices & wearables

Healthcare Wearable Device Readings

Heart rate, steps, SpO2, and sleep stages, along with device

This dataset contains time-stamped, multi-vital sign readings from wearable health devices, including heart rate, steps, SpO2, and sleep stages, along with device and data quality metadata. Designed for health monitoring, anomaly detection, and longitudinal analysis, it enables researchers and clinicians to track user health trends, detect anomalies, and assess data reliability at scale.

11 cols

device_battery_level
heart_rate_bpm
steps_count
spo2_percent
+7

Open in factory

device_battery_level: 81
heart_rate_bpm: 75
steps_count: 0

Patient care

Clinical Notes Image Matching

Mapping between de-identified clinical notes

This dataset provides a comprehensive mapping between de-identified clinical notes and their corresponding diagnostic images, enabling advanced research in multi-modal AI for healthcare. Each entry includes rich metadata for both text and imaging, supporting tasks such as automated diagnosis, cross-modal retrieval, and explainable AI in clinical settings.

13 cols

image_type
image_file_path
match_confidence
image_date
+9

Open in factory

image_type: X-ray
image_file_path: /images/xray/P10001_20190312.png
match_confidence: 0.98

Patient care

Patient Health Risk Factor Scores

Demographic data, clinical measurements

This dataset provides detailed records of patient health risk assessments, including demographic data, clinical measurements, and calculated risk factor scores for chronic disease prediction. It is ideal for population health analytics, risk stratification, and supporting proactive care management in healthcare settings.

21 cols

risk_factor_score
risk_category
age
sex
+17

Open in factory

risk_factor_score: 7.4
risk_category: low
age: 27

Patient care

Healthcare Patient Acuity Levels

Simulated hospital patient admission records with detailed acuity scores

This dataset provides simulated hospital patient admission records with detailed acuity scores and categorical labels, supporting advanced triage modeling and resource planning. It includes patient demographics, diagnoses, admission details, and outcome data, making it ideal for healthcare analytics, operational optimization, and predictive modeling of patient care needs.

16 cols

acuity_score
acuity_level
admission_datetime
discharge_datetime
+12

Open in factory

acuity_score: 1.4
acuity_level: low
age: 0

Patient care

Healthcare Telemedicine Session Logs

Session timing, medical specialty, technical issues encountered

This dataset provides detailed, session-level logs of virtual healthcare visits, including session timing, medical specialty, technical issues encountered, and patient feedback. It enables comprehensive analysis of telemedicine operations, quality of care, and technical performance, supporting optimization of virtual healthcare delivery and patient satisfaction.

22 cols

session_start_time
session_end_time
session_duration_minutes
session_status
+18

Open in factory

session_duration_minutes: 35
session_status: completed
specialty: general_practice

Hospital operations

Patient Appointment No-show Logs

Patient demographics, appointment details, reminders

This dataset provides detailed logs of scheduled healthcare appointments, including patient demographics, appointment details, reminders, and attendance outcomes (attended, no-show, or cancelled). It enables comprehensive analysis of patient attendance patterns, supports predictive modeling for no-shows, and helps optimize healthcare resource allocation.

26 cols

patient_name
appointment_time
appointment_type
no_show
+22

Open in factory

patient_name: Ava Müller
appointment_type: immunization
no_show: false

Clinical trials

Clinical Trial Patient Records

Patient demographics, treatment assignments, progress tracking

This dataset provides comprehensive, subject-level records from simulated clinical trials, including patient demographics, treatment assignments, progress tracking, and outcome measures. It supports robust biostatistical analyses and machine learning applications for clinical research, safety monitoring, and predictive modeling of trial outcomes.

20 cols

age
sex
race_ethnicity
treatment_group
+16

Open in factory

age: 42
sex: female
race_ethnicity: White

Patient care

Labeled Healthcare Image Annotations

Labeled medical images (such as X-rays

This dataset contains synthetic, labeled medical images (such as X-rays and MRIs) with detailed annotations for use in computer vision model training and diagnostic tool development. Each record includes image metadata, patient demographics, annotation details (including spatial data and confidence scores), and diagnostic labels, making it ideal for research, benchmarking, and algorithm validation in medical imaging.

20 cols

image_modality
image_width
image_height
image_resolution_dpi
+16

Open in factory

image_modality: X-ray
image_width: 2048
image_height: 2048

Hospital operations

Hospital Readmission Risk Factors

Hospital admissions, capturing patient demographics, clinical diagnoses

This dataset provides detailed records of hospital admissions, capturing patient demographics, clinical diagnoses, procedures, comorbidities, and key risk factors for readmission. Designed for healthcare analytics, it enables predictive modeling, quality improvement, and targeted intervention strategies to reduce hospital readmissions and improve patient outcomes.

29 cols

readmitted_within_30_days
hospital_department
age
race
+25

Open in factory

readmitted_within_30_days: false
hospital_department: cardiology
age: 78

Hospital operations

Doctor Appointment Scheduling Patterns

Patient demographics, appointment timing, booking channels

This dataset provides detailed records of doctor appointment bookings, including patient demographics, appointment timing, booking channels, and status outcomes. It enables analysis of scheduling patterns, resource utilization, and patient engagement, supporting data-driven optimization of healthcare operations and reduction of idle doctor time.

24 cols

appointment_start_time
appointment_end_time
appointment_status
doctor_name
+20

Open in factory

appointment_status: completed
doctor_name: Dr. Michael Carter
doctor_specialty: Cardiologist

Hospital operationsTop 10 most opened

Hospital Readmission Prediction Dataset

Demographics, diagnoses, treatments, medications, and outcomes

This dataset provides comprehensive, visit-level hospital data for predicting patient readmission risk, including demographics, diagnoses, treatments, medications, and outcomes. It enables advanced analytics and machine learning for care management, resource allocation, and quality improvement in healthcare settings. The dataset is ideal for developing predictive models, benchmarking hospital performance, and supporting population health initiatives.

24 cols

readmitted_within_30_days
age
race
primary_diagnosis_code
+20

Open in factory

readmitted_within_30_days: false
age: 74
race: white

Hospital operations

Medical Appointment No-Show Records

Patient demographics, health conditions, appointment details, reminders

This dataset provides detailed records of medical appointments, including patient demographics, health conditions, appointment details, reminders, and attendance outcomes. It enables analysis of no-show patterns, the impact of reminders, and patient history to optimize healthcare resource utilization and improve patient engagement.

28 cols

appointment_time
previous_appointments
appointment_type
appointment_date
+24

Open in factory

previous_appointments: 5
appointment_type: checkup
age: 34

Pharmacy

Drug Prescription Adherence Records

Patient demographics, prescription details, adherence status

This dataset provides detailed records of patient adherence to prescribed medications, including patient demographics, prescription details, adherence status, and provider information. It enables healthcare providers and researchers to analyze medication compliance, identify patterns of non-adherence, and develop interventions to improve patient outcomes and reduce hospital readmissions.

16 cols

adherence_status
adherence_percentage
prescription_start_date
prescription_end_date
+12

Open in factory

adherence_status: adherent
adherence_percentage: 98.4
medication_name: Lisinopril

Hospital operations

Hospital Bed Turnover Rates

Timing, department, bed type, turnover reasons, and cleaning status

This dataset provides detailed records of hospital bed assignments and releases, including timing, department, bed type, turnover reasons, and cleaning status. It enables healthcare administrators to analyze bed utilization, optimize patient flow, and improve resource planning. The data supports operational efficiency studies and strategic decision-making in hospital management.

14 cols

hospital_name
bed_type
turnover_reason
bed_status_after_release
+10

Open in factory

hospital_name: Green Valley Medical Center
bed_type: ICU
turnover_reason: Discharge

Patient care

Patient Symptom Onset Tracking

Dates, severity, and confirmation status, to support disease monitoring

This dataset provides detailed tracking of patient symptom onset, including dates, severity, and confirmation status, to support disease monitoring and early intervention by healthcare professionals. It enables longitudinal analysis of symptoms, facilitates timely clinical response, and supports research into disease progression patterns.

10 cols

symptom_name
onset_date
severity_level
recorded_by
+6

Open in factory

symptom_name: Fever
severity_level: 6
recorded_by: nurse.james

Hospital operations

Clinical Equipment Utilization Logs

Daily logs of clinical equipment usage

This dataset provides detailed daily logs of clinical equipment usage, capturing information on equipment identity, usage times, staff operators, departments, and maintenance needs. It enables healthcare organizations to analyze utilization patterns, optimize equipment allocation, and proactively manage maintenance schedules for improved operational efficiency and patient care.

18 cols

equipment_name
equipment_type
utilization_status
department
+14

Open in factory

equipment_name: Siemens Magnetom Aera
equipment_type: MRI
utilization_status: completed

Real codes. Never real patients.

Code systems found in the sample rows of all 221 healthcare datasets.

Code systemDatasets using it, of 221

ICD-10diagnoses41I10 · E11.9 · J45.909
CPTprocedures2699213 · CPT99214 · 99233
NPIUS providers51865478910 · 4871920382 · 3042157890
LOINClab tests32345-7 · 718-7
CARCdenial reasons3CO16 · CO-16
NDCdrug products312345-6789-01 · 00093051230
DRGinpatient groups2291
HCCrisk adjustment2HCC18 · HCC19
MedDRAadverse events110029205

A patient from the EOB datasetGenerated

patient_first_name: Emily
patient_last_name: Stevens
patient_date_of_birth: 1986-05-14
patient_city: Springfield
service_code: 99213
service_description: Office/outpatient visit, established patient

Generated Real code

Most common columnsDatasets, of 221

patient_id159
provider_id54
department26
diagnosis_code24
medication_name21

Not quite what you need? Describe it.

One sentence in. A dataset with that pattern out.

Your sentence

Over-75s readmitted 2×
Real ICD-10 codes
3% missing dates

Preview 20 rows freeNo signup. No card.

30-day readmission rate by age

Sample rows for: Discharges from 6 wards, where patients over 75 are readmitted within 30 days twice as often, with real ICD-10 codes and 3% of discharge dates missing.
age	primary_dx	discharge_date	readmit_30d
81	I50.9	2024-03-14	yes
52	E11.9	2024-03-14	no
77	J44.1	—	yes
64	N18.3	2024-03-15	no

A pattern you asked for Everything else

What should your data show?

No signup. No card.