Empatica Health Monitoring Platform; EmbracePlus; Empatica Care; Care Portal

The Empatica Health Monitoring Platform is a wearable device worn on the wrist paired with mobile and cloud-based software for retrospective remote monitoring of physiologic parameters in ambulatory adults 18+ years in home-healthcare settings. It continuously collects data on pulse rate, blood oxygen saturation (under no-motion conditions), respiratory rate (under no-motion conditions), peripheral skin temperature, electrodermal activity, and movement during sleep, intended for review by trained healthcare professionals or researchers rather than real-time alerting.

The subject device is technologically identical to its predicate (K230457) across all measured parameters: pulse rate uses photoplethysmography (24–240 bpm, ±3 bpm accuracy no-motion/±5 bpm motion); SpO₂ uses hemoglobin light-absorption principles (70–100%, ±3% accuracy); respiratory rate uses photoplethysmogram analysis (6–40 brpm, ±3 brpm); temperature uses a high-precision sensor (0–50°C, ±0.1°C); electrodermal activity measures skin conductivity (0.01–100 μS); and activity/sleep monitoring uses a MEMS accelerometer (±16 g, 26–208 Hz). The sole difference is implementation of a Predetermined Change Control Plan (PCCP) for a machine-learning-based upgrade to the SpO₂ quality indicator algorithm.

ISO 10993-1 (biocompatibility of patient-contacting materials); ISO 80601-2-61 (medical electrical equipment—particular requirements for pulse oximeter safety and performance); FDA Guidelines for Pulse Oximeters – Premarket Notification Submissions [510(k)s]: Guidance for Industry and FDA Staff (2013).

The device is substantially equivalent because it performs identical physiological measurements using identical sensor technologies and algorithms compared to the cleared predicate, with no changes to intended use, target population, anatomical site, or performance specifications. The PCCP proposes a machine-learning replacement of the SpO₂ quality-indicator (input signal filtering, not the SpO₂ calculation itself), which maintains the same binary output and input signals while requiring bench and clinical testing to demonstrate non-inferiority in sensitivity, specificity, false discovery rate, and accuracy (Arms error ≤ predicate, ≥90% output agreement). This controlled modification framework ensures continued safety and effectiveness without altering the fundamental operation or intended retrospective monitoring purpose.