Search Results

The device provides positive pressure therapy for the treatment of adult obstructive sleep apnea syndrome in self breathing patients weighing over 30kg (66lbs). This product can be used in the home as well as in clinical/hospital environments.

The proposed device is a non-invasive, continuous positive airway pressure ventilator, incorporating a heated respiratory humidifier. The device is intended to treat obstructive sleep apnea by delivering a flow of positive airway pressure at a level prescribed by a physician to splint open the airway and prevent airway collapse. The proposed device is available in three types, which are Aurora, Resware and Zizmer. Each type is available in different models designed with different therapy modes and pressure ranges. The therapy modes are available in four types, which are CPAP, Spontaneous (S), Spontaneous/Timed (S/T) and Timed (T). The pressure range for the proposed devices is available in three types, which are 4-20cm H2O, 4-25cm H2O and 4-30cm H2O. Alarm module is incorporated in the device. The device will generate audio and visual alarm for airway leakage, motor malfunction and high motor temperature. The proposed device is provided non-sterile, and not to be sterilized by the user prior to use. The proposed device can be reused by single patient.

The provided text is a 510(k) Premarket Notification for a medical device (SysMed S/T, a noncontinuous ventilator for treating obstructive sleep apnea). It describes the device, its intended use, and states that non-clinical tests were conducted to demonstrate substantial equivalence to predicate devices based on compliance with various engineering, safety, and biocompatibility standards.

However, this document does NOT describe the acceptance criteria and the study that proves the device meets the acceptance criteria in terms of clinical performance, specifically an AI/ML type of study. The information requested, such as sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, and training set details, are typically found in clinical validation reports for AI/ML-driven medical devices.

The provided document focuses on demonstrating substantial equivalence based on physical and functional characteristics, and compliance with well-established performance and safety standards for medical ventilators. It does not involve AI/ML performance evaluation as would be described for an AI/ML-driven diagnostic or therapeutic device.

Therefore, I cannot populate the requested table and answer the study-specific questions based on the provided text. The document confirms that non-clinical tests were done to verify compliance with standards, but not a study demonstrating clinical performance against specific acceptance criteria relevant to AI/ML.

Here's why the document doesn't contain the requested information:

• Device Type: The SysMed S/T is a non-continuous ventilator. Its primary function involves delivering positive airway pressure. While it might incorporate some automated features (like therapy modes), the provided document does not indicate it's an AI/ML-driven device that makes diagnostic or treatment recommendations requiring complex clinical validation studies with human readers or AI-specific performance metrics like sensitivity, specificity, or AUC against a ground truth established by experts.
• 510(k) Process: The 510(k) pathway for medical device clearance primarily focuses on demonstrating "substantial equivalence" to a legally marketed predicate device. This often involves engineering bench testing, biocompatibility testing, and comparison of technical specifications, rather than a full-scale clinical trial or AI/ML performance study unless the device introduces novel technology or significant changes affecting safety or effectiveness.
• Lack of Clinical Data/AI Performance Metrics: The "Non-Clinical Test Conclusion" section lists various industry standards (e.g., IEC, ISO) that the device complies with, relating to electrical safety, electromagnetic compatibility, alarm systems, home healthcare environment use, sleep apnea therapy equipment, humidifying equipment, and biocompatibility. These are typical engineering and safety tests, not clinical performance studies for an AI/ML algorithm.

If this were an AI/ML device, the "Non-Clinical Test Conclusion" or a separate "Clinical Study" section would detail how the AI's performance was measured against a clinically relevant ground truth, including metrics like sensitivity, specificity, or area under the ROC curve, and would address the points in your query.

Ask a specific question about this device

The Oxygen Concentrator is intended for the administration of supplemental oxygen. This device is not intended for life supporting nor does it provide any patient monitoring capabilities. The system will be operated by trained personnel, at home, in community health care and medical institutions.

The Oxygen Concentrator adopts the principle of pressure swing adsorption technology. At normal temperature, the device can continuously supply a high concentration of supplemental oxygen (93%±3%). The main function of the proposed device includes supplying supplemental oxygen. The device also includes alarms for high temperature, low oxygen output, and interruption of power. The proposed device includes three models, which are M50, M40 and M30. The only difference of the three models is flow rate.

The provided document pertains to a 510(k) premarket notification for an Oxygen Concentrator. As such, it describes a medical device, not an AI/ML algorithm. Therefore, many of the requested details regarding acceptance criteria, study design for AI performance, expert adjudication, and ground truth establishment are not applicable to this document.

The document focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing and comparison of technical characteristics.

Here's a breakdown of the relevant information from the document, addressing the applicable parts of your request:

1. Table of acceptance criteria and the reported device performance

The document does not present "acceptance criteria" in the typical sense of a target performance metric for an AI algorithm. Instead, it describes compliance with established medical device standards and comparison to a predicate device. The "performance" is demonstrated by meeting these standards and showing similar technical characteristics to the predicate.

Below is a table summarizing the technical characteristics of the proposed device and how they compare to the predicate, which serves as the basis for the substantial equivalence determination. The "acceptance criteria" here are implied by the predicate device's characteristics and relevant standards.

Note on "Acceptance Criteria" for a non-AI/ML device: For this type of device, "acceptance criteria" are typically defined by compliance with recognized standards (e.g., ISO, IEC, AAMI) and demonstration of substantial equivalence to a legally marketed predicate device. The document explicitly states: "Non clinical tests were conducted to verify that the proposed device met all design specifications as was Substantially Equivalent (SE) to the predicate device."

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

This is not applicable as there is no "test set" in the context of an AI/ML algorithm's performance evaluation. The "testing" refers to non-clinical bench testing to demonstrate compliance with standards and safety/performance specifications of the physical device.

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

This is not applicable. No expert-established ground truth for an AI/ML algorithm's performance is involved in this 510(k) submission.

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

This is not applicable. No expert adjudication for an AI/ML algorithm's performance is 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

This is not applicable. This submission is for a physical medical device (oxygen concentrator), not an AI-assisted diagnostic or therapeutic tool.

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

This is not applicable. There is no algorithm to evaluate in a standalone manner.

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

This is not applicable. For this type of device, "ground truth" relates to the physical and functional parameters of the device (e.g., oxygen purity, flow rate, pressure) as measured by calibrated equipment and verified against engineering specifications and industry standards. It's not a diagnostic or clinical "ground truth."

8. The sample size for the training set

This is not applicable. There is no AI/ML algorithm involved, and thus no training set.

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

This is not applicable. There is no AI/ML algorithm involved, and thus no training set or associated ground truth.

Summary of the Study Proving Device Meets Acceptance Criteria (and Substantial Equivalence):

The "study" refers to non-clinical testing and comparative analysis rather than clinical trials or AI performance evaluations.

• Type of Testing: Non-clinical tests were conducted. These typically include bench testing for electrical safety, electromagnetic compatibility, oxygen concentration accuracy, flow rate stability, alarm functions, sound levels, and biocompatibility of patient-contacting materials.
• Standards Met: The device demonstrated compliance with several international and US standards, including:
  • AAMI / ANSI ES60601-1 (General requirements for basic safety and essential performance of medical electrical equipment)
  • IEC 60601-1-2 (Electromagnetic Compatibility)
  • ISO 80601-2-69 (Particular requirements for basic safety and essential performance of oxygen concentrator equipment)
  • ISO 10993-5 (Biological Evaluation - In Vitro Cytotoxicity)
  • ISO 10993-10 (Biological Evaluation - Irritation and Skin Sensitization)
  • VOCs and PM2.5 test (per EPA TO 15 and IP-10 method)
• Comparison to Predicate Device (K150930): A detailed comparison of technical characteristics (Table 1) was performed against the predicate oxygen generator.
  • Similarities were highlighted in classification, product code, regulation number, intended use principle, and oxygen purity.
  • Differences in flow rate range, sound level, oxygen purity warning threshold, electrical requirements, and outlet pressure were acknowledged and discussed. The submission argues that these differences do not raise different questions of safety and effectiveness because:
    • The proposed device's flow rate is within the predicate's range.
    • Even with a lower oxygen purity warning level (<82% vs <85%), both comply with ISO 80601-2-69.
    • The outlet pressure, while different, also complies with ISO 80601-2-69.
    • Electrical requirements, though different, comply with the relevant electrical safety and EMC standards.
• Conclusion: Based on the non-clinical tests and the comparison, the manufacturer concluded that the proposed device models are substantially equivalent to the predicate device.
• Clinical Study: The document explicitly states: "No clinical study is included in this submission." This indicates that the substantial equivalence determination for this device did not require human clinical data.

Ask a specific question about this device