Search Results

The Luna® G3 BPAP System is a Bi-level PAP (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. It is to be used on patients > 66 lbs / 30 kg for whom CPAP therapy has been prescribed.

The Luna® G3 BPAP system is a microprocessor controlled, blower-based system that generates positive airway pressure to support treatment of obstructive sleep apnea. Its hardware design is identical to the previously cleared Luna® G3 BPAP 25A (K201620). The subject device includes two models, with different pressure ranges. They both have four therapy modes, which are CPAP, Spontaneous (S), Timed (T) and Spontaneous/Timed (S/T).

This 510(k) summary (K212263) describes a device modification to an existing Bi-level PAP system (Luna G3 BPAP System). The core of the submission revolves around demonstrating substantive equivalence to a predicate device (Luna G3 BPAP 25A, K201620) and referencing a device (Juno VPAP ST-A, K153061) for new functionalities.

It is crucial to understand that this document describes a device intended for treatment of Obstructive Sleep Apnea (OSA), providing positive airway pressure. It is not an AI/ML powered diagnostic device that would typically involve a multi-reader multi-case (MRMC) study or complex ground truth establishment from expert consensus or pathology, as might be seen for an imaging AI.

Therefore, many of the typical "acceptance criteria" and "study types" for AI/ML-powered devices, such as those related to standalone performance (e.g., sensitivity, specificity, AUC), MRMC studies, and expert ground truth establishment for a diagnostic output, are not applicable to this type of medical device submission.

Instead, the acceptance criteria and supporting studies are focused on engineering and performance characteristics of the medical device itself, ensuring it functions safely and effectively as intended and is equivalent to previously cleared devices.

Here's an analysis based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't present a single aggregated table of "acceptance criteria" versus "reported performance" for a diagnostic output as would be seen for AI/ML diagnostic tools. Instead, it details specific performance tests and standards met, comparing the subject device's characteristics to its predicate and reference devices. The "acceptance criteria" are implied by adherence to recognized standards and demonstrated equivalence to the cleared predicate.

Here's an interpretation of relevant performance characteristics that serve as de facto acceptance criteria and their reported performance:

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

This is an engineering and performance validation study for a medical device, not a clinical study involving patient data for diagnostic accuracy.

• Sample Size: Not applicable in the traditional sense of patient data. The "test set" consists of the physical device units subjected to various engineering and performance tests (e.g., electrical safety, fluid dynamics, sound, software functionality). The document does not specify the number of physical units tested, but it would typically involve a small number of production or pre-production units.
• Data Provenance: Not applicable in the sense of country of origin of patient data. The tests are performed in a laboratory setting by the manufacturer, or by accredited third-party labs on behalf of the manufacturer, to verify product specifications and compliance with standards. The manufacturing location is indicated as Beijing, China (BMC Medical CO., LTD.).
• Retrospective or Prospective: Not applicable. These are engineering validation tests.

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

Not applicable. The "ground truth" for this type of device is defined by engineering specifications, validated performance against benchmarks (predicate and reference devices), and adherence to international recognized standards (e.g., ISO, IEC). There are no human "experts" establishing a clinical "ground truth" diagnosis for the device's output in the way a radiologist would for an imaging AI. The "experts" involved would be the engineers, quality assurance personnel, and regulatory affairs specialists who design, test, and approve the device.

4. Adjudication Method for the Test Set

Not applicable. There is no subjective interpretation or "adjudication" of results in the way there would be for a clinical diagnostic study with human readers. Test results are objective measurements against defined performance criteria and standards.

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 is not an AI/ML-powered diagnostic device, nor is it designed to assist human readers in interpretation. It is a breathing therapy device. Therefore, an MRMC study is irrelevant to this submission.

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

This device does not have a "standalone" algorithmic component in the sense of a diagnostic AI assessing, for example, medical images. Its "algorithm" refers to the control software that manages the positive airway pressure delivery. The "standalone performance" refers to the device's ability to accurately deliver and control pressure, humidification, and other functions as per its specifications, which is what the various performance tests (e.g., static pressure, dynamic pressure, maximum flow rate, rise time, display accuracy) described under "Non-Clinical Performance Testing" are designed to evaluate. The results of these tests demonstrate the device's standalone performance in a lab setting.

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

The "ground truth" for this device's performance validation is based on:

• Engineering Specifications: The device's design parameters and target performance levels.
• International Standards: Adherence to recognized medical device standards (e.g., ISO 80601-2-70, ISO 80601-2-74, IEC 60601-1-2) which define acceptable ranges for various functional properties.
• Predicate Device Performance: The established, cleared performance characteristics of the Luna G3 BPAP 25A (K201620) and the relevant functionalities of the Juno VPAP ST-A (K153061). The current submission leverages the "substantial equivalence" argument, meaning the performance of the new device is compared to and validated as being equivalent to the legally marketed predicate.

8. The Sample Size for the Training Set

Not applicable. This is not an AI/ML model that is "trained" on a "training set" of data. The device's internal control software/algorithm is based on fixed programming, not machine learning.

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

Not applicable for the same reason as point 8. The "ground truth" for the device's design and programming comes from established physiological principles of breathing support and engineering principles for mechanical ventilation devices.

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

iCodeConnect, in conjunction with a Luna CPAP or Auto-CPAP device, is intended for use in treating obstructive sleep apnea (OSA) on adult patients (>30 kg).

iCodeConnect is intended to augment the standard follow-up care of patients diagnosed with obstructive sleep apnea by displaying usage and therapeutic information that has been transmitted from the patient's Luna CPAP or Auto-CPAP therapy device located in the home to the clinician or healthcare professional. iCodeConnect also provides remote settings capabilities.

iCodeConnect is a web based patient management system used to store and manage sleep compliance and efficacy data uploaded from a Luna CPAP or Auto-CPAP device.
iCodeConnect allows device patient data to be uploaded using a variety of methods, including manual entry, SD Card, and wireless transmission. Use of wireless transmission (i.e. WiFi) can provide wireless compliance monitoring and remote settings update functions.

For wireless transmission, iCodeConnect consists of the wireless data transmission module Wi-Fi kit and web based iCodeConnect patient management software. The Wi-Fi Kit is intended to be used in conjunction with the Luna CPAP System (E-20C-H-O), Auto-CPAP System (E-20A-H-O / E-20AJ-H-O), which were cleared in K141770.

1. iCodeConnect Software is an analysis and management platform for the patient's therapy data. This platform, adopting the form of a website, not only realizes the uniform management of the patient's data and the information of the provider, the doctor and the patient, but also allows for the Wi-Fi Kit or other wireless communication module to transmit data and remotely updating therapy device settings, which reduces the inconvenience brought by the traditional mailing of SD card and makes data collection more timely.

Wi-Fi Kit is an accessory module that attaches via USB cable to the data output port of a Luna® CPAP or Auto-CPAP devices. The wireless module Wi-Fi Kit uploads the device's therapy data to the iCodeConnect software with the help of Wi-Fi off-the-shelf technology. After connecting to the internet. the wireless kit shall automatically collect the user information, statistical information and detailed information in the therapy device for uploading.

The provided text describes the iCodeConnect device and compares it to a predicate device, EasyCare Online, to establish substantial equivalence. However, it explicitly states that clinical testing was NOT required to demonstrate the safety and effectiveness of iCodeConnect. Therefore, the document does not contain information about acceptance criteria for device performance based on a clinical study, nor does it detail a study proving the device meets such criteria.

The document focuses on non-clinical testing for functional verification and device performance, and software verification to demonstrate substantial equivalence to the predicate device.

Here's a breakdown of the information available based on your request, with an emphasis on what is not present:

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

• No specific acceptance criteria for a clinical study are provided. The table in the "Substantial Equivalence" section (pages 8-9) compares features and functions of the proposed device (iCodeConnect) with the predicate device (EasyCare Online). This table demonstrates equivalence in various aspects, but these are generally functional and technical specifications, not clinical performance metrics with acceptance criteria.
• Reported device performance (clinical): Not applicable, as clinical testing was not performed/required.
• Reported device performance (non-clinical/functional): The document states that "Non-clinical testing of the iCodeConnect has been carried out to cover functional verification and device performance. The proposed iCodeConnect has been tested to appropriate standards and other applicable requirements." (page 6). It further concludes that "Hardware testing carried out for iCodeConnect indicates it meets design and performance functional requirements. Software verification demonstrates that device features and the system configuration functions are substantially equivalent to the predicate device." (page 11). No specific quantitative performance metrics from these tests are reported in the summary provided.

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 as clinical testing was not conducted. Sample sizes for non-clinical functional testing are not specified.

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 as clinical testing was not conducted, and thus there was no "test set" requiring expert-established ground truth in a clinical context.

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

• Not applicable as clinical testing was not conducted.

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. The iCodeConnect device is a patient management system for CPAP/Auto-CPAP data and remote settings, not an AI-assisted diagnostic tool that would typically involve an MRMC study.

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

• This device is a patient management system and wireless data transmission module. Its "standalone" performance would likely refer to its functional accuracy in data transfer, storage, display, and remote setting capabilities. The document indicates these aspects were verified through non-clinical testing and software verification, concluding they meet design and performance requirements and are substantially equivalent to the predicate (pages 6, 11). However, specific metrics for this "standalone" performance are not provided.

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

• Given the absence of clinical testing, there is no mention of ground truth established through expert consensus, pathology, or outcomes data. For functional testing, the "ground truth" would likely be defined by the expected behavior and output based on design specifications and engineering standards.

8. The sample size for the training set

• Not applicable. The iCodeConnect is described as a web-based patient management system and a wireless data transmission module. There is no indication it uses machine learning or AI that would require a "training set" in the context of typical clinical algorithm development.

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

• Not applicable for the reasons mentioned in point 8.

Ask a specific question about this device

The Luna® CPAP and Auto CPAP System are intended to deliver pressure for the treatment of Obstructive Sleep Apnea. The optional integrated hunidifier is indicated for the humidification and warming of air from the flow generator. These devices are intended for single patient use by prescription in the home or hospital/institutional environment on adult patients.

The materials of water chamber of Luna® CPAF and Auto CPAP device were changed. The suppliers of Polycarbonate and silicone were changed. The basic functional and performance characteristics of the Luna® CPAP and Auto CPAF devices are unchanged from the predicate devices (K141770).

This document (K153387) is a 510(k) premarket notification for a medical device (Luna® CPAP and Auto CPAP System) to the U.S. Food and Drug Administration (FDA). It is not a study report that describes the acceptance criteria and performance of an AI/ML device in the way requested. Instead, it is a submission seeking clearance to market a modified version of an existing device (K141770) based on demonstrating "substantial equivalence" to the predicate device.

Therefore, the specific information requested about acceptance criteria, study details, sample sizes, ground truth establishment, expert involvement, and MRMC studies for an AI/ML device is not present in this document.

The document primarily focuses on:

• Device Modification: The only modification is a change in the materials used for the water chamber of the Luna® CPAP and Auto CPAP system. The suppliers of Polycarbonate and silicone were changed.
• Demonstration of Substantial Equivalence: The submission asserts that the modified device is substantially equivalent to the predicate device (K141770) because it has the "same intended use, same operating principle, same technology, and same manufacturing process."
• Non-Clinical Testing for Material Change: To address the material change, biological and mechanical tests were conducted on the new materials and the water chamber.

Here's how the information provided in the document relates to your request, highlighting what can be extracted and what cannot:

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

• Not Applicable in the AI/ML context. This document is about a material change in a CPAP device, not an AI/ML diagnostic or prognostic tool.
• What is shown: The document refers to "appropriate biological tests conducted and passed for these components, in accordance with FDA guidance #G95-1" and "Series mechanical tests were also conducted to demonstrate the mechanical performance of the water chamber, including: drop test, leak test, and humidity performance test." The specific acceptance criteria for these tests (e.g., maximum allowable leakage, specific drop test pass/fail conditions) are not detailed in this summary, nor are the quantitative results of these tests, beyond a statement that they "demonstrated substantial equivalence."

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

• Not Applicable in the AI/ML context. This is not an AI/ML study.
• What is shown: The document does not specify sample sizes (e.g., number of water chambers tested for biocompatibility or mechanical performance). It also does not mention data provenance in the context of clinical studies, as this is a non-clinical material change submission.

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 in the AI/ML context. There is no "ground truth" establishment in the sense of expert review of images or clinical data for this type of submission. The "ground truth" here is the biological and mechanical safety/performance of the new materials, assessed through standardized lab tests.

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

• Not Applicable in the AI/ML context. No adjudication method is described as there's no diagnostic or interpretative task involved.

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 is not an AI/ML device, and no MRMC study was performed or is relevant to this submission.

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

• Not Applicable. This is not an AI/ML algorithm.

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

• What is shown: The "ground truth" for this submission are the results of standardized biocompatibility tests (ISO 10993 series, including Genotoxicity, Cytotoxicity, Implantation, Sensitization, and Irritation tests, plus Intracutaneous Reactivity, Ames test, In vitro Mammalian Cell Gene Mutation Test, Skin Sensitization Mammalian Test, In vitro Chromosome Aberration In Vitro Cytotoxicity Test and Muscle Implantation Test) and mechanical performance tests (drop test, leak test, and humidity performance test). The acceptance is that the new materials and components pass these established safety and performance standards.

8. The sample size for the training set

• Not Applicable. This is not an AI/ML device where a training set is relevant.

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

• Not Applicable. See point 8.

In summary, this document is a regulatory submission for a minor device modification (material change) of a CPAP system and does not contain the information typically found in an AI/ML device study report.

Ask a specific question about this device