Movano Health announced major advances in the accuracy of its heart rate in motion algorithm following the implementation of deep learning into the processing. The Company recently released an engineering accuracy study directed by Movano Health Founder and CTO Michael Leabman, Enhanced Heart Rate in Motion Accuracy with the Evie Ring Using Advanced Deep Learning Algorithms, which demonstrates the value of deep learning integration into heart rate (HR) algorithms for improved accuracy. The study was conducted with 65 subjects, completing 7-10 sessions of various activities including sleeping, resting, walking, running, climbing stairs, working out at the gym and swimming.

Data was collected with the Evie Ring and a Polar H7 chest strap used as a control device. The results demonstrated a high correlation with the Polar H7 chest strap outputs across a diverse data set, confirming the reliable reporting of heart rate by Evie's HR algorithm across all activities. To overcome the challenges of measuring heart rate from PPG signals in wearables, Evie's HR solution combines the best from the signal processing world as well as recent advances in AI-based Deep Learning.

Optimally filtering out motion artifacts and more accurately tracking heart rate through development of AI algorithms in a specific, novel Deep Learning solution. Removing motion artifacts from the PPG signal by leveraging both PPG and 3D accelerometer data. Enhancing the signal-to-noise ratio (SNR) through Deep Learning.

The Company plans to convert all Evie Ring algorithms including sleep, respiration, heart rate variability (HRV), and blood oxygen saturation (SpO2) through this same process.