Search Results

The Curasa AUTO CPAP (Continuous Positive Airway Pressure) with heated humidifier system is intended for the treatment of Obstructive Sleep Apnea only in spontaneously breathing patients weighing >30 kg. It is for use in the home or hospital /institutional environment.

The Curasa AUTO CPAP System with heated humidifier is used on adult patients for treatment of obstructive sleep apnea (OSA). The Auto CPAP system provides a stable continuous positive airway pressure (CPAP). The Auto mode detects breathing phenomena (e.g. snore, hypopnea) and automatically adjusts the delivered pressure. The humidifier provides warm, humidified air for comfort to the patient, reducing nose and airway dryness. The Curasa AUTO CPAP system includes the following accessories: a power supply, a Patient Air Circuit, and a U-tube connection between CPAP and humidifier. All of the accessories provided with the Curasa AUTO CPAP are identical to those provided with the predicate Curasa CPAP SD (K123897).

The Auto CPAP system has been modified based Curasa CPAP SD (K123897) hardware and software. The design of the humidifier and humidifier interface is identical to the referenced predicate device (Curasa CPAP SD, K123897). The basic function and performance characteristics of Curasa AUTO CPAP are similar to the referenced predicate device (Curasa CPAP SD K123897). The Auto mode of operation is similar to the referenced predicate, Respironics Remstar Auto CPAP (K012554).

The Curasa AUTO CPAP with Heated Humidifier System is intended for the treatment of Obstructive Sleep Apnea (OSA). The studies performed for this device included compliance with a number of electrical safety, biocompatibility, and performance standards, as well as a clinical study.

1. Table of Acceptance Criteria and Reported Device Performance

• Pressure Range: 4-20 cm H2O
• Pressure Stability: 4-20 cm H2O, +/- 2.0 cm H20
• Maximum Flow: 35 LPM | Pass (ISO 17510 compliant:
• Pressure Range: 4-20 cm H2O
• Pressure Stability: 4-20 cm H20 +/- 2.0 cm H20
• Maximum Flow: 35 LPM) |
  | Biocompatibility | ISO 10993-3: Genotoxicity, Carcinogenicity and Reproductive Toxicity
  ISO 10993-5: Tests for in vitro cytotoxicity
  ISO 10993-6: Test for local effect after implantation
  ISO 10993-10: Tests for irritation and skin sensitization
  ISO 10993-12: Sample Preparation and reference materials | Pass (Biocompatibility Tests - leveraged from predicate) |
  | Software | IEC 62304: Medical Device Software Software Life Cycle Process | Pass (Software Verification Testing) |
  | Environmental | IEC 60068-2-6: Environmental Testing -- Test FC: Vibration (sinusoidal)
  IEC 60068-2-34: Environmental Testing Test FC: Vibration (Random)
  IEC 60068-2-27: Basic Environmental Testing Procedure: Test Ea and guidance: Shock | Pass (Shock and Vibration Testing) |
  | Sound | Not explicitly defined, but generally related to acceptable noise levels for medical devices. | Pass (Sound Testing) |
  | Air Quality | Not explicitly defined, but related to user safety regarding airborne particles and volatile organic compounds. | Pass (VOC and PM2.5 Testing) |
  | Predicate Comparison (Functional Equivalence) | No statistical difference in AHI and SpO2 compared to predicate Respironics Auto CPAP. | Results showed that the Curasa AUTO CPAP is effective and that there is no statistical difference between the Curasa AUTO CPAP and the predicate Respironics Auto CPAP device based on AHI (Apnea/Hypopnea Index), minimum SpO2, and average SpO2. |
  | System and User Interface | Not explicitly defined, but generally refers to the device's operational functionality and ease of use. | Pass (System and User Interface Testing) |
  | IFU Validation | Not explicitly defined, but generally refers to ensuring the Instructions for Use are clear, complete, and accurate. | Pass (IFU Validation Testing) |
  | Safety (IPX1 / ESD) | IPX1 (Drip Proof Equipment) and Class II Electrical shock protection. | Pass (IPX1 / ESD) |
  | Reliability | Not explicitly defined, but generally refers to the consistent performance over time. | Pass (Reliability Test - leveraged from predicate) |
  | Packaging | Not explicitly defined, but generally refers to the ability of the packaging to protect the device during transport and storage. | Pass (Packaging Test - leveraged from predicate) |

2. Sample Size for the Test Set and Data Provenance

• Sample Size: 60 adult patients diagnosed with Obstructive Sleep Apnea (OSA).
• Data Provenance: Clinical study conducted at two (2) hospitals in China.
• Retrospective or Prospective: Prospective, as patients were enrolled and underwent a 3-night study protocol specifically for this evaluation.

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

The document does not specify the number or qualifications of experts used to establish the "ground truth" for the test set in the clinical study. However, the study involved Polysomnography (PSG) for diagnosing OSA and recording AHI and SpO2, which implies interpretation by trained sleep specialists or technicians.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method for the test set. It mentions that AHI, minimum SpO2, and average SpO2 were recorded by PSG, and p-values were calculated for before and after treatment groups, and for trial and control groups. This implies direct measurement and statistical comparison rather than a human reader adjudication process for the primary endpoints.

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

A MRMC comparative effectiveness study involving human readers and AI assistance was not performed. The clinical study compared the Curasa AUTO CPAP system's performance to a predicate device (Respironics Auto CPAP) in treating OSA patients, not the performance of human readers with or without AI assistance.

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

The device itself is an automated CPAP system, implying it operates "standalone" in its function of automatically adjusting pressure based on detected breathing phenomena. The clinical study evaluated the effectiveness of this automated function. However, the term "standalone performance" often refers to an algorithm's performance against a ground truth in an AI/imaging context, which is not directly applicable here. The clinical study assessed the overall device (hardware + embedded algorithms) performance in vivo.

7. The Type of Ground Truth Used

The ground truth for the clinical study was established using objective physiological measurements from Polysomnography (PSG). Specifically, AHI (Apnea/Hypopnea Index), minimum SpO2 (Pulse Oximeter Oxygen Saturation), and average SpO2 were recorded by PSG. These are standard, objective metrics for assessing the severity and treatment effectiveness of Obstructive Sleep Apnea.

8. The Sample Size for the Training Set

The document does not specify a separate "training set" sample size. The clinical study enrolled 60 patients to evaluate the device's performance, implying this dataset was for verification/validation rather than training a machine learning model from scratch. Given the device's "Auto mode" functionality is described as "similar to the referenced predicate, Respironics Remstar Auto CPAP (K012554)," it's likely the auto-adjusting algorithm was developed and refined using prior knowledge and potentially internal datasets, but this information is not provided for the Curasa device.

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

As no "training set" is explicitly mentioned for the Curasa AUTO CPAP's auto-adjustment algorithm within this document, the method for establishing its ground truth for training is not provided. If the auto-mode algorithm was adapted from the predicate, then its initial ground truth would have been established during the predicate's development.

Ask a specific question about this device

The K Series CPAP System, is designed for the treatment of Obstructive Sleep Apnea only in spontaneously breathing patients weighing >30 kg. It is intended to be used in the home or hospital/institutional environment.

The K Series CPAP systems are used on adult patients for treatment of obstructive sleep apnea (OSA). The K Series CPAP Systems has 3 commercially available models, Curasa CPAP (K120285), Floton CPAP (K120285), and Curasa CPAP SD (K123897). This 510(k) application adds the Curasa CPAP EUT model to the currently commercially available selection of models. as well as the AutoManager PC Software accessory. The K series CPAP system provides a stable continuous positive airway pressure (CPAP). The humidifier, which works with all the K Series CPAP Systems, provides warm, humidified air for comfort to the patient, reducing nose and airway dryness. Each K Series CPAP system also includes the following accessories: a power supply, a Patient Air Circuit, and a U-tube connection between CPAP and humidifier. The Curasa CPAP EUT has the same electronic design and similar software as the Curasa CPAP SD, except for the addition of EUT (expiratory unload trigger) feature. The EUT feature detects patient exhalation phase and reduces output pressure. EUT feature has 3 levels of pressure reduction. The CPAP EUT also works with a special accessory PC software tool, AutoManager™ AutoManager™ is used by the service provider to analyze the patient's CPAP compliant data and, if needed, update the CPAP pressure setting via the CPAP's SD card. The AutoManager™ software collects/updates CPAP device data via an SD card. The AutoManager™ PC software is an independent accessory to the CPAP device and runs on a stand-alone PC and not on the CPAP device itself.

This document describes the Curasa CPAP EUT with AutoManager PC Software accessory, a device intended for the treatment of Obstructive Sleep Apnea. The information provided focuses on demonstrating substantial equivalence to a predicate device, rather than providing detailed acceptance criteria and study results for a novel device. As such, many of the requested elements (like sample size for test set, number of experts, adjudication methods, MRMC studies, specific ground truth types for training, effect size with AI) are not directly applicable or available in the provided text, as this is a 510(k) submission primarily focused on demonstrating equivalence through standard compliance and comparative design.

Here's a breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't present a table of specific acceptance criteria with quantitative thresholds for performance metrics. Instead, it lists compliance with various standards and successful completion of design verification tests, all reporting "Pass." The "acceptance criteria" here are implicitly linked to meeting the requirements of these standards and completing the specified tests without failure, thus demonstrating substantial equivalence rather than a novel performance claim.

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

• Sample Size: The document mentions "IFU Validation Testing (patients)", indicating that some patient data was used. However, the specific sample size for this test or any other test set is not provided.
• Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective.

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

This information is not provided in the document. The study described focuses on technical compliance and equivalence.

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

This information is not provided.

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:

• MRMC Study: No MRMC comparative effectiveness study was done or mentioned. This submission does not involve AI for diagnostic purposes or human reader assistance.
• Effect Size of AI Improvement: Not applicable, as this device does not incorporate AI for diagnostic assistance.

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

• Standalone Performance: The "Software Verification Testing" and "AutoManager Software Verification Testing" represent standalone testing of the software components. However, this is for functional verification of the CPAP device and its accessory software, not for an algorithm-only diagnostic or AI performance evaluation. The device itself is "algorithm only" in its automated pressure adjustment, but its primary function is therapeutic, not diagnostic.

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

The document does not explicitly state the type of ground truth used for performance evaluation, as it primarily relies on established engineering and safety standards. For the "IFU Validation Testing (patients)", the ground truth would likely be related to patient comprehension and ability to use the device as intended, potentially assessed through observation or questionnaires, but this is not detailed. For software testing, the ground truth would be the expected functional behavior based on design specifications.

8. The sample size for the training set:

Not applicable, as this device does not involve machine learning or AI models with a distinct "training set" in the context of this submission. The development process would involve iterative testing and refinement, but this is not a traditional AI training set.

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