The science that makes
invisible healthcare
possible
Tapas.one HealthOS is built on three converging breakthroughs: nano-material biosensing, multimodal AI health modeling, and a clinical-grade data infrastructure. Together, they create something that has never existed before.
Six physiological channels. One cream. No needles.
Most wearables measure one or two signals. Tapas.one's nano-cream integrates four distinct sensing modalities simultaneously — capturing a richer biological picture than any existing consumer or clinical wearable, without breaking the skin.
Electrochemical Sensing
Nano-scale electrodes embedded in the cream matrix detect sweat biomarkers including cortisol, lactate, glucose, uric acid, and electrolytes through amperometric and potentiometric methods.
Electrophysiological Sensing
Conductive polymer networks in the cream capture skin-surface electrical signals, enabling continuous measurement of electrodermal activity and cardiac electrical patterns.
Thermal & Optical Sensing
Embedded thermochromic and photonic elements measure core body temperature gradients and microvascular blood flow patterns through the skin surface.
Mechanical Sensing
Piezoelectric nano-particles capture subtle mechanical vibrations from the skin surface, enabling pulse wave analysis and respiratory pattern detection.
From skin to insight in seconds
A six-stage AI pipeline transforms continuous biosignal streams into plain-English health intelligence — personalized to your biology, delivered in near real time. No PhD required to understand the output.
Signal Acquisition
Raw biosignals sampled at up to 1kHz from the nano-cream sensor array via the relay module
Preprocessing & Artifact Removal
Motion artifact filtering, baseline wander correction, and signal quality scoring using on-device ML
Feature Extraction
Time-domain, frequency-domain, and nonlinear feature extraction across all sensing modalities simultaneously
Multimodal Fusion
Cross-modal correlation engine combines features from all sensing channels into a unified physiological state vector
Personal Baseline Modeling
Bayesian personalization layer adapts population-level models to individual biological patterns over time
Predictive Intelligence
Anomaly detection, trend forecasting, and intervention recommendation engine generates actionable health insights
Why this is hard to replicate
Tapas.one is not just a product — it is a platform with six compounding structural advantages. Each one gets stronger with every user, every day of data, and every clinical partnership. Together, they create a moat that takes years to build.
Proprietary Nano-Cream Formulation
The nano-cream's biocompatible sensing matrix is a patentable invention by Pau Sabater. The specific formulation of conductive polymers, electrochemical sensors, and piezoelectric elements creates a defensible IP moat that competitors cannot replicate without years of materials science R&D.
Longitudinal Biosignal Dataset
Every day of operation generates unique, labeled, multimodal biosignal data from real users. This dataset — impossible to acquire any other way — trains increasingly accurate personal health models and creates a compounding data advantage over time.
Personal Health Twin Models
The AI models that constitute each user's Health Twin are deeply personalized and non-transferable. The longer a user stays on the platform, the more accurate and irreplaceable their Health Twin becomes — creating powerful switching costs and retention.
Clinical Validation Pathway
Led by Eangelica Aton's clinical AI expertise, Tapas.one is building toward FDA clearance for specific health monitoring use cases. Clinical validation creates regulatory barriers to entry and opens institutional healthcare channels unavailable to consumer wellness companies.
Integrated Hardware-Software Stack
Unlike pure software health apps, Tapas.one controls the full stack from sensing material to AI inference. This vertical integration enables optimizations impossible when hardware and software are developed separately — and makes the system extremely difficult to replicate.
Clinical-Grade Cloud Infrastructure
Led by Michael Tedescucci (CIO/COO), Tapas.one’s infrastructure is architected for the reliability, security, and compliance that clinical-grade health data demands. Multi-cloud resilience, DevSecOps-first design, and a 350%+ utilisation track record mean the platform scales from pilot to production without compromise.
The team behind the science
Tapas.one is built at the intersection of clinical medicine, AI engineering, and materials science.
Eangelica Aton
Co-founder · Clinical AI & Health Intelligence
Clinical background with deep expertise in AI-driven health systems, predictive diagnostics, and the translation of biological data into actionable clinical intelligence. Leads product strategy, AI architecture, and the clinical validation roadmap.
Pau Sabater
Co-founder · Nano-Material Science & Sensing
Inventor of the nano-cream biosensing formulation. Deep expertise in nano-material engineering, electrochemical sensing, and biocompatible material design. Leads hardware R&D, sensor development, and the IP portfolio.
R&D Validated on SignalSys.Click
Every biosignal modality captured by the Tapas nano-cream sensor is characterised, filtered, and validated using SignalSys.Click — a Next Gen AI-Powered Signal Processing platform built by Next Gen Engineers Worldwide. SignalSys bridges the gap between theoretical biosensor design and validated real-time signal pipelines.
FFT Spectrum Analysis
Frequency-domain characterisation of nano-cream biosensor output — identifying signal bandwidth, noise floor, and dominant physiological frequencies (0.5–40 Hz for ECG; 20–500 Hz for EMG).
Biosensor Circuit Simulation
Interactive op-amp, BJT/FET amplifier, and instrumentation amplifier simulations used to design the Layer 1 nano-cream signal conditioning front-end and the Layer 2 reader/relay hardware.
ECG / EMG / EEG Processing
MATLAB-validated algorithms for QRS detection (Pan-Tompkins), RMS envelope extraction, and Butterworth band-pass filtering — applied to validate biosensor signal fidelity before AI feature extraction.
RF Telemetry Validation
Bode diagram and bandwidth analysis for the BLE 5.3 / Sub-GHz RF transmission path between the nano-cream sensor and the Layer 2 reader/relay module, ensuring <200ms end-to-end latency.
Real-Time Signal Pipeline
Soft real-time processing (<100ms) for continuous biosignal streams, validated on SignalSys before integration into the Tapas AI Health Engine for HRV, stress index, and inflammatory marker extraction.
Amplitude-Based Noise Filtering
Filtering strategy for signals with high-magnitude frequency density functions where noise is low-magnitude and spectrally spread — directly applicable to nano-cream EDA and microcirculation channels.
Why SignalSys for Tapas R&D?
Nano-Cream Science Applied to
Elective Care Recovery
MedConnect.Team connects patients with world-class elective care clinics across Türkiye. Every Tapas biosensing modality — optical, electrochemical, and impedance-based — maps directly onto a MedConnect clinical pathway, enabling continuous, needle-free recovery monitoring that travels home with the patient.
The nano-cream medium is applied topically before the procedure, establishing a baseline biomarker profile. Post-discharge, patients continue transmitting recovery data to their MedConnect clinic dashboard from anywhere in the world — closing the cross-border continuity-of-care gap in medical tourism.
Optical biosensors measure melanin index, erythema, and TEWL continuously via nano-cream applied to the treatment area — no rigid hardware, no patient discomfort.
Electrochemical nano-cream sensors track glucose and cortisol in interstitial fluid to detect post-operative metabolic complications early.
Peri-nasal nano-cream application captures facial tissue perfusion and oedema resolution via photoplethysmographic optical sensing.
Peri-orbital nano-cream monitors post-LASIK and cataract surgery recovery through hydration and inflammatory cytokine proxies in the skin.
Salivary cortisol and systemic inflammatory markers are proxied via transdermal biosensing to assess peri-operative stress and healing.
SpO₂-correlated skin biomarkers and respiratory rate estimation via nano-cream optical sensing complement pulmonary function monitoring.
We use cookies
We use essential cookies to keep you signed in and optional analytics cookies to understand how Tapas is used — no advertising, no third-party tracking.
Essential
Always on — required for login & security
Analytics
Optional — anonymous usage stats