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 Nox RIP Belts are intended for measuring of respiratory effort signals. They function as accessories for sleep/polysomnography (PSG) systems.
The Nox RIP Belts are indicated for use on patients greater than 2 years of age.
The intended environments are hospitals, institutions, sleep centers, sleep clinics, or other test environments, including the patient 's home.

The RIP Belt Cables are intended to interconnect Nox RIP belts (respiratory effort sensors) and Nox sleep devices, to allow measuring of respiratory effort signals.
The RIP Belt Cables are indicated for use on patients greater than 2 years of age.
The intended environments are hospitals, institutions, sleep centers, sleep clinics, or other test environments, including the patient´s home.

The Third Party RIP Belt Cables are intended to allow measuring of respiratory effort signals by interconnecting Nox RIP belts (respiratory effort sensors) and sleep devices with oscillation circuitry capable of measuring inductance between 1 and 5 µH.
The Third Party RIP Belt Cables are indicated for use on patients greater than 2 years of age.
The intended environments are hospitals, institutions, sleep centers, sleep clinics, or other test environments, including the patient's home.

The Nox RIP Belts are respiratory effort sensors that are intended to function as an accessory with sleep/polysomnography (PSG) systems. The RIP Belts measure respiratory effort signals based on Respiratory Inductance Plethysmography (RIP) technology, which is the gold standard technology for respiratory effort belts.
Two RIP belts are used to measure the respiratory effort of the patient. One belt is placed around the patient's abdomen and the other around the patient's thorax. Both abdomen and thorax belts are identical.
The Nox RIP Belt Cables are used to connect between the respiratory effort sensor (RIP belts) and the applicable sleep recorder/polysomnography (PSG) system.
There are two product groups for the Nox RIP Belt Cables; RIP Belt Cables and Third Party RIP Belt Cables.
The RIP Belt Cables are designed for use with Nox recorders only. Those are abdomen cables only because the thorax belt is attached directly to the Nox recorders.
The Third Party RIP Belt Cables are designed for use with third party recorders. The Third Party RIP Belt Cables come in pairs for abdomen and thorax.

The provided document is a 510(k) premarket notification for Nox RIP Belts and Nox RIP Belt Cables. The core of this submission is to demonstrate substantial equivalence to a predicate device, not necessarily to set new performance acceptance criteria through a clinical study in the same way an AI-driven diagnostic might.

Therefore, the acceptance criteria and study described here are focused on demonstrating that the new devices perform equivalently to the predicate, and comply with relevant safety standards.

Here's an attempt to extract the information you requested, based on the provided text, while noting the differences in context for a traditional medical device accessory vs. an AI diagnostic:

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a submission for device accessories (RIP belts and cables) demonstrating substantial equivalence to a predicate, the "acceptance criteria" are primarily related to meeting performance specifications and safety standards, and showing clinical equivalence to the predicate's signal quality. There aren't specific metrics like sensitivity/specificity for disease detection.

• ISO 14971 (Risk Management)
• ISO 15223-1 (Symbols)
• AAMI/ANSI/ES 60601-1 (Basic Safety & Essential Performance)
• IEC 60601-1-2 (EMC)
• AAMI/ANSI/IEC 62366 (Usability Engineering)
• 21 CFR 898 (for Third Party RIP Belt Cables) |
  | Functional | Conformance to design input/specifications. | Verification testing: Design output conforms to design input, fulfilling all physical characteristics, performance, functional, interface, packaging, labeling, safety, and reliability requirements. |
  | Usability | Minimize use errors and risks. | Usability testing resulted in all usability goals passed. |
  | Signal Quality | Clinically equivalent signal to predicate. | Signal integrity tests (signal-to-noise ratio, signal range, bandwidth, linearity) for new devices compared to predicate (QDC-PRO AND NOX-RIP) demonstrated clinical equivalence. |
  | Risk Management | Risks appropriately managed. | Risk analysis performed according to ISO 14971; appropriate measures implemented and their effectiveness verified/validated. |
  | Material/Physical Equivalence | Materials do not raise new safety/effectiveness concerns. | Verification testing and risk analysis show minor differences in material do not raise new questions about safety and effectiveness (for RIP Belt Cables). |
  | Connector Equivalence | Different connectors do not raise new safety/effectiveness concerns. | Verification testing, signal integrity comparison, and risk analysis show different connectors do not raise new questions about safety and effectiveness (for RIP Belt Cables). |

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

The document does not specify a "test set" in the context of patient data or clinical images for an algorithm. The testing described is primarily bench testing, engineering verification, and validation against product requirements and standards.

• Sample Size for Test Set: Not applicable in the context of patient-specific data for algorithm performance. The "samples" would be the manufactured devices (RIP Belts and Cables) themselves. The number of devices tested is not specified, but it implies a statistically sound sample for verification and validation activities.
• Data Provenance: Not applicable for patient data. The provenance of the testing results is "thorough internal testing" conducted by Nox Medical ehf.

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

Not applicable. As a medical device accessory focused on signal measurement and equivalence to a predicate, the "ground truth" is established by direct physical/electrical measurements against known standards and the predicate device's performance, rather than expert interpretation of a clinical finding.

4. Adjudication Method for the Test Set

Not applicable. There is no expert adjudication mentioned, as the nature of the device (respiratory effort sensors) involves direct measurement and comparison, not subjective interpretation.

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

Not applicable. This device is a sensor and cable accessory, not an AI diagnostic tool that assists human readers.

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

Not applicable. This device does not involve an algorithm with standalone performance. It measures respiratory effort signals, which are then used by sleep/polysomnography (PSG) systems, presumably to be interpreted by healthcare professionals.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The "ground truth" for the performance evaluation of these accessories primarily consists of:

• Engineering Specifications and Standard Compliance: Adherence to established ISO and IEC standards for medical devices (e.g., electrical safety, EMC, risk management, usability).
• Predicate Device Performance: The QDC-PRO AND NOX-RIP (K124062) device serves as the benchmark for "clinical equivalence" of signal quality. New devices' signals were compared against the predicate's signals using metrics like signal-to-noise ratio, signal range, bandwidth, and linearity.

8. The Sample Size for the Training Set

Not applicable. There is no "training set" as this device does not involve machine learning or AI.

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

Not applicable. There is no training set for this type of device.

Ask a specific question about this device