Search Results

Auto CPAP System is a CPAP (Continuous Positive Airway Pressure) device designed for the treatment of adult Obstructive Sleep Apnea (OSA) only, either in the hospital or at home.
Auto CPAP System is for prescription use only. It is a travel CPAP device intended for single-patient use.
LightTrip App is a mobile application for patients to remotely operate BMC Mini serial devices, and transmit, store and display usage and treatment information. It can also receive parameters and device firmware upgrade data from the cloud, and then transmit these data to the device. The LightTrip app also allows healthcare professionals to remotely configure compatible OSA therapy devices. LightTrip App is for prescription use only.

Auto CPAP System is a microprocessor controlled, blower-based system that generates continuous positive airway pressure (CPAP) to support treatment of obstructive sleep apnea. The system provides fixed or auto-adjust pressure from 4 to 20 cmH2O above the ambient atmospheric pressure to a patient's oral/nasal airway.
The Auto CPAP System is designed and developed on the basis of the predicate device Luna CPAP and Auto CPAP System (K153387). The parameters and algorithms of the two devices, such as the treatment mode (CPAP and AutoCPAP), the pressure range (4 to 20 cm H2O), and the Respiratory Event Detection, are consistent. Compared with the predicate device, the subject device does not include a humidifier and an LCD screen. The parameters of subject device are displayed and set via the LightTrip App.

The provided document is a 510(k) summary for the BMC Medical Co., Ltd. Auto CPAP System. Unlike typical AI/ML device submissions, this document focuses on the substantial equivalence of a CPAP device to existing predicate devices, primarily through bench testing for various physical and electrical performance metrics. It does not describe a study involving an AI algorithm that diagnoses or assists in the diagnosis of a medical condition in the way that would typically involve acceptance criteria related to diagnostic performance.

Therefore, many of the requested elements for describing AI/ML device performance, such as sample size for test sets, data provenance, expert ground truth, adjudication methods, MRMC studies, standalone performance, and training set details, are not applicable to this specific submission.

The "Performance Data" section primarily details bench testing and standards compliance, which are the acceptance criteria for a device like a CPAP system.

Here's an interpretation of the provided document in the context of your request, noting where information is not applicable:

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

For a CPAP device, the acceptance criteria are generally defined by performance standards that ensure the device delivers therapy accurately and safely. The document states that "bench testing were conducted according to ISO 80601-2-70:2015" and lists specific tests. The implication is that the device met the requirements of these standards.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

Not applicable. The "test set" here refers to the device itself being subjected to bench tests, not a dataset for an AI algorithm. Therefore, there is no sample size of patients or images, nor data provenance in the context of an AI study.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

Not applicable. The ground truth for CPAP device performance is established by recognized engineering and medical device standards (e.g., ISO 80601-2-70). It does not involve expert interpretation of clinical data in the same way an AI diagnostic device would.

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

Not applicable. Adjudication methods are relevant for resolving discrepancies in expert interpretations of clinical data, which is not part of this device's performance evaluation.

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 an Auto CPAP System, a therapy device, not an AI diagnostic tool intended to assist human readers.

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

This application is for an Auto CPAP System, which is a therapeutic device that delivers continuous positive airway pressure. While it contains algorithms for automatic pressure adjustment and respiratory event detection, these algorithms are integral to the device's function and are not presented as a standalone diagnostic tool. The performance of these internal algorithms is validated through the general device bench testing (e.g., "Dynamic pressure testing," "Algorithm" section, which states it utilizes the "same algorithm as the primary predicate device").

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

The "ground truth" for the device's performance is adherence to established international and national medical device standards (e.g., ISO 80601-2-70, IEC 60601 series) for safety and essential performance, as well as demonstrating equivalence to the predicate device's established performance characteristics (e.g., pressure delivery accuracy, sound levels).

8. The sample size for the training set

Not applicable. This device is not an AI/ML diagnostic system that reports on training data. The algorithms within the CPAP device (e.g., for auto-adjusting pressure, respiratory event detection) are stated to be the "same algorithm as the primary predicate device," implying they were previously developed and validated, not newly trained for this submission.

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

Not applicable, as there is no mention of a new training set for AI/ML development in this submission. The algorithms are inherited from a predicate device.

Ask a specific question about this device

The Luna® G3 BPAP 25A is a Bi-level Positive Airway Pressure) device designed for the treatment of adult Obstructive Sleep Apnea (OSA). The integrated humidification and warming of air from the flow generator device. These devices are intended for single-patient use by prescription in the home or hospital/ institutional environment on adult patients. If is to be used on patients >66lbs/30kg for whom CPAP therapy has been prescribed. The system can deliver bi-level therapy or auto bi-level therapy.

The Luna® G3 BPAP 25A is a microprocessor controlled, blower-based system that generates bi-level positive airway pressure (IPAP/EPAP) to support treatment of obstructive sleep apnea. The system provides fixed or auto-adjust pressure from 4 to 25 cmH2O above the ambient atmospheric pressure to a patient's oral/nasal airway.

This document, primarily a 510(k) Pre-market Notification to the FDA, describes a medical device called the Luna® G3 BPAP 25A, a Bi-level Positive Airway Pressure (BPAP) device for treating Obstructive Sleep Apnea (OSA). The document outlines its intended use, technological characteristics, and compares it to predicate devices to prove substantial equivalence.

Acceptance Criteria and Device Performance:

The acceptance criteria for the Luna® G3 BPAP 25A are not explicitly stated as quantitative performance metrics (e.g., accuracy, sensitivity, specificity) but are derived from comparing its technological characteristics and performance against legally marketed predicate and reference devices, as well as adherence to recognized regulatory standards. The "reported device performance" refers to the demonstrated compliance with these standards and the equivalence of its characteristics to established devices.

Here's a table summarizing the implicit acceptance criteria (based on predicate device characteristics and regulatory standards) and the reported performance of the subject device:

Study Details:

The document describes a submission for a 510(k) premarket notification, which relies on demonstrating substantial equivalence to existing legally marketed devices rather than conducting new clinical trials to prove efficacy from scratch. Therefore, the "study" is a collection of non-clinical tests and comparisons to predicate devices.

1. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

   • This document does not describe a clinical "test set" in the context of patient data. The evaluation is based on non-clinical performance data and comparison of device specifications.
   • For biocompatibility, electrical safety, EMC, software, and mechanical testing, specific sample sizes for components or devices under test are not provided. These are typically standard engineering and regulatory tests performed on a defined number of device units or materials.
   • The provenance of data for these non-clinical tests would be the manufacturer's testing facilities or certified third-party labs where the tests were performed. This is not explicitly stated but is implied by the submission from 3B Medical, Inc. (USA) and the manufacturer BMC Medical CO., LTD. (CHINA).

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

   • No "ground truth" established by external experts in medical diagnosis (like radiologists) is relevant for this type of 510(k) submission, as it focuses on engineering and performance equivalence, not a new clinical diagnostic claim.
   • The "experts" involved would be the engineers, toxicologists, and regulatory specialists who conducted and reviewed the non-clinical tests (biocompatibility, electrical safety, software validation, etc.) and assessed the substantial equivalence. Their specific qualifications are not detailed in this summary but are implicit in the adherence to international standards and FDA guidance.

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

   • There is no "adjudication method" in the sense of expert review of case data for this submission. The determination of substantial equivalence is made by the FDA based on the provided non-clinical data and comparisons.

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 MRMC comparative effectiveness study was done. This device is a therapeutic device (BPAP machine), not an AI-assisted diagnostic or interpretative tool that would involve human "readers."

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

   • The device has algorithms for controlling pressure delivery and detecting respiratory events. The document states that the blower and algorithm are the same as the primary predicate device for respiratory event detection and therapy. The AutoCPAP algorithm is identical to a reference device.
   • The performance of these algorithms is implicitly validated through the device's conformance to safety standards and its functional equivalence to predicate devices, which are already marketed and established as safe and effective. No specific "standalone" performance study of the algorithm in isolation (e.g., measuring its diagnostic accuracy against a gold standard in a clinical population) is described, as the 510(k) pathway focuses on equivalence.

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

   • There is no "ground truth" of clinical outcomes or expert consensus in this submission. The "ground truth" in this context refers to the established safety and performance characteristics of the predicate devices and the requirements of the relevant international and FDA standards (e.g., for biocompatibility, electrical safety, software V&V). The device demonstrates its performance by meeting these standards and showing that its specifications are equivalent or superior to the predicate devices without raising new safety or effectiveness concerns.

7. The sample size for the training set:

   • Not applicable. This device is not an AI/ML device that requires a "training set" in the sense of learning from clinical data. The algorithms are based on established principles of respiratory therapy.

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

   • Not applicable, as no training set is described.

Ask a specific question about this device