Health data research and education

Synthetic Medical IoT datasets for health-data research

Medical IoT records provide synthetic physiological time series that include vital-sign signals and glucose-model outputs for research, education, and machine-learning experiments.

Generate a dataset Explore original records

Experimental Engine — Under Scientific Review

This domain is an early-stage research prototype. Its models, units, temporal behaviour, and event semantics are being audited. Outputs should not be treated as empirically validated observations.

engine 3.2.0 · maturity experimental · validation audit_pending

Not for clinical use

These records provide no clinical decision support and do not substitute for patient data, diagnosis, or medical guidance. They contain no real patient records.

Research scope

These records do not provide clinical decision support and do not substitute for patient data, diagnosis, or medical guidance.

Vital signs, oxygen saturation, heart rate, blood pressure, and glucose-related series

Synthetic health-data scenarios for research and educational model development

Column schema

Every record in this domain emits the same 12 columns . Types and ranges below are read from the generator itself, so they cannot drift from the files it produces.

Column	Type	Range
Timestamp	datetime	—
Patient_ID	string	—
Age_Group	categorical	—
Heart_Rate_bpm	integer	30, 200
BP_Systolic_mmHg	integer	70, 220
BP_Diastolic_mmHg	integer	40, 130
SpO2_Pct	float	70, 100
Temperature_C	float	35, 42
Respiratory_Rate	integer	8, 45
Glucose_mg_dL	integer	50, 400
Activity_Level	categorical	—
Health_Status	categorical	—

Generative models

Values come from explicit equations, not from a trained generative model. Each component below is documented in the methodology.

Heart rate

Circadian baseline with AR(1) variation.

Blood pressure

Heart-rate to blood-pressure coupling.

Glucose and insulin

Bergman Minimal Model, a three-state ODE integrated with RK4: dG/dt = -(p1 + X)G + p1.Gb + D(t); dX/dt = -p2.X + p3(I - Ib).

Acuity scoring

NEWS2

NEWS2 scoring across the vital-sign set.

Research uses

The common thread is known ground truth: the generator records the true state alongside the observation of it, which a real deployment cannot supply.

Vital-sign anomaly detection without data-governance delay

Glucose-response modelling from a documented ODE

Early-warning score validation

Teaching health-data methods where real records cannot be shared

Measured datasets in this area remain the reference for site realism. A generator answers a different question: what a method does when the true state is known and the scenario can be set deliberately. These are complements, not substitutes.

Measured dataset	What it provides	What a generated record adds
MIMIC-III Waveform	Intensive-care physiological waveforms.	No data-use agreement or governance delay, and no disclosure risk.
WESAD	Wearable stress and affect detection, 15 subjects.	Arbitrary subject counts rather than a fixed small cohort.
MIT-BIH Arrhythmia	Annotated ECG recordings.	A documented glucose-insulin ODE alongside the vital-sign channels.

Scope and limits

What is currently established

— The generator runs and emits its declared column contract.
— Output is deterministic for a given domain, parameter set and seed.
— Scientific audit of its models, units, temporal behaviour and event semantics is still outstanding.

What it does not establish

— Site realism, or transfer to any specific real deployment.
— Calibration against a named site, sensor network, fleet or population.

Read the full research record →

Browse Medical IoT generated records

Each card links to the original citable record. IoTSyn keeps that URL, its dataset file, and its citation guidance unchanged.

Open the full library