(457 days)
Withings Sleep Rx is indicated to record a patient's Withings index during sleep as an aid for diagnosis of obstructive sleep apnea (OSA).
The Withings Sleep Rx is also indicated to record heart rate and movement in an automatic contactless manner.
The device is designed for use in home-screening of adults with suspected possible sleep breathing disorders. Results are used to assist the healthcare professional in determining the need for further diagnosis and evaluation. The system is not intended as a substitute for full polysomnography when additional parameters such as sleep stages, limb movements, or EEG activity are required.
The device is indicated for use in adults weighing ≤ 350 lbs in a home environment during sleep and resting conditions.
This device is not indicated for active patient monitoring, as it does not provide alarms for timely response in life-threatening situations.
The Withings Sleep Rx is a device intended as an aid for diagnosis of obstructive sleep apnea (OSA). It is intended for home use. The device is placed under the mattress and is contactless with the user. It provides a Withings index based on breathing (sound, variations of pressure in the bladder) and heart rate measured in a contactless manner. The number of breathing events per hour is displayed to the user in the companion app. The results are used to assist the healthcare professional in determining the need for further diagnosis and evaluation.
In addition, the device records heart rate and movement during sleep in an automatic contactless manner. The recordings are displayed in the companion app.
Withings Sleep Rx is composed of the following components: (1) Mat (hardware); (2) Withings Sleep Rx embedded software included in the Mat and (3) Companion App included in a companion mobile application.
The Withings Sleep Rx device is cleared for recording a patient's "Withings index" during sleep as an aid for diagnosing obstructive sleep apnea (OSA), and for recording heart rate and movement in an automatic, contactless manner. It is intended for home screening of adults with suspected sleep breathing disorders, to assist healthcare professionals in determining the need for further diagnosis.
Here's a breakdown of the acceptance criteria and supporting studies:
1. Acceptance Criteria and Reported Device Performance
| Parameter / Indication | Acceptance Criteria | Reported Device Performance (Withings Sleep Rx) |
|---|---|---|
| Withings Index (OSA Screening) | ||
| Se (Sensitivity) for AHI ≥ 15 | Lower bound of 95% CI > 0.70 | 0.88 (95% CI lower bound: 0.79) |
| Sp (Specificity) for AHI ≥ 15 | Lower bound of 95% CI > 0.70 | 0.886 (95% CI lower bound: 0.733) |
| AUC for AHI ≥ 15 | N.A. | 0.926 (95% CI lower bound: 0.873) |
| Se (Sensitivity) for AHI ≥ 30 | Lower bound of 95% CI > 0.70 | 0.86 (95% CI lower bound: 0.733) |
| Sp (Specificity) for AHI ≥ 30 | Lower bound of 95% CI > 0.70 | 0.912 (95% CI lower bound: 0.818) |
| AUC for AHI ≥ 30 | N.A. | 0.954 (95% CI lower bound: 0.916) |
| Heart Rate Estimation | ||
| Accuracy | Lower bound of 95% CI > 0.95 | 0.9597 (95% CI lower bound: 0.9523) |
| Movement Detection | ||
| Se (Active / non active) | > 0.80 | 0.92 (95% CI: 0.90, 0.94) |
| Sp (Active / non active) | > 0.80 | 0.92 (95% CI: 0.89, 0.94) |
| AUC (Full body / legs) | > 0.80 | 0.94 (95% CI: 0.92, 0.95) |
| AUC (Legs / arms) | > 0.80 | 0.93 (95% CI: 0.91, 0.95) |
| AUC (Arms / no movement) | > 0.80 | 0.89 (95% CI: 0.87, 0.92) |
2. Sample Size and Data Provenance
- Withings Index (OSA Screening):
- Sample Size: 118 patients.
- Data Provenance: The study was conducted with patients referred to a PSG test in a sleep laboratory, suggesting a clinical setting in a specific geographic location (publication mentions "J Clin Sleep Med," and authors are from various institutions, potentially implying an international or multi-center European study due to authors' affiliations). The study involved simultaneous polysomnography (PSG), making it a prospective (or at least concurrent data collection) study.
- Heart Rate Estimation:
- Sample Size: Data pooled from two clinical studies (ESAS and VPASS). Specific combined sample size not directly stated, but the studies were described as enrolling patients with suspected sleep apnea syndrome referred for a sleep study analysis.
- Data Provenance: Both studies were conducted with the subject device and involved simultaneous polysomnography (PSG), implying prospective or concurrent data collection in a clinical setting related to sleep studies.
- Movement Detection:
- Sample Size: Participants in an internal human study. Specific sample size not stated.
- Data Provenance: Internal study with predetermined movements, suggesting a controlled, laboratory-like setting.
3. Number of Experts and Qualifications for Ground Truth - Test Set
- Withings Index (OSA Screening):
- Number of Experts: Not explicitly stated, but "simultaneous polysomnography (PSG) manually scored by certified specialists" implies multiple certified specialists.
- Qualifications: "Certified specialists" in manual scoring of PSG, following AASM guidelines.
- Heart Rate Estimation:
- Number of Experts: Not explicitly stated, but "simultaneous polysomnography (PSG) scored by a qualified investigator following AASM guidelines" implies qualified investigators.
- Qualifications: "Qualified investigator" following AASM (American Academy of Sleep Medicine) guidelines.
- Movement Detection: Not applicable as the ground truth was based on predetermined movements by participants.
4. Adjudication Method for the Test Set
- Withings Index (OSA Screening) and Heart Rate Estimation: The information provided does not specify an explicit adjudication method (e.g., 2+1, 3+1). It states "manually scored by certified specialists" or "scored by a qualified investigator," which might imply single scoring or an internal consensus process, but no detail on a formal adjudication protocol is given.
- Movement Detection: Not applicable, as ground truth was based on pre-defined movements.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No information is provided about a multi-reader multi-case (MRMC) comparative effectiveness study to assess the effect size of human readers improving with AI vs. without AI assistance. The studies focused on the performance of the device itself against established clinical standards (PSG).
6. Standalone (Algorithm Only) Performance
- Yes, the studies primarily assessed the standalone performance of the Withings Sleep Rx device.
- The "Withings Index" for OSA screening was compared directly against PSG.
- The heart rate estimation was compared against simultaneous PSG data.
- The movement detection was evaluated based on the device's ability to identify pre-defined participant movements.
7. Type of Ground Truth Used
- Withings Index (OSA Screening) and Heart Rate Estimation: Expert Consensus (PSG scoring). Polysomnography (PSG) manually scored by certified specialists/qualified investigators following AASM guidelines is considered the gold standard for sleep disorder diagnosis.
- Movement Detection: Predefined movements/experimental protocol. The ground truth was based on the participants performing known, predetermined movements for specific durations, allowing for unambiguous identification.
8. Sample Size for the Training Set
- The document explicitly states regarding heart rate estimation:
- "ESAS was designed to train the algorithm calculating the Withings index of Sleep Rx, but not to train the estimation of heart rate."
- "VPASS was designed to validate the Withings index, but not to train the estimation of heart rate."
- While these studies mention their role in training or validating the Withings index algorithm, the specific sample size used solely for algorithm training for the Withings Index, heart rate, or movement detection is not provided. The 118 patient study listed under "Clinical study for the validation of the Withings' index" is explicitly for validation of the Withings' index.
9. How the Ground Truth for the Training Set Was Established
- For the ESAS study, which was "designed to train the algorithm calculating the Withings index," the ground truth would have been established through simultaneous polysomnography (PSG) manually scored by certified specialists, similar to the validation studies. However, the exact details of the ground truth establishment specifically for the training set are not fully elaborated in this document, beyond stating its purpose was for training.
§ 868.2375 Breathing frequency monitor.
(a)
Identification. A breathing (ventilatory) frequency monitor is a device intended to measure or monitor a patient's respiratory rate. The device may provide an audible or visible alarm when the respiratory rate, averaged over time, is outside operator settable alarm limits. This device does not include the apnea monitor classified in § 868.2377.(b)
Classification. Class II (performance standards).