Medical Device Sensor Streams

This dataset contains granular, timestamped sensor readings from wearable medical devices, including user and device identifiers, sensor types, measured values, and contextual metadata. It enables advanced research in health monitoring, anomaly detection, device performance, and personalized care analytics, supporting both clinical and consumer health applications.

  • last updated 22 Jul 2025
  • by GoMask
The brief that made it

Continuous health monitoring and early anomaly detection for patients

Sample rows

preview · 8 of 200 rows · all 14 columns
stream_idstringsensor_statusstringsensor_valuefloatanomaly_flagbooleandevice_modelstringdevice_idstringuser_idstringtimestampdatetimesensor_typestringunitstringfirmware_versionstringlocation_latitudefloatlocation_longitudefloatnotesstring
STRM0000001normal74.3falseMedWear Pro X1DEV0001USER00012024-05-01T08:10:19Zheart_ratebpmv1.2.037.7749-122.4194User walking to work
STRM0000002normal36.9falseCardioBand L2DEV0002USER00022024-05-01T08:15:22ZtemperatureCelsiusv3.4.140.7128-74.006Resting after mild exercise
STRM0000003normal98.2falseMedWear Pro X1DEV0001USER00032024-05-01T08:16:37Zspo2%v1.2.0blankblankIndoor reading
STRM0000004normal0.02falsePulseSense ZDEV0003USER00042024-05-01T08:19:09Zaccelerometergv2.0.534.0522-118.2437User sitting, minimal movement
STRM0000005normal0.9falseHeartFit SDEV0004USER00052024-05-01T08:21:10ZecgmVv5.1.252.5213.405Relaxed, reading a book
STRM0000006calibrating16falseRespiraBand 2DEV0005USER00062024-05-01T08:23:45Zrespiratory_ratebpmv4.0.048.85662.3522Calibration in progress
STRM0000007normal122falsePulseSense ZDEV0003USER00042024-05-01T08:24:30Zblood_pressuremmHgv2.0.534.0522-118.2437BP check after morning coffee
STRM0000008normal0.02falseCardioBand L2DEV0002USER00072024-05-01T08:26:55Zgyroscopegv3.4.140.7128-74.006Turning head left

What the 200 rows show

from the 200-row sample
  • 16%anomaly_flag = true
  • 25.3median sensor_value
  • 9sensor types
  • 11units
sensor_status200 rows by value
085170161normal81%15error8%8low_b…4%2disco…1%10calib…5%4unkno…2%
sensor_value200 rows, in bands of 25
05010039728133218801-25100200sensor_value →

Median 25.3, from -1.5 to 189.0.

device_model200 rows · top 10 of 34 values
  1. PulseTrack V213
  2. BioSense-G49
  3. AirMon 3.08
  4. FitMonitor X8
  5. MedWear Pro X17
  6. HeartFit S7
  7. RespiraBand 27
  8. OxyPro-57
  9. CardioBand L26
  10. PulseSense Z6
14 columns by typefrom the column list below
  • string 9
  • float 3
  • datetime 1
  • boolean 1

Columns

14 columns in four groups
blueprint · 14 columns
columntypedescriptionexample
Text 9 columns
stream_idstringUnique identifier for each sensor data stream from a device.uniqueSTRM0000001
device_idstringUnique identifier for the wearable medical device generating the data.DEV0001
user_idstringUnique identifier for the user or patient wearing the device.USER0001
sensor_typestringType of sensor that generated the reading (e.g., heart_rate, temperature, spo2, accelerometer, ecg).9 valuesheart_rate
unitstringUnit of measurement for the sensor value (e.g., bpm, Celsius, %, mmHg, g, mV).11 unitsbpm
sensor_statusstringOperational status of the sensor at the time of reading (e.g., normal, error, low_battery, disconnected).6 values · optionalnormal
device_modelstringModel name or number of the wearable device.optionalMedWear Pro X1
firmware_versionstringFirmware version of the device at the time of data capture.optionalv1.2.0
notesstringFree-text notes or comments related to the reading (e.g., user activity, device placement).optionalUser walking to work
Numbers 3 columns
sensor_valuefloatMeasured value from the sensor (unit depends on sensor_type).74.3
location_latitudefloatLatitude where the reading was taken, if available.-90 to 90 · optional37.7749
location_longitudefloatLongitude where the reading was taken, if available.-180 to 180 · optional-122.4194
Dates and times 1 column
timestampdatetimeDate and time when the sensor reading was recorded (in UTC).2024-05-01T08:10:19Z
True or false 1 column
anomaly_flagbooleanIndicates if the reading was flagged as an anomaly by the device or monitoring system.optionalfalse

Use it for

  • anomaly flag16%31 of 200 rowsmean sensor value by …44.0norm…51.2error79.9low_…30.9disc…

    A healthcare dashboard

    The anomaly_flag rate, sensor_value by sensor_status and a breakdown of device_model. Excel, Power BI or Tableau.

  • Why do 31 of 200 rows have anomaly_flag = true?

    A class exercise

    Hand out the rows and one question. Everyone works from the same 200 rows.

  • A software demo

    Believable streams with device_id, user_id and timestamp to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 14 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset200 rows14 columns
Yours1,000 rows14 columnslocation_latitude: UK only

blueprint · medical-device-sensor-streams

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 14 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
  • Streams include heart rate, SpO2, and accelerometer readings.
  • Data is anonymized and grouped by patient ID.
  • Events like falls or irregularities are timestamped.
  • Each patient has at least 24 hours of data.
  • Device calibration metadata is included.
Rows
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
medical-device-sensor-streams

More in Healthcare

Browse all
Also in HealthcareMedical Device Usage AnalyticsHospital Readmission Prediction DatasetPharmacy Retail Purchase EventsAll 1,966 datasets

What should your data show?

Preview 20 rows free
No signup. No card.