What is wearable data science?
Wearable data science is the engineering work of extracting, processing and validating useful signals from wearable sensor data for clinical and commercial health applications. Consumer wearable analytics can tolerate approximation. Clinical wearable data science cannot: every pipeline component has to be deterministic, reproducible and defensible to a regulator. Raw accelerometer, gyroscope and photoplethysmography signals from devices like Apple Watch, Empatica, Samsung and ActiGraph go through preprocessing pipelines that normalise sampling rates, axes and units before the clinical algorithms compute anything. Cross-platform validation, meaning proof that the same algorithm gives equivalent results on devices with different sensor hardware, is a hard problem that ordinary data science work rarely meets. Engagements usually cover signal processing pipeline development, algorithm portability across hardware platforms and output validation against clinical reference standards. Devsort built and validated cross-platform wearable pipelines for PKG Health (now Empatica) covering five device platforms under FDA, CE and TGA requirements.
How does clinical wearable data science differ from consumer analytics?
Consumer wearable analytics (step counts, sleep summaries, resting heart rate trends) is built on aggregated population statistics, where individual errors average out. Clinical wearable data science works on individual patient data, and every sample matters. A misclassified movement event, a badly normalised accelerometer reading or an undetected sampling artefact can produce a clinically wrong output for a specific patient at a specific time.
The second difference is reproducibility. A clinical algorithm must give the same output for the same input every time, across hardware revisions, software environments and processing platforms. Building a preprocessing pipeline that guarantees this across five device types, each with its own sensor hardware, sampling rate and axis convention, is the central technical problem in clinical wearable data science.
Devsort's experience comes from building exactly this kind of pipeline for PKG Health's movement disorder monitoring system. The work required understanding the signal characteristics of each device at the hardware level before a single line of algorithm code could run on it.
The pipeline is one layer of a wearable product. If you also need the firmware, the companion app or the algorithms around it, our wearable app development service covers all four layers together.
How did we take PKG Health's algorithms cross-platform?
PKG Health's movement disorder algorithms were originally validated on a single hardware platform. Expanding the algorithm suite to run on Apple Watch, Samsung Galaxy Watch, Sony devices, Empatica E4, and ActiGraph required building a preprocessing pipeline from scratch. Its job was to normalise the raw output of five very different accelerometers into one input format the clinical algorithms could trust.
Each device has different axis orientation conventions, different sampling frequencies, different units, and different filter characteristics baked into the hardware. The preprocessing pipeline detects which device produced the data, applies the appropriate transformation, resamples to the algorithm's expected input frequency, and outputs a standardised signal. Every transformation was validated against clinical datasets to confirm that algorithm outputs were equivalent across platforms.
The same engagement also involved reimplementing a subset of the validated Python algorithms in embedded C for the Empatica wrist device, which moved the work from cloud processing to embedded real-time execution.
Wearable platforms we have worked with
Frequently asked questions
How does signal processing differ between consumer and clinical wearables?
Consumer signal processing optimises for battery life and user experience, so data is aggregated, smoothed and shown as trends. Clinical signal processing has to be deterministic and lossless at the sample level: every raw accelerometer or PPG reading is preserved, validated and processed in a documented, reproducible way. The algorithm downstream is only as trustworthy as the preprocessing in front of it.
Which wearable platforms can your algorithms run on?
We have validated preprocessing pipelines and algorithm ports for Apple Watch, Empatica E4, Samsung Galaxy Watch, Sony SmartWatch, and ActiGraph devices. For new platforms, we assess the hardware's sensor specifications, build the preprocessing transformation, and validate output equivalence against a reference device before we confirm that the algorithm runs correctly on it.
What does cross-platform validation require?
Cross-platform validation requires a reference dataset collected simultaneously on the target device and a reference device, a preprocessing pipeline that normalises both to a common format, and a statistical comparison of algorithm outputs across both. Any differences are investigated at the signal level to determine whether they are within the tolerance defined by the regulatory or clinical specification. The validation process is documented in full.
How long does a cross-platform wearable data project take?
Adding one new device to an existing validated algorithm usually takes six to twelve weeks: two to four weeks for sensor characterisation and preprocessing, two to four for algorithm porting and initial validation, and two to four for full validation and documentation. Multi-platform programmes covering three or more devices run three to nine months, depending on the number of algorithms and how complex each device's signals are.
Can you work with custom or proprietary wearable hardware?
Yes, provided we have access to the hardware specifications and raw data output format. Custom hardware typically requires more upfront sensor characterisation work than a commercial device with published specifications, but the pipeline-building and validation process is the same. If the hardware is a prototype, we work with engineering teams to establish the calibration and output format conventions before building the preprocessing layer.
Do you work on non-clinical wearable applications?
Yes. Most of our work is clinical-grade pipelines, but the same signal processing and cross-platform techniques work for fitness, occupational health and research wearables. What changes is the validation: clinical applications need documented equivalence against regulatory standards, research needs documented methodology, and fitness needs performance benchmarks. We scope each engagement to the standard that fits.