About Us

Our Story

Who We Are

Novasyne is a research-led technology company building software for clinical and translational research. STUDYPRO runs the trial; Wearable Workbench, EEG Workbench, Analytics Workbench and Imaging Workbench take the recordings that trial collects and turn them into results.

Founded on the belief that cutting-edge research should translate into real-world tools, we bridge the gap between academic discovery and the software researchers use every day, one study at a time.

Our Vision

Built For Research

We envision a future where advanced AI and data science seamlessly integrate into healthcare, giving clinicians and researchers powerful tools to understand, predict and treat neurological and mental health conditions. Nothing we build is hidden behind a summary: every inference our software makes is visible and can be overridden, every preprocessing step is recorded, and every automated interpretation names the literature it drew on.

Our Principles

Why Novasyne Is Different

Our product philosophy is built around scientific trust rather than black-box automation — the same standard STUDYPRO, Wearable Workbench, EEG Workbench, Analytics Workbench and Imaging Workbench are held to.

Visible Methods

Preprocessing and inference are exposed, recorded and exportable, never hidden behind a summary.

Data Provenance

The analysis history travels with the file rather than disappearing behind a result.

Multimodal By Design

Trial, EEG, wearable and biomarker data share a study context across every product.

Statistical Guardrails

Repeated measures and multiple testing are explicitly handled, not left for the researcher to catch.

Open Outputs

Researchers keep their data: every product exports to CSV, Excel and the specialist formats statisticians already use.

AI With Boundaries

Automated interpretation names its sources and is constrained by the data supplied, never by a black box.

For Reference

Selected Publications

The methods behind our products are grounded in peer-reviewed work. The list below is provided for reference.

Generalizable machine learning for stress monitoring from wearable devices: A systematic literature review
International Journal of Medical Informatics
Ensemble machine learning model trained on a new synthesized dataset generalizes well for stress prediction using wearable devices
Journal of Biomedical Informatics
Stress monitoring using low-cost electroencephalogram devices: A systematic literature review
International Journal of Medical Informatics
The effects of ketogenic metabolic therapy on mental health and metabolic outcomes in schizophrenia and bipolar disorder: a randomized controlled clinical trial protocol
Frontiers in Nutrition
Stabilizing machine learning for reproducible and explainable results: A novel validation approach to subject-specific insights
Computer Methods and Programs in Biomedicine
A statistical approach for synthetic EEG data generation
arXiv
Machine Learning‑Assisted Pulse Electrodeposition of Copper for Enhanced Nitrate Sensing
ChemElectroChem
The effect of acute stress on the interpretability and generalization of schizophrenia predictive machine learning models
Biomedical Signal Processing and Control
Decoding neural emotion patterns through large language model embeddings
Neurocomputing
Synaptic Pruning: A Biological Inspiration for Deep Learning Regularization
arXiv
Standardized synchronization and validation pipeline for physiological biomarkers across multiple devices
Behavior Research Methods
Machine Learning-Assisted Identification of Biomarkers Associated with Schizotypal and Cyclothymic Traits
Psychiatry International

5

Products

23

Wearable Devices Supported

5

EEG Formats Read And Written

30+

Years Software Experience