Search Results

The Wesper Lab is a digital recording device designed to be used under the direction of a physician or trained technician but may be applied by a layperson. Wesper Lab records multiple physiological parameters from a sleeping patient for the purpose of simultaneous or subsequent display of the parameters. The displayed data assists in the identification of sleep apnea by trained personnel. Wesper Lab is intended to be used for adult sleep studies at home or clinical environment. The device does not actively monitor or diagnose the patient and does not issue any alarms.

Wesper Lab ("the device") is a digital recording device designed to be used under the direction of a physician or trained technician but may be applied by a layperson. Wesper Lab records multiple physiological parameters from a sleeping patient for the purpose of simultaneous or subsequent display of the parameters. The displayed data assists in the identification of sleep apnea by trained personnel.

The device consists of an abdominal patch, a thoracic patch and a mobile application. The patches are multi-use wearable, flexible, thin, and wireless, and are designed to record sleep data in adult patients. Both patches are the same and differ only in their anatomical designation, which is determined by the order in which the user applies them at test setup time. The flexible fabric allows the patch to contract and expand as the patient breathes and moves during sleep.

The mobile application ("the app") resides on the patient's personal mobile device, relaying sleep data wirelessly to a secure remote storage location ("the cloud") for subsequent analysis by a healthcare professional. The app has 3 Bluetooth Low-Energy (BLE) ports, each of which receives multiple physiological channels from the patient.

The device's BLE ports connect to the following:

• 1. Abdominal patch
• 2. Thoracic patch
• 3. Pulse oximeter

The patches collect multiple physiological parameters related to sleep to be used by a healthcare professional. Specifically, the patches measure sleep position, respiratory effort, and airflow / air pressure. The patches leverage accelerometry and optical sensing to provide these measurements.

Data from the patches is transmitted via BLE throughout the night to the app, which uploads the data to the cloud. A third BLE port on the app connects to an FDA cleared pulse oximeter, which provides heart rate and blood oxygen saturation measurements.

The data recorded by the patches is relayed to a remote secure storage, where it will be downloaded to a local PC. Then, Wesper staff will execute the Study Output Module (SOM) and save the data locally on the desktop computer. The data is then ready for interpretation by a healthcare provider.

The provided text describes the Wesper Lab (K221816) device and its substantial equivalence to a predicate device (Wesper Lab, K203343). The information mainly focuses on justifying the substantial equivalence for FDA premarket notification. While it outlines the performance testing done for electrical safety, EMC, and usability, it does not include a detailed study proving the device meets specific acceptance criteria related to its primary function: recording physiological parameters for sleep apnea identification.

The document states: "Wesper Lab met all acceptance criteria" for Electrical Safety / EMC tests, but it does not provide acceptance criteria or performance data for the physiological parameter recording itself, nor for its utility in assisting with sleep apnea identification.

Therefore, many of the requested details cannot be extracted from the provided text.

Here is a breakdown of what can and cannot be answered based on the provided document:

Acceptance Criteria and Device Performance (Based on available information for Electrical Safety / EMC):

Note: The document does not provide specific numerical acceptance criteria or performance metrics for the primary function of recording physiological parameters relevant to sleep apnea.

Detailed Study Information:

1. Sample size used for the test set and the data provenance:

   • Not provided for the physiological parameter recording or sleep apnea identification assistance.
   • For Electrical Safety/EMC and Usability, information on study specifics (like sample size or data provenance) is not detailed beyond "Wesper Lab met all acceptance criteria" and "confirmed by a usability study."

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not provided. The document states "The displayed data assists in the identification of sleep apnea by trained personnel," but it does not describe any study that involved experts establishing ground truth for sleep apnea identification based on the device's data.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • Not provided.

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:

   • No evidence of an MRMC study or AI assistance evaluation is mentioned for this device. The device is described as a "digital recording device" that provides data to "trained personnel" for assistance in identification, not as an AI-powered diagnostic tool.

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

   • Not applicable/Not provided. The device is presented as a data recording device aiding human interpretation, not as a standalone algorithm for diagnosis. The document states, "The device does not actively monitor or diagnose the patient and does not issue any alarms."

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • Not provided for the device's primary function of assisting in sleep apnea identification. The testing detailed relates to hardware safety and usability.

7. The sample size for the training set:

   • Not applicable/Not provided. This device is a data acquisition system, not an AI/ML device that would typically have a "training set" in the context of diagnostic algorithms.

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

   • Not applicable/Not provided. (See point 7)

Summary of Device Functionality from the Text:

The Wesper Lab (K221816) is a digital recording device that records multiple physiological parameters (sleep position, respiratory effort, airflow/air pressure, heart rate, blood oxygen saturation via external oximeter). This data is displayed for "trained personnel" to assist in the identification of sleep apnea. The device itself does not actively monitor, diagnose, or issue alarms. The key changes from the predicate device (K203343) are the addition of a charging element and a replaceable adhesive layer for the patches. The performance data provided only confirms compliance with electrical safety, EMC, and usability standards, not the clinical performance related to sleep apnea identification. The FDA clearance is based on substantial equivalence, implying that its performance regarding physiological parameter recording is considered equivalent to the predicate, and therefore, no separate clinical performance study for that specific aspect was required for this 510(k) submission.

Ask a specific question about this device

WesperO2 is a finger-worn pulse oximeter in measuring, displaying, storing and transmitting functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate for adult patients. It is intended for spot-check and/or continuous data collection, and not continuous monitoring. It can be used in sleep labs and home use.

WesperO2 ("the device") is a pulse oximeter, meant to be worn on the finger of an adult patient over the age of 21. The device is intended for spot checking or continuous collection of functional oxygen saturation of arterial hemoglobin by way of sensing peripheral capillary perfusion ("SpO2") and Pulse Rate. It is intended to be used in the patient's home or in a sleep lab. The device's core technology is based on collecting reflected light from the intact skin of the patient's finger to form Photoplethysmography ("PPG") waveforms. These waveforms can then be used to extract a measurement of SpO2 and Pulse Rate. The sensing component is carried by an electronics assembly, which is comprised of a battery-powered Printed Circuit Board ("PCB"). The electronics assembly is housed inside of a soft, flexible casing, which encapsulates the entirety of the assembly, except for the actual optical front-end of the sensing component, which exposes an array, consisting of two LEDs and a photodiode. The entire assembly is referred to as "the WesperO2 probe." The silicone housing has a "thimble-style" form factor, such that the patient can wear it on their fingertip, with the optical sensor pointed at the pad of their finger. The probe is then meant to create a snug, yet comfortable fit to ensure consistent positioning of the optical sensor throughout the usage period. The probe has a Bluetooth interface through which it sends SpO2 and Pulse Rate measurements to a companion mobile application ("WesperO2 app"), which resides on the patient's mobile device. The application can both record the data and display it in real-time to the patient. Recordings are saved on the mobile device and can be shared later through the application with a healthcare provider over the internet.

Here's a detailed breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

Study Details

Based on the provided text, the primary study for the WesperO2 focused on standalone performance and did not involve a multi-reader, multi-case comparative effectiveness study with human readers.

1. Sample size used for the test set and the data provenance:

   • Test Set Sample Size (for SpO2): N=223 (for ARMS calculation). This refers to the number of data points or observations, not necessarily the number of unique subjects.
   • Test Set Sample Size (for Pulse Rate): N=235 (for ARMS calculation).
   • Data Provenance: The text states the study was a clinical study. While the specific country of origin is not explicitly mentioned, it's generally understood that FDA submissions for clinical studies conducted for US market clearance are often performed in North America or under international standards recognized by the FDA. The study was conducted in accordance with ISO 80601-2-61:2019 and FDA-2007-D-0205 guidance, which outlines requirements for clinical performance in adult subjects. The study appears to be prospective as it was conducted for the validation of the WesperO2 pulse oximeter.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • The ground truth for SpO2 accuracy was established by arterial blood sample CO-Oximetry. This is a direct, objective measurement from a laboratory device, not reliant on human expert interpretation.
   • The ground truth for Pulse Rate accuracy was compared to a "Reference Oximeter Pulse Rate." The text does not specify how this reference oximeter's pulse rate ground truth was established, but it would typically be from a validated reference device or ECG.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Since the ground truth for SpO2 was established by CO-Oximetry and for Pulse Rate by a reference oximeter (or equivalent objective method), human adjudication was not applicable for establishing the primary ground truth.

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:

   • No, a multi-reader multi-case (MRMC) comparative effectiveness study was not described. The study focused on the accuracy of the device itself (standalone performance) against objective physiological measurements. The device is a measurement tool, not an AI-assisted diagnostic aid for human readers.

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

   • Yes, a standalone performance study was conducted. The clinical study evaluated the WesperO2 pulse oximeter's accuracy in measuring SpO2 and Pulse Rate against established physiological reference methods.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • SpO2: Arterial blood sample CO-Oximetry (a direct physiological measurement).
   • Pulse Rate: Reference Oximeter Pulse Rate (a measurement from a validated reference device or potentially ECG).

7. The sample size for the training set:

   • The document does not provide information regarding the sample size of a training set. This is typical for medical device submissions that focus on the validation of a commercial product (especially hardware) rather than AI/ML models that would explicitly require a separate training dataset. The WesperO2's core technology is based on photoplethysmography (PPG) waveforms, a well-established principle in pulse oximetry. While there is software, its validation is described in terms of adherence to standards and risk analysis rather than a statistical training-testing split as seen in AI/ML performance studies.

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

   • As no training set is explicitly mentioned or detailed, the method for establishing its ground truth is not provided.

Ask a specific question about this device

The Wesper Lab is a digital recording device designed to be used under the direction of a physician or trained technician but may be applied by a layperson. Wesper Lab records multiple physiological parameters from a sleeping patient for the purpose of simultaneous or subsequent display of the parameters. The displayed data assists in the identification of sleep apnea by trained personnel. Wesper Lab is intended to be used for adult sleep studies at home or clinical environment. The body-worn component of the system is single-use, to be discarded nightly application. The device does not monitor or diagnose the patient and does not issue any alarms.

Wesper Lab ("the device") is indicated as a digital recording device designed to be used under the direction of a physician or trained technician but may be applied by a layperson. Wesper Lab records multiple physiological parameters from a sleeping patient for the purpose of simultaneous or subsequent display of the parameters. The device consists of an abdominal patch, a thoracic patch and a mobile application. The patches are single-use wearable, flexible, thin, and wireless, and are designed to record sleep data in adult patients. Both patches are identical and differ only in their anatomical designation at test setup time. The flexible fabric allows the patch to retract and expand as the patient breathes and moves during sleep. The mobile application ("the app") resides on the patient's personal mobile device, relaying sleep data wirelessly to a secure remote storage location ("the cloud") for subsequent analysis by a healthcare professional. The patches collect multiple physiological parameters related to sleep to be used by a healthcare professional. Specifically, the patches measure sleep position, respiratory effort, and Wesper-Sum- Flow / Wesper-Sum-Pressure. Data from the patches is transmitted via Bluetooth low energy (BLE) throughout the night to the app, which uploads the data to the cloud. A third BLE port on the app connects to an FDA cleared pulse oximeter, which provides pulse rate and blood oxygen saturation measurements. The data recorded by the patches is relayed to a remote secure storage, where it will be downloaded to a local PC. Then, Wesper staff will execute the Study Output Module (SOM) and save the data locally on the desktop computer. The data is then ready for interpretation by a healthcare provider.

Based on the provided text, the Wesper Lab is a digital recording device used for sleep studies to assist in the identification of sleep apnea. The performance data section describes the studies undertaken to demonstrate its safety and effectiveness.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

For the specific aspect of sleep apnea identification, the key performance metric is the correlation with Polysomnography (PSG) AHI (Apnea-Hypopnea Index), which is the gold standard.

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size for Clinical Test Set: 45 patients
• Data Provenance:
  • Country of Origin: Not explicitly stated, but the study was described as "multi-center," suggesting it was conducted across different sites. Given the FDA submission, it's highly likely to be within the United States.
  • Retrospective or Prospective: Prospective. The text states, "Wesper has conducted a prospective, multi-center clinical study for Wesper Lab..."

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

The text states that the "gold standard - in-lab, polysomnographic (PSG) tests" were used to establish ground truth. PSG tests are typically interpreted by trained personnel, often registered polysomnographic technologists (RPSGTs) and sleep physicians (e.g., neurologists or pulmonologists with sleep medicine board certification). The number of experts is not specified, nor are their exact qualifications beyond "trained personnel."

4. Adjudication Method for the Test Set

The text does not explicitly describe an adjudication method for the PSG ground truth. It implies that standard PSG interpretation procedures were followed to derive the AHI, which serves as the ground truth. There is no mention of multiple independent expert interpretations followed by an adjudication process (e.g., 2+1, 3+1).

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done and Effect Size

No, an MRMC comparative effectiveness study involving human readers assisting with or without AI was not reported for the sleep apnea identification aspect. The study evaluated the device's standalone performance in correlating with PSG AHI.

The study did involve, "The displayed data assists in the identification of sleep apnea by trained personnel," which implies human interpretation. However, the study's focus was on the Wesper Lab's ability to record and display data that could achieve a high correlation with the gold standard AHI, not on how human readers' diagnostic accuracy changed with AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, the clinical study's primary objective, as described by the 95.1% correlation with PSG AHI, appears to be a standalone (device only) performance evaluation because it compares the device's output (presumably, its calculated AHI or raw data leading to AHI) directly against the PSG AHI ground truth. While the device's purpose is to provide data for interpretation by "trained personnel," the reported correlation is a measure of the device's accuracy in capturing the necessary physiological parameters that align with PSG-derived AHI.

7. The Type of Ground Truth Used

The primary ground truth used for the clinical study was gold standard in-lab Polysomnography (PSG) tests, specifically their derived Apnea-Hypopnea Index (AHI).

8. The Sample Size for the Training Set

The text does not explicitly state the sample size used for the training set. The clinical study described with 45 patients is clearly identified as a test set for performance evaluation.

9. How the Ground Truth for the Training Set Was Established

Since the training set size and details are not provided, it is unclear how ground truth for the training set was established. However, given the nature of the device and the eventual performance evaluation against PSG, it's highly probable that any training data would also have been validated against PSG or similarly reliable methods for sleep data.

Ask a specific question about this device