(227 days)
wheezo is intended to detect and record abnormal breath sounds (continuous adventitious breath sounds/CABS) at the windpipe (trachea), reported as WheezeRate in adults and children (2 years and older). A licensed health care professional's advice is required to understand the meaning and importance of the wheezo readings.
The Respiri wheezo WheezeRate Detector contains the following components (1) wheezo Sensing Device (2) wheezo App and (3) Secure cloud server. The wheezo transfers a user's breath sound data to the App using a Smart Device. The sound data is analysed in the alqorithm, which is integrated inside the App and runs on the Smart Device.
It is a hand-held, battery-operated, computer-based, pulmonary sound detector that utilises microphones to acquire, amplify, filter, record and quantify the presence of wheezing. The breath sound is transferred using Bluetooth® technology to smartphone for detection and quantification of wheeze presence, expressed as wheeze rate.
The wheezo samples breathing and ambient sounds, and streams the audio data wirelessly via Bluetooth SPP profile to a connected Smart Device Mobile App. It does not store any recorded data into persistent memory. The Mobile App, through user interaction, must perform the standard Bluetooth pairing process to the wheezo prior to use. Wheeze rate is calculated by the Mobile App using the audio data received from the sensing device. A remote device can connect to the wheezo Sensing Device via Standard Bluetooth. The device supports Bluetooth Serial Port Protocol (SPP) mode, where asynchronous serial packets are transported using Bluetooth RFCOMM protocol. When not paired, the sensing device will be in discoverable mode.
Here's a breakdown of the acceptance criteria and the study details for the wheezo WheezeRate Detector, based on the provided FDA 510(k) summary:
Acceptance Criteria and Device Performance:
The document doesn't explicitly state quantitative acceptance criteria for "wheeze rate accuracy" for the wheezo device to be considered substantially equivalent. Instead, it relies on a comparison to a predicate device (SonoSentry) and a clinical validation study demonstrating agreement with expert assessment. The key "performance" is the detection and quantification of wheezing.
Given the information, the primary "acceptance criteria" appear to be:
- Accuracy in Wheeze Rate Calculation: The wheezo's calculated wheeze rate must align with expert manual calculations.
- Safety and Effectiveness: The device must not raise new questions of safety or effectiveness compared to the predicate device, despite technological differences.
Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Accuracy in Wheeze Rate Calculation | Validation of the wheezo device output (calculated wheeze rate) was performed by comparing it to a panel of three respiratory experts' manual calculation of the wheeze rate. The study found sufficient agreement to support substantial equivalence. (Specific quantitative metrics like sensitivity, specificity, or error rates for the wheeze rate are NOT provided in this summary.) |
| Safety and Effectiveness | "Performance testing, including but not limited to side comparative testing demonstrated that the new device is substantially equivalent to the predicate device with respect to safety and effectiveness." "Technological characteristics of the wheezo do not raise new or different questions in relation to safety or effectiveness." |
| Compliance with International Standards | Passed all testing in accordance with internal company protocols and various international standards (listed in Section 9), covering biocompatibility, risk analysis, mechanical testing, electrical safety, EMC, transport, software, and cybersecurity. |
Here's the breakdown of the study details:
2. Sample size used for the test set and the data provenance:
- Sample Size: 189 recordings from 56 patients and 20 healthy individuals.
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). However, the study describes "patients and healthy individuals," suggesting it was prospective data collection specifically for validation.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: A panel of three respiratory experts.
- Qualifications of Experts: Only stated as "respiratory experts." Specific qualifications like years of experience or board certification are not provided in this summary.
4. Adjudication method for the test set:
- The document states that the wheezo's calculated wheeze rate was "compared to a panel of three respiratory experts' manual calculation of the wheeze rate." It does not specify an explicit adjudication method like "2+1" or "3+1" for reaching a consensus among experts on each recording. It implies that the experts' manual calculations individually formed the ground truth against which the device was validated, rather than a single adjudicated ground truth per case.
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, an MRMC comparative effectiveness study was not explicitly described. The clinical testing section refers to "Validation of the wheezo device output... compared to a panel of three respiratory experts' manual calculation of the wheeze rate." This suggests a standalone performance evaluation against expert opinion, not an evaluation of human readers using the AI device compared to human readers without it.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance study was done. The clinical testing section explicitly describes "Validation of the wheezo device output (calculated wheeze rate)... compared to a panel of three respiratory experts' manual calculation of the wheeze rate." This is a direct measure of the algorithm's performance in calculating the WheezeRate independently.
7. The type of ground truth used:
- Expert Consensus / Expert Opinion: The ground truth for the clinical validation was established by the "manual calculation of the wheeze rate" by a "panel of three respiratory experts."
8. The sample size for the training set:
- Not provided. The document describes the clinical validation study but does not provide information about the training set used for the wheezo's algorithm.
9. How the ground truth for the training set was established:
- Not provided. As the training set details are not included, how its ground truth was established is also not available in this summary.
§ 868.1900 Diagnostic pulmonary-function interpretation calculator.
(a)
Identification. A diagnostic pulmonary-function interpretation calculator is a device that interprets pulmonary study data to determine clinical significance of pulmonary-function values.(b)
Classification. Class II (performance standards).