Not black-box scores
Wherever devices allow, we work from raw PPG, accelerometry and beat-to-beat data, not only vendor summaries.
Longitudinal health analytics, from raw signals to publishable results.
Our data science team turns wearable, smartphone, EMA and questionnaire data into validated measures, models and figures, using methods we have published in peer-reviewed journals. Your data can come from Centralive or from another source.
Services
What we analyze.
Sleep, physical activity, heart rate and HRV, stress and mental health, and the methods that tie them together.
Sleep
Sleep analytics
Sleep staging from raw PPG and accelerometry, sleep metrics, device validation and night-to-night patterns.
Learn more →ActivityPhysical activity and gait analytics
Steps, intensity, sedentary time, energy expenditure and gait from accelerometry, with honest uncertainty.
Learn more →HRVHeart rate and HRV analytics
Clean interbeat intervals from ECG and PPG, the full set of HRV metrics, respiration rate and long-term cardiac trends.
Learn more →Mental healthStress and mental health analytics
Stress, affect, loneliness, depressive symptoms and pain from wearables, smartphone sensing and EMAs.
Learn more →BiosignalsBiosignal processing
ECG, PPG, EEG, EDA, respiration and accelerometry, from quality assessment to validated features.
Learn more →Time seriesLongitudinal time-series analytics
Seasonality, temporal patterns, clustering, anomalies, change points and event mining across months of data.
Learn more →CausalCausal analysis
Causal discovery and estimation, mediation, counterfactuals, structural equation modeling and factor analysis.
Learn more →Machine learningMachine learning and forecasting
Prediction, risk stratification, treatment response, explainable AI, NLP and time-series forecasting.
Learn more →Generative AIAgents and generative AI
Virtual health assistants, care coordination, patient monitoring and research assistance agents, built with Livi.
Learn more →Why work with us
Analytics built by researchers, for researchers.
Signal quality before features
Every segment is checked before HR, HRV or sleep is computed from it.
Checked against reference standards
Our team has validated consumer devices against polysomnography, ECG and research-grade actigraphy.
Methods reviewers accept
Figures, tables, statistics and a methods section, with reporting reviewers expect.
How it works
From question to results.
Free consultation
We talk through your research questions, data and timeline, and agree on the analysis plan.
Secure data transfer
We work with data collected on Centralive or exported from your own devices and platforms.
Transparent methods
Quality checks, processing and modeling with documented, reproducible code.
Deliverables you can use
Reports, figures, tables and methods text for your paper, grant or product.
Open source
Tools our team wrote and maintains.
GitHub
E2E-PPG
End-to-end PPG pipeline: quality assessment, motion-artifact handling, reconstruction, peak detection and HR/HRV extraction.
GitHubpyPPGqa
Deep learning PPG quality assessment for reliable heart rate and HRV.
GitHubecg2rr
LSTM-based ECG R-peak detection for robust RR-interval extraction from noisy recordings.
GitHubpyEDA
Electrodermal activity preprocessing and feature extraction, including tonic and phasic components.
Evidence
Selected peer-reviewed work by our team.
- Kazemi et al. Improved sleep stage predictions by deep learning of photoplethysmogram and respiration patterns. Computers in Biology and Medicine, 2024. doi:10.1016/j.compbiomed.2024.108679
- Cao et al. Accuracy assessment of Oura ring nocturnal heart rate and heart rate variability in comparison with electrocardiography in time and frequency domains: comprehensive analysis. Journal of Medical Internet Research, 2022. doi:10.2196/27487
- Sarhaddi et al. A comprehensive accuracy assessment of Samsung smartwatch heart rate and heart rate variability. PLOS ONE, 2022. doi:10.1371/journal.pone.0268361
- Feli et al. Preterm birth risk stratification through longitudinal heart rate and HRV monitoring in daily life. Scientific Reports, 2024. doi:10.1038/s41598-024-70773-0
- Feli et al. End-to-end PPG processing pipeline for wearables: from quality assessment and motion artifacts removal to HR/HRV feature extraction. IEEE BIBM, 2023. doi:10.1109/BIBM58861.2023.10385998
- Jafarlou et al. Objective monitoring of loneliness levels using smart devices: a multi-device approach for mental health applications. PLOS ONE, 2024. doi:10.1371/journal.pone.0298949
- Khatibi et al. Impact of COVID-19 pandemic on sleep including HRV and physical activity as mediators: a causal ML approach. IEEE BSN, 2023. doi:10.1109/BSN58485.2023.10331423
- Labbaf et al. ZotCare: a flexible, personalizable, and affordable mHealth service provider. Frontiers in Digital Health, 2023. doi:10.3389/fdgth.2023.1253087