Search Results

The Z1 CPAP System is a single patient reusable device that provides continuous positive airway pressure (CPAP) to support treatment of adults weighing over 66 lbs (30 kg) with obstructive sleep apnea.

The Z1 CPAP System provides continuous positive pressure to support the treatment of adults over 66 lbs (30 kg) with obstructive sleep apnea. The device is a non-critical care, reusable, single patient device for use in the home setting, and it is intended to be a prescription use only device. The Z1 CPAP System is a modified version of the Z1 Blower cleared in K121374. The modifications include: addition of an optional battery, addition of an APAP mode, addition of Bluetooth and a mobile app, addition of new user settings, and changes to firmware.

The provided document describes the Z1 CPAP System and its substantial equivalence to predicate devices, focusing on performance testing rather than clinical studies with human subjects. Therefore, some of the requested information, such as sample sizes for test and training sets, number of experts for ground truth, adjudication methods, or MRMC studies, are not applicable in this context.

Here's an analysis based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the Z1 CPAP System are primarily based on equivalence to predicate devices and adherence to established performance standards.

Study Proving Device Meets Acceptance Criteria:

The device's acceptance is primarily based on bench performance testing comparing the Z1 CPAP System to predicate devices, particularly the iSleep20i (K063476) for the APAP mode, and demonstrating compliance with relevant national and international performance and safety standards. No clinical data was generated to support substantial equivalence.

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

• Sample Size for Test Set: Not explicitly stated as a numerical patient or case count. The testing involved "pneumatic air flow signals from a test lung" comprising a "clinically diverse data set of respiratory patterns, breathing rates, pressure settings, recovery to normal breathing and non-recovery patterns, etc." It also included "digitized flow samples" which formed another "clinically diverse data set."
• Data Provenance: The data used for testing was generated from a "test lung" and "digitized flow samples." This indicates the data is synthetic/simulated rather than originating from human patients in a specific country. It is retrospective in the sense that predetermined test cases were applied to the devices, rather than ongoing data collection from patients.

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

• Number of Experts: Not applicable. The ground truth for this bench testing was established by the engineering specifications and expected outputs of the predicate device (iSleep20i). The comparison was directly against the known, cleared performance of the predicate device, not against expert medical interpretations of patient data.
• Qualifications of Experts: N/A as it's not an expert-driven ground truth.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable. The comparison was an objective, quantitative one between the output of the Z1 CPAP System and the predicate iSleep20i system, as well as against pre-defined engineering limits and standards. An "exact match" was an acceptance criterion for apnea-hypopnea event detection.

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, an MRMC comparative effectiveness study was not done. The device is a CPAP system, not an AI-assisted diagnostic tool that involves human readers interpreting results.

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

• Standalone Performance: Yes, the testing described appears to be a standalone (algorithm only) performance evaluation. The Z1 CPAP System's performance, particularly its APAP software, was compared directly against the iSleep20i's performance using identical input signals, without human intervention in the loop of the device's operational response.

7. The type of ground truth used:

• Type of Ground Truth: The ground truth for the APAP software equivalence testing was the known, cleared performance and output of the predicate device (iSleep20i), particularly its pressure adjustment outputs and apnea-hypopnea event detections. For other performance aspects (e.g., temperature, noise, flow rate), the ground truth was based on established engineering specifications, regulatory limits, and compliance with recognized standards.

8. The Sample Size for the Training Set:

• Sample Size for Training Set: Not applicable. The document states that the Z1 CPAP System's APAP software is identical to the cleared iSleep20i software (from K063476). This means the Z1 did not involve a separate training process for its APAP algorithm itself, but rather acquired and ported existing, already-trained (or developed) software.

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

• How Ground Truth for Training Set was Established: Not applicable, as the APAP software was acquired from a previously cleared device. The document states, "Human Design Medical ported the iSleep20i APAP software into the Z1 CPAP System without modification." Therefore, the training for the original iSleep20i software would have established its ground truth, but this information is not part of the current submission.

Ask a specific question about this device