Search Results

The MouthLab Vital Signs Monitoring System is a hand-held, wireless device intended to record, transfer, store and display single lead electrocardiography (ECG), heart rate variability (HRV), functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate (PR), respiration rate (RR), respiration pattern (RP), oral temperature (TEMP) and basic lung function measurements: peak expiratory flow (PEF) and forced expiratory volume in one second (FEV1).

This system is for spot checking and does not have continuous monitoring capability or any alarm features. The device comes in contact with the user for approximately 60 seconds at each use and the captured medical parameters shall be displayed on a mobile application.

It is intended for use by adults in the home environment and in healthcare facilities. This system makes no specific diagnosis. Respiration rate is not intended for adults with underlying or suspected medical conditions. The device is for single user use.

It is intended for use with users who are well perfused and during no motion condition. Users with implanted pacemakers and/or implanted cardioverter-defibrillators (ICDs) are not recommended to use the device.

The MouthLab Vital Signs Monitoring System is a non-invasive, battery-powered, handheld, wireless, personalized single-user, vital sign measuring apparatus. The device is intended to intermittently monitor the user vitals through the use of an integrated SpO2 sensor, ECG electrodes, microphones and thermistor, which measures the users' functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate (PR), oral temperature (TEMP), ECG, heart rate (HR) and heart rate variability (HRV). The users' respiration rate (RR) measurements, respiration pattern (RP) and the basic lung functions (FEV1 and PEF) measurements are obtained are obtained through the acoustic measurement of air turbulence. The vital signs data are transferred to the Aidar Cloud™ Application via a cellular network for processing and storage. This processed data is then displayed on the Aidar Care™ Mobile Application.

The provided document, a 510(k) Summary for the MouthLab Vital Signs Monitoring System (K201635), outlines the device's acceptance criteria and the studies conducted to demonstrate its performance. The device measures multiple physiological parameters, and therefore, different studies were conducted for each.

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Sizes Used for the Test Set and Data Provenance:

• SpO2 Measurements: "a controlled desaturation study with adults." The specific sample size is not provided. The data provenance is implied to be prospective clinical testing, likely conducted in a controlled environment as it refers to a "controlled desaturation study." The country of origin is not specified.
• Respiration Rate Measurements: "20 healthy adults." The data provenance is prospective clinical testing. The country of origin is not specified.
• For other parameters (ECG/HR, Pulse Rate, Temperature, PEF/FEV1), bench testing was performed, meaning synthetic data or physical test equipment was used. No human subject sample size is applicable.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:

• Respiration Rate Measurements: Ground truth was established by "a clinician's manually scored capnography (EtCO2) waveforms." The number of clinicians is not specified, and their specific qualifications beyond "clinician" are not detailed.
• SpO2 Measurements: Ground truth was established by "reference co-oximeter analysis of arterial blood gas." This implies laboratory analysis rather than human expert interpretation of raw data. No human experts were explicitly stated to establish this ground truth in the provided text.

4. Adjudication Method for the Test Set:

• For SpO2, and Temperature, the comparison was against a reference standard (co-oximeter, calibrated thermometer) implying direct comparison, not a human adjudication process.
• For Respiration Rate, the comparison was against "a clinician's manually scored capnography waveforms." This suggests a single clinician's scoring was used as ground truth, implying no adjudication method (e.g., 2+1 or 3+1) was employed for establishing this ground truth.

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:

• No MRMC comparative effectiveness study was done involving human readers with and without AI assistance (the MouthLab system). The studies described are validation studies comparing the device's measurements to reference standards, not studies on human reader performance improvement.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

• Yes, the performance data provided describes the standalone performance of the MouthLab Vital Signs Monitoring System in measuring various physiological parameters. The clinical and bench tests evaluate the device's ability to accurately capture and report these values.

7. The type of ground truth used:

• ECG and Heart Rate: Bench testing compliant with IEC 60601-2-27:2012. (Simulated physiological signals)
• Pulse Rate: Bench testing compliant with ISO 80601-2-61:2017. (Simulated physiological signals)
• Temperature: Bench agreement study as per ISO 80601-2-56:2017. (Reference temperature measurements)
• Peak Flow Measurements (FEV1 and PEF): Bench testing according to the ATS Standardization of Spirometry, 2005 Update. (Reference flow/volume measurements)
• SpO2 Measurements: Reference co-oximeter analysis of arterial blood gas. (Objective clinical reference standard)
• Respiration Rate Measurements: Clinician's manually scored capnography (EtCO2) waveforms. (Expert interpretation of surrogate physiological data)

8. The sample size for the training set:

• The document does not explicitly mention a training set sample size. The performance data section focuses on "bench testing" and "clinical testing" for validation, not on the training of machine learning models. If the device uses algorithms trained on data, that information is not detailed in this summary.

9. How the ground truth for the training set was established:

• As the document does not mention a training set, the method for establishing its ground truth is not provided.

Ask a specific question about this device