Search Results

DeepRESP is an aid in the diagnosis of various sleep disorders where subjects are often evaluated during the initiation or follow-up of treatment of various sleep disorders. The recordings to be analyzed by DeepRESP can be performed in a hospital, patient home, or an ambulatory setting. It is indicated for use with adults (22 years and above) in a clinical environment by or on the order of a medical professional.

DeepRESP is intended to mark sleep study signals to aid in the identification of events and annotation of traces; automatically calculate measures obtained from recorded signals (e.g., magnitude, time, frequency, and statistical measures of marked events); infer sleep staging with arousals with EEG and in the absence of EEG. All output is subject to verification by a medical professional.

DeepRESP is a cloud-based software as a medical device (SaMD), designed to perform analysis of sleep study recordings, with and without EEG signals, providing data for the assessment and diagnosis of sleep-related disorders. Its algorithmic framework provides the derivation of sleep staging including arousals, scoring of respiratory events and key parameters such as the Apnea-Hypopnea Index (AHI).

DeepRESP is hosted on a serverless stack. It consists of:

• A web Application Programming Interface (API) intended to interface with a third-party client application, allowing medical professionals to access DeepRESP's analytical capabilities.
• Predefined sequences called Protocols that run data analyses, including artificial intelligence and rule-based models for the scoring of sleep studies, and a parameter calculation service.
• A Result storage using an object storage service to temporarily store outputs from the DeepRESP Protocols.

Here's a breakdown of the acceptance criteria and the study details for the DeepRESP device, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria & Reported Device Performance:

The document doesn't explicitly state "acceptance criteria" as a separate table, but it compares DeepRESP's performance against manual scoring and predicate devices. I've extracted the performance metrics that effectively serve as acceptance criteria given the "non-inferiority" and "superiority" claims against established devices.

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

• Type I/II Studies (EEG present): 2,224 sleep recordings
• Type III Studies (No EEG): 3,488 sleep recordings (including 2,213 Type I recordings and 1,275 Type II recordings, processed to utilize only Type III relevant signals).
• Provenance: Retrospective study. Data originated from sleep clinics in the United States, collected as part of routine clinical work for patients suspected of sleep disorders. The patient population showed diversity in age, BMI, and race/ethnicity (Caucasian or White, Black or African American, Other, Not Reported) and was considered representative of patients seeking medical services for sleep disorders in the United States.

3. Number of Experts and Qualifications for Ground Truth:

The document explicitly states that the studies used "manually scored sleep recordings" but does not specify the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience"). It implicitly relies on the quality of "manual scoring" from routine clinical work in US sleep clinics as the ground truth.

4. Adjudication Method for the Test Set:

The document does not describe any specific adjudication method (e.g., 2+1, 3+1). It refers to "manual scoring" as the established ground truth.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No, a MRMC comparative effectiveness study was not reported. The study design was a retrospective data analysis comparing the algorithm's performance against existing manual scoring (ground truth) and established predicate devices. There is no information about human readers improving with AI vs. without AI assistance. The device is intended to provide automatic scoring subject to verification by a medical professional.

6. Standalone (Algorithm Only) Performance:

Yes, the study report describes the standalone performance of the DeepRESP algorithm. The reported PPA, NPA, OPA percentages, and ICC values represent the agreement of the automated scoring by DeepRESP compared to the manual ground truth. The device produces output "subject to verification by a medical professional," but the performance metrics provided are for the algorithmic output itself.

7. Type of Ground Truth Used:

The ground truth used was expert consensus (manual scoring). The document states "It used manually scored sleep recordings... The studies were done by evaluating the agreement in scoring and clinical indices resulting from the automatic scoring by DeepRESP compared to manual scoring."

8. Sample Size for the Training Set:

The document does not explicitly state the sample size used for the training set. The clinical validation study is described as a "retrospective study" used for validation, but details about the training data are not provided in this summary.

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

The document does not specify how the ground truth for the training set was established. It only describes the ground truth for the validation sets as "manually scored sleep recordings" from routine clinical work.

Ask a specific question about this device

Noxturnal Web is intended to be used for the diagnostic evaluation by a physician to assess sleep quality and as an aid for the diagnosis of sleep and respiratory-related sleep disorders in adults only.

Noxturnal Web is a software-only medical device to be used to analyze physiological signals and manually score sleep study results, including the staging of sleep, AHI, and detection of sleep disordered breathing events including obstructive apneas.

It is intended to be used under the supervision of a clinician in a clinical environment.

Noxturnal Web is a web-based software that can be utilized to screen various sleep and respiratoryrelated sleep disorders. The users of Noxturnal Web are medical professionals who have received training in the areas of hospital/clinical procedures, physiological monitoring of human subjects, or sleep disorder investigation. Users can input a sleep study recording stored on the cloud (electronic medical record repository) using their established credentials. Once the sleep study data has been retrieved, the Noxturnal Web software can be used to display, manually analyze, generate reports and print the prerecorded physiological signals.

Noxturnal Web is used to read sleep study data for the display, analysis, summarization, and retrieval of physiological parameters recorded during sleep and awake. Noxturnal Web facilitates a user to review or manually score a sleep study either before the initiation of treatment or during the treatment follow-up for various sleep and respiratory-related sleep disorders.

Noxturnal Web presents information from the input sleep study data in an organized layout. Multiple visualization layouts (e.g., Study Overview, Respiratory Signal Sheet, etc.) are available to allow the users to optimize the visualization of key data components. The reports generated by Noxturnal Web allow the inclusion of custom user comments, and these reports can then be viewed on the screen and/or printed.

The provided document is a 510(k) summary for the medical device Noxturnal Web. It states that clinical data were not relied upon for a determination of substantial equivalence. Therefore, there is no information in this document regarding a clinical study or a test set with expert-established ground truth.

However, the document does describe the performance expectations and how suitability was determined through non-clinical testing, specifically software verification and validation.

Here's the information based on the provided text, focusing on the non-clinical and comparative aspects:

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

The document does not present explicit quantitative acceptance criteria for performance in a table format with reported numerical device performance. Instead, it describes functional equivalence to the predicate device through comparative analysis and states that the software meets its pre-specified requirements and performs as intended.

The comparison table on pages 8-9 highlights the functional equivalences:

The general acceptance criterion is that the Noxturnal Web is "as safe and effective as the predicate devices" and "meets its pre-specified requirements."

2. Sample size used for the test set and the data provenance

The document explicitly states: "Clinical data were not relied upon for a determination of substantial equivalence." Therefore, there is no clinical test set of patient data with ground truth as would be used in a clinical study.

The testing performed was "Software verification and validation testing... to demonstrate safety and performance based on current industry standards," and "Verification and Validation testing of all requirement specifications defined for Noxturnal Web was conducted and passed." This implies that the 'test set' consisted of various software functions and their outputs, but not a large set of patient physiological recordings serving as a "test set" in the context of a clinical performance study. The data provenance and size of this kind of "test set" (software test cases) are not detailed in this summary.

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

Given that "Clinical data were not relied upon," there was no clinical test set requiring expert-established ground truth in the traditional sense for demonstrating substantial equivalence. The summary highlights that the device supports manual scoring completed by medical professionals who have received training in relevant areas (page 7). This implies that the human-in-the-loop performance is based on the expertise of the user, rather than the device itself establishing ground truth.

4. Adjudication method for the test set

Not applicable, as no clinical test set with established ground truth was used for assessing substantial equivalence.

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 study was done, as indicated by the statement "Clinical data were not relied upon for a determination of substantial equivalence." The device's primary function is to facilitate manual scoring by a clinician, not to provide AI-assisted automated interpretations that would then be compared to human-only interpretations via an MRMC study.

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

The device is described as "software-only medical device to be used to analyze physiological signals and manually score sleep study results" and "It is intended to be used under the supervision of a clinician in a clinical environment." This indicates that the device is not intended for standalone (algorithm only) performance without human-in-the-loop interaction for interpretation and scoring. The comparative table also notes that both the subject device and the primary predicate "rely on manual scoring."

7. The type of ground truth used

For the purpose of regulatory clearance, the "ground truth" for the device's functionality was its ability to replicate the features and performance of legally marketed predicate devices, as demonstrated through "comparative analysis, software and performance testing." The ground truth for interpreting sleep studies using this device resides with the trained medical professional who manually scores the data according to the "American Academy of Sleep Medicine (AASM) Manual for the Scoring of Sleep and Associated Events."

8. The sample size for the training set

Not applicable, as this device appears to be a software tool for manual scoring and analysis, rather than an AI/ML algorithm that requires a "training set" in the context of deep learning or machine learning models. The summary makes no mention of AI/ML or training data; its emphasis is on providing tools for manual clinician review.

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

Not applicable, for the same reasons as point 8.

Ask a specific question about this device

The Sleep Apnea Notification Feature (SANF) is a software-only mobile medical application that analyzes Apple Watch sensor data to identify patterns of breathing disturbances suggestive of moderate-to-severe sleep apnea and provides a notification to the user. This feature is intended for over-the-counter (OTC) use by adults age 18 and over who have not previously received a sleep apnea diagnosis and is not intended to diagnose, treat, or aid in the management of sleep apnea. The absence of a notification is not intended to indicate the absence of sleep apnea.

The Sleep Apnea Notification Feature (SANF) is an over-the-counter mobile medical application (MMA) intended to identify patterns of breathing disturbances suggestive of moderate-to-severe sleep apnea and provide a notification to the user. SANF is intended to run on compatible iOS (e.g. iPhone, iPad) and Apple Watch platforms. Users set up SANF and view their health data on the iOS platform. Prior to use, users must undergo educational onboarding. SANF uses accelerometer sensor data collected by the Apple Watch to calculate breathing disturbance values while a user is asleep. Breathing disturbances describe transient changes in breathing patterns, such as temporary breathing interruptions.

Breathing disturbance data is analyzed in discrete, consecutive 30-day evaluation windows, If patterns consistent with moderate-to-severe sleep apnea are identified within the 30-day evaluation window, the user is notified. SANF provides visualizations depicting the user's breathing disturbance data over various time scales. SANF is not intended to provide instantaneous measurements. Instead, once activated, SANF runs opportunistically in the background receiving signals from Apple Watch sensors for processing.

Here's a summary of the acceptance criteria and study details for the Sleep Apnea Notification Feature (SANF), based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

Sleepiz One+ is a contactless medical device intended to measure heart rate and respiration rate in adult patients, at rest or during sleep (in non-motion condition).

The Sleepiz One+ hardware unit is intended to be used by a healthcare professional when the recordings are performed in a clinical setting, or by patients or their caregivers when the recordings are performed in a home environment. The Sleepiz One+ web application is Intended for use by healthcare professionals.

Sleepiz One+ device can also detect the presence of patients and their body movements at rest or during sleep. This device is not indicated for active patient monitoring, as it does not provide alarms for timely response in life-threatening situations. It is not indicated for use on pregnant women or patients with active implantable devices.

Sleepiz One+ is a contactless medical device that uses radar technology to measure respiration rate and heart rate. The device is placed on a bedside table or a stand, mounted slightly higher than the mattress level, from where it detects the presence of a patient and their physiological signals. From that position, distance changes between the device and the patient's body are captured by Doppler radar. The recorded signals are then transmitted to the cloud software where these are analyzed by the signal processing software ("Sleep Analytics Software") to obtain respiration rate, heart rate and facilitate the monitoring of the presence of the patient and their body movement. These outputs are then displayed on the web application to allow the annotation of the data, compilation of results into reports, and the management of the hardware units.

Here's a breakdown of the acceptance criteria and study information for the Sleepiz One+ device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

• Accuracy: +/- 3 breaths per minute (99% accuracy rate)
• 95% Limits of Agreement: -1.42 to 0.97 breaths/min (for neurorehabilitation ward patients)
• 95% Limits of Agreement: -1.3 to 0.8 breaths/minute (for patients suspected of sleep apnea)

Compared to end-tidal CO2 (etCO2) via capnography:

• Accuracy: +/- 2 breaths/minute (93.7% accuracy)
• 95% Limits of Agreement (instantaneous breathing rate): -2.51 to 2.04 breaths/minute
• Mean Absolute Error (average breathing rate): 0.79 breaths/minute
• 95% Limits of Agreement (average breathing rate): -2.63 to 2.01 breaths/minute |
  | Heart Rate Accuracy | The subject device performs comparably to established methods for heart rate measurement. | Compared to Electrocardiography (ECG):
• Accuracy: +/- 5 beats per minute (94% accuracy rate)
• 95% Limits of Agreement: -2.64 to 5.82 beats/min (for neurorehabilitation ward patients)
• 96% heart rate accuracy (for patients suspected of sleep apnea) |
  | Safety | Complies with relevant electrical, mechanical, and emission safety standards. | Passed all electrical and mechanical safety tests per ANSI AAMI ES60601-1 and IEC 60601-1-11. Passed all emission tests per IEC 62304 and Federal Register CFR 47 Part 15 subpart B. Passed Coexistence Immunity and Wireless Crosstalk tests per 27701:2019 and ANSI IEEE C63.27-2017. |
  | Software Performance | Software components function as intended and meet user needs. | All software components verified against System Requirements Specifications and system-level validated against user needs. All tests passed. |
  | Risk Management | Identified hazards are mitigated through risk controls. | Risk analysis performed per ISO 14971; risk controls implemented. Cybersecurity risks identified and addressed through penetration testing. |
  | Usability | Device is usable for intended users in intended environments. | Extensive Human Factor Engineering/Usability Engineering performed per IEC 62366-1 and FDA guidance; found substantially equivalent for intended users, uses, and environments. |

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

The clinical studies involved a total of 199 subjects.
The data provenance is from clinical studies conducted with patients in a neurorehabilitation ward and patients suspected of suffering from sleep apnea. The studies were prospective as patients were continuously monitored overnight.

Specific sample sizes for each comparison are:

• Neurorehabilitation ward patients: 59 patients for respiration rate (compared to respiratory effort belt), 32 patients for heart rate (compared to ECG).
• Patients suspected of sleep apnea: 105 patients for respiration rate, 73 patients for heart rate.
• etCO2 comparison: 35 participants.

The country of origin is not explicitly stated in the provided text.

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

The text indicates that some measurements were "manually scored by a healthcare professional" for the comparison with end-tidal CO2 (etCO2). However, it does not specify the number of experts involved or their specific qualifications (e.g., years of experience, specialty). For other comparisons (respiratory effort belt, ECG), the ground truth devices are referenced, but expert involvement in scoring those particular signals is not detailed beyond the etCO2 mention.

4. Adjudication Method for the Test Set

The text does not explicitly state an adjudication method (e.g., 2+1, 3+1). It implies that the comparator device measurements (e.g., respiratory effort belt, ECG, etCO2) served as the direct reference or "ground truth." For the "manually scored" etCO2 data, it's not clear if multiple healthcare professionals scored the data and an adjudication process was used.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

An MRMC comparative effectiveness study was not explicitly mentioned or performed to assess improvement of human readers with AI assistance. The studies described are focused on the device's accuracy against established medical reference standards.

6. Standalone (Algorithm Only) Performance

Yes, the studies described are primarily standalone (algorithm only) performance evaluations. The Sleepiz One+ outputs (heart rate, respiration rate) were compared directly against reference devices (ECG, pulse oximetry, respiratory effort belt, nasal cannula, etCO2 measurements). While the device records and transmits data for healthcare professionals to view, the reported accuracy metrics are for the device's automated estimation of these vital signs.

7. Type of Ground Truth Used

The ground truth for the test set was established using:

• Established Medical Devices: Electrocardiography (ECG), pulse oximetry, respiratory effort belt, nasal cannula, and an FDA-cleared device for end-tidal CO2 (etCO2) measurements.
• Expert Scoring: For the etCO2 comparison, the ground truth was "manually scored by a healthcare professional."

Polysomnography devices (Somnotouch RESP (K140861), Nox A1 (K192469)) were used as comparator devices in the clinical studies, specifically using subsets of their channels for the performance assessment.

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set for the Sleepiz One+ device's algorithms.

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

The document does not specify how the ground truth for the training set was established. It only describes the methodology for the performance evaluation (test set).

Ask a specific question about this device