Personalized wellness intelligence
Most devices report numbers. SciFold identifies meaningful physiological trends relative to each person's own baseline — separating true change from motion, contact, and daily variation. Under the hood: a wrist-worn platform combining Green, Red, IR940, and IR1050 optical sensing with motion, pressure, and temperature context.
Four optical channels plus context sensors feed an on-device trend engine.
Market gap
Most consumer devices report numbers, charts, and alerts. The harder problem is separating true physiological trend from motion, contact pressure, temperature, and personal baseline variation. SciFold focuses on confidence-gated trend interpretation rather than isolated readings.
Who it's for
SciFold's value is strongest wherever a person's own trend, not a population average, is what counts. These are the first markets we are building toward.
For older adults and their families, gradual change matters more than any single reading. SciFold surfaces baseline-relative shifts in recovery, perfusion, and activity trends to support awareness and independence — without clinical claims.
Workers in hot or high-exertion environments benefit from early, confidence-gated heat-strain and exertion trend flags that combine heart rate, respiration, skin temperature, and perfusion context.
Athletes and coaches track recovery strain, HRV trend, and readiness against a personal baseline rather than generic targets, with signal confidence shown alongside every trend.
Employers running wellness programs get privacy-preserving trend indicators — stress-response and recovery patterns — that respect employee data ownership by design.
Care and wellness programs that follow people at home benefit from on-device trend interpretation that reduces raw-data exposure and cloud dependence.
Wellness and risk programs can use baseline-relative, confidence-scored trend signals as engagement and prevention inputs, framed as non-diagnostic wellness indicators.
Why SciFold
The architecture itself is the differentiator. Everything runs where the signal lives.
Core trend intelligence runs on the device. The product is not gated behind a recurring cloud fee to function.
Filtering, feature extraction, confidence estimation, and trend flags are computed locally on the wearable — not on a remote server.
Physiological data stays with the user. SciFold is designed so raw signals do not have to leave the device to be useful.
Local computation reduces raw-data exposure and recurring cloud cost by design, rather than as an afterthought.
Green, Red, IR940, and IR1050 channels provide complementary optical views of pulse, oxygenation context, tissue depth, and baseline-relative trend features.
Read moreA near-infrared channel beyond standard wearable PPG, used for deeper optical context and baseline-relative fluid/perfusion trend analysis.
Read moreFiltering, feature extraction, confidence estimation, and trend flags run locally on the wearable ARM/DSP layer.
Read moreTrend-oriented HRV and recovery features with signal-confidence gating.
Read moreRespiration estimates from pulse modulation and spectral features when window length and signal quality permit.
Read moreComposite baseline-relative trend score that fuses fluid, perfusion, stress, recovery, thermal context, and confidence.
Read moreTechnology readiness
HR, HRV, respiration, sleep, and fall-detection algorithms are functional in the current software stack.
iOS prototype running with Polar Verity Sense for green-channel algorithm validation before custom multispectral hardware.
Custom multispectral hardware, PCB spins, enclosure, pilot units, manufacturing readiness, and IP filings.
iOS prototype
Before the custom SciFold wearable is finalized, the core physiological analytics pipeline is being exercised on a real optical sensor platform. Polar Verity Sense provides a green-channel validation base for HR, HRV, respiration, perfusion, Mayer-wave, stress-index, rhythm, and fall-monitoring features.
Konstantin Gedalin, PhD — Founder & CEO. Signal-processing and machine-learning specialist with experience in optical physiology, embedded algorithms, and applied ML/DL.
Pavel Margulis, MSc — Hardware Engineering. Systems and electronics architect with decades of engineering experience across patient-monitor design and analog/RF work.
Email: support@scifold.com
Location: Ashdod, Israel