K Number
K151835
Date Cleared
2016-02-05

(214 days)

Product Code
Regulation Number
870.1025
Panel
CV
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Vital Signs Patch (VSP) system is intended to be used on patients in a clinical environment for the continuous, noninvasive monitoring of ECG, Heart Rate (HR), respiration rate, surface temperature, and arterial blood oxygen saturation (intended use group adults 21 and above), when prescribed by a physician or other qualified healthcare professional.

Device Description

The Vital Signs Patch (VSP in short) system is designed to monitor selected vital signs of patients in a clinical environment. The VSP system is comprised of the following components: Physical Patch, Brain - VSP Transmitter, Gateway mobile device, Clinical Backend. The Patch is attached to the patient's chest. The Brain plugs into a cradle on the Patch and is connected to the Patch with a 16-pin connector. The Brain receives the power from the Pattery; the data from the sensors are transmitted using the 16-pin connector. The Gateway includes a dedicated, medical SW application (also known as the Gateway application) designed by LifeWatch Technologies. The Brain transmits data to the Gateway application using the RF component. The patient can manually trigger an event by the pressing a button on the Brain. In addition, the Brain contains a 32MB Flash memory chip that can store 6-10 hours of data in case of communication failure with the Gateway. All data received from the Brain is recorded and stored on the Gateway. In addition, the Gateway can be used to view vital sign signals received from the Brain and to transmit the data to a Monitoring Center via the internet by the Wi-Fi network. The VSP is not intended for use on patients with life threatening arrhythmias; hence it is not intended for patients in the ICU. The internal LifeWatch Technologies Ltd. Part Number of the Vital Signs Patch system is CG-1101B; this model serves also as the predicate device (cleared in K132407) for this Special submission.

AI/ML Overview

The provided document is a 510(k) summary for the Vital Signs Patch (VSP) system, which is a modified version of a previously cleared device. It details product information and the modifications made, but it does not contain detailed information about specific acceptance criteria, study methodologies, or performance metrics in a quantitative way.

The document states:
"The 510(k) summarizes the testing that was performed, the acceptance criteria and the results of the testing."
However, this summary itself does NOT provide those details. It explicitly mentions that the full 510(k) contains this information, but this extract does not. Therefore, I cannot construct a table of acceptance criteria and reported device performance from the given text.

Based on the information provided in the extract, here's what can be inferred or stated about the requested points:

  1. A table of acceptance criteria and the reported device performance:

    • Not provided in the extract. The document states that the full 510(k) summarizes this, but the extract itself only mentions that testing was performed, acceptance criteria were met, and results did not raise new safety or effectiveness issues.
  2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

    • Not provided in the extract. The document mentions "design verification and validation testing of the modified device have been performed" but gives no details on sample size, data type, or origin.
  3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

    • Not provided in the extract. The nature of the device (vital signs monitor) suggests that ground truth would likely come from standard, calibrated medical equipment rather than expert human interpretation in the same way an AI diagnostic tool might, but this is not explicitly stated.
  4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

    • Not provided in the extract.
  5. 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/Not provided. This device is a vital signs monitor, not an AI-assisted diagnostic imaging tool for human readers. No mention of human readers or AI assistance in interpretation is present.
  6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

    • Not explicitly stated, but implied. The device is a "continuous, non-invasive monitoring" system for various vital signs. Its primary function is to measure and record these signs. Its performance would inherently be a "standalone" measurement against a gold standard (e.g., how accurately it measures heart rate compared to an ECG machine), rather than an algorithm assisting human interpretation. However, specific details of such standalone performance or the reference standard against which it was compared are not in this excerpt.
  7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • Not explicitly stated. For vital signs, the ground truth would typically be established by established, gold-standard medical measurement devices (e.g., a clinically validated ECG for heart rate, a separate temperature probe for temperature, a hospital-grade oximeter for SpO2). The document mentions "performance specifications," implying comparison to such standards, but doesn't detail them.
  8. The sample size for the training set:

    • Not provided in the extract. The document primarily concerns modifications to an existing cleared device ("Special 510(k)"), so extensive new training data might not have been central to this specific submission, but this is speculation.
  9. How the ground truth for the training set was established:

    • Not provided in the extract.

§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).

(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.