(158 days)
The eMotion Faros ECG sensor is a wearable, externally applied, electrocardiograph recorder and transmitter for the purpose of health monitoring, biofeedback and scientific research.
The eMotion Faros ECG Mobile is intended for use in clinical settings to collect and transmit health parameters to healthcare professionals for monitoring and evaluation.
Health parameters are collected from a variety of commercially available, external plug-in devices such as ECG sensors, Weight Scales, Blood Pressure Meters and Pulse Oximeters.
Indicated for adult patients who require clinical ECG monitoring in healthcare facility environment under supervision of a physician or prescript by the supervising physician to supplement data acquisition in home environment.
The eMotion Faros ECG Mobile does not provide any automatic analysis or diagnosis.
The eMotion Faros ECG Mobile is a mobile device. PC and Internet based telemetry solution for the ambulant monitoring of the pluq-in device data of chronic patients via a mobile network. Pluq-in devices can be ECG devices, blood pressure monitors, weighing scales, etc. The device reads data from the plug-in device via a Bluetooth connection. The mobile device sends the data to a server (Health Gateway) over mobile networks using the secured connection.
Data can be viewed from the Health Gateway server using the Virtual Clinic interface. Monitoring is performed using PC application that reads data from the server over the internet using the secured connection. ECG data is possible to record on eMotion Faros ECG sensors internal memory. Data from ECG sensors can be reviewed with eMotion EDF Viewer or uploaded via USB connection.
Data acquisition is performed using eMotion Faros ECG sensors and applicable plug-in devices. Faros ECG sensors are modified versions of eMotion ECG sensor which the FDA granted clearance on November 26, 2013 (K131699).
The provided text does not contain detailed acceptance criteria or a specific study that proves the device meets such criteria in the format typically found for AI/ML device evaluations. This submission primarily focuses on establishing substantial equivalence to a predicate device, as opposed to demonstrating specific performance metrics for an AI component.
However, based on the Performance Data Summary section and general principles of device clearance, we can infer some aspects and highlight what information is not present that would typically be in an AI/ML device submission.
Inferred Acceptance Criteria and Reported Device Performance (Based on "Performance Data Summary"):
| Acceptance Criteria Category | Reported Device Performance (or implied) |
|---|---|
| Safety and Essential Performance | Meets requirements of EN 60601-1:2006 (General Requirements for Basic Safety and Essential Performance). |
| Electromagnetic Compatibility (EMC) | Meets requirements of EN 60601-1-2:2007 (Collateral Standard: Electromagnetic Compatibility - Requirements and Tests). |
| Biocompatibility | Meets requirements of ISO 10993-1:2003 (Biological Evaluation of Medical Devices Part 1: Evaluation and Testing). |
| Electrocardiograph Specific Standards | Meets requirements of EN 60601-2-25:1999 (Particular requirements for the basic safety and essential performance of electrocardiographs). |
| Design and Intended Use Performance | "Fully verified and validated against written test protocols to demonstrate that the design meets the requirements and performs as intended." (General Statement) |
| Substantial Equivalence (Overall) | Demonstrated substantial equivalence to K131699 "eMotion ECG Mobile" based on identical intended use, and similar technological characteristics and principles of operation, with performance testing showing no new safety/effectiveness questions. |
Information NOT available in the provided text (and why it's typically relevant for AI/ML devices but not explicitly discussed here):
The provided 510(k) submission is for an ECG recorder and transmitter device that does not provide any automatic analysis or diagnosis. Therefore, it does not involve an AI/ML algorithm that requires performance metrics against ground truth for diagnostic or analytical capabilities. The "study" mentioned here refers to non-clinical testing to ensure the device's technical specifications and safety standards are met, particularly in comparison to a predicate device.
1. Sample sized used for the test set and the data provenance: Not applicable in the context of an AI/ML algorithm's test set. The "test set" here refers to the device itself being tested for compliance with technical standards. If this were an AI/ML device, details about the number of cases/patients, their demographic breakdown, and where the data originated (e.g., specific hospitals, countries, retrospective/prospective collection) would be crucial.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Since the device does not perform analysis or diagnosis, there's no "ground truth" to establish for its output. If this were an AI/ML device, this section would detail the number of clinicians (e.g., cardiologists), their experience levels, and their role in labeling the data.
3. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. No human adjudication is mentioned as the device's function is data collection and transmission, not interpretation. For an AI/ML diagnostic device, this would describe how expert disagreements in ground truth labeling were resolved.
4. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not applicable. The device does not assist human readers in diagnosis. An MRMC study would be critical for an AI/ML device that provides interpretative assistance.
5. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable. There is no standalone algorithm for analysis or diagnosis.
6. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not applicable. There is no ground truth needed for diagnostic accuracy as the device merely records and transmits.
7. The sample size for the training set: Not applicable. There is no AI/ML algorithm being trained by the device.
8. How the ground truth for the training set was established: Not applicable. As there is no training set for an AI/ML algorithm.
§ 870.2920 Telephone electrocardiograph transmitter and receiver.
(a)
Identification. A telephone electrocardiograph transmitter and receiver is a device used to condition an electrocardiograph signal so that it can be transmitted via a telephone line to another location. This device also includes a receiver that reconditions the received signal into its original format so that it can be displayed. The device includes devices used to transmit and receive pacemaker signals.(b)
Classification. Class II (performance standards).