:: SYSTEM STATUS: ONLINE ::

Decoding the
Human Signal

We combine high-fidelity biosensors with proprietary AI models to predict cardiovascular events before they happen.

Initialize Partnership

The Silent Failure

Cardiovascular disease is a data problem. Current diagnostics miss the subtle, early-warning patterns in endothelial function and heart rate variability.

32% Global Deaths
520M Affected Lives
:: METRICS ROADMAP ::

From Signal to Risk Score

We start with the signals today's devices capture — and systematically add the markers that predict cardiovascular events years before they occur.

[ NOW ]

Foundation Metrics

  • Heart Rate & HRV
  • SpO2 / Oxygen Saturation
  • ECG & PPG Signal
  • Respiration Rate
  • Motion-corrected ambulatory ECG
[ NEXT ]

Advanced Vascular Markers

  • Flow-Mediated Dilation (FMD)
  • Endothelial Function Index
  • Blood Pressure Trending
  • Arterial Stiffness Proxy
[ VISION ]

Holistic Risk Intelligence

  • Unified cardiovascular risk score
  • Longitudinal trend analysis
  • Clinician-ready risk reports
:: MACHINE LEARNING PIPELINE ::

The Neural Engine

Our proprietary stack processes raw sensor data at the edge, extracting clinical features in real-time.

1. Ingestion

High-frequency sampling of PPG & ECG raw data inputs

[ High Freq Sampling ]

2. Feature Extraction

Advanced signal processing and AI/CNNs

[ Tensor Processing ]

3. Prediction

Risk scoring against our proprietary clinical dataset

[ Risk Score: 98% ]
:: CORE ARCHITECTURE ::

The Aoknos Platform

[ 01 ]

Flow-Mediated Dilation

Non-invasive assessment of endothelial function. We capture vascular reactivity data that standard cuffs miss.

[ 02 ]

AI-Denoising

Proprietary algorithms filter motion artifacts from ambulatory ECGs, delivering clinical-grade fidelity in motion.

[ 03 ]

Predictive Vitals

Real-time streaming of HRV, Oxygen Saturation, and Blood Pressure trends directly to the cloud.

:: WHY AOKNOS ::

Beyond the Consumer Wearable

Standard wearables count steps. Clinical monitors require clinic visits. Neither was built to catch cardiovascular disease early — we were.

[ STANDARD APPROACH ]

Heart rate and SpO2, nothing more

Consumer wearables capture surface-level metrics. They cannot measure vascular reactivity or endothelial function — the earliest known indicators of cardiovascular risk.

Motion makes signals unusable

Ambulatory ECG degrades the moment a patient moves. Most wearable ECGs are only reliable at rest, limiting their clinical value to static snapshots.

Isolated alerts, no context

Each metric is evaluated independently. A single high reading triggers an alarm — but no device synthesizes the full picture into an actionable risk assessment.

Gold-standard tests stay in the clinic

Flow-Mediated Dilation requires specialist equipment, a trained technician, and a hospital visit. It is never available continuously or at the point of care.

[ AOKNOS ]

FMD and beyond — on a single device

We are the first platform to bring Flow-Mediated Dilation into an ambulatory form factor, alongside a full suite of cardiovascular biosignals captured continuously.

Clinical-grade signal in motion

Our proprietary AI denoising removes motion artifacts in real time, delivering clean, clinically interpretable ECG data whether the patient is resting, walking, or exercising.

One unified risk score

Our ML engine synthesizes every captured signal — HRV, SpO2, FMD, ECG morphology — into a single, longitudinal cardiovascular risk score that evolves with the patient.

Continuous, anywhere monitoring

Edge-processed on the device. No clinic visit required. Clinicians receive structured risk reports continuously, enabling intervention before symptoms appear.

The Team

Ashish Chordia
Founder & President [ LinkedIn ]
Lampros Kalampoukas
Founder & CEO [ LinkedIn ]
Umesh Iyer
Founder & CTO [ LinkedIn ]
Vijay Agarwal
Founder & VP of Engineering [ LinkedIn ]
Sanjay Kuhikar
Principal Founding Engineer [ LinkedIn ]
Sindhura Reddy
Sr. Data Scientist [ LinkedIn ]
Tushar Deshpande
Sr. Embedded Engineer [ LinkedIn ]
Sagar Deyagond
Sr. Data Scientist [ LinkedIn ]