(347 days)
The Inspiration ™ Ventilator System with Smart Positive Airway Pressure (SPAP) and Volume Targeted Ventilation (VTV) options is indicated for use with a wide range of patients from infant through adult, requiring respiratory support for a wide range of clinical conditions in hospital, hospital-type facilities and intra-hospital transport.
The Inspiration™ Ventilator System with Smart Positive Airway Pressure (SPAP) and Volume Targeted Ventilation (VTV) options provides continuous ventilation to patients requiring respiratory support by means of pressure-based and volume-based mandatory and spontaneous breaths. The device is identical to the cleared device, the Inspiration™ Ventilator System, with the addition of two new software options: 1) The Smart Positive Airway Pressure (SPAP) modification provides the Inspiration™ Ventilator System with a biphasic pressure mode that allows for spontaneous breathing at two separate PEEP baselines. 2) The Volume Targeted Ventilation (VTV) modification provides the Inspiration™ Ventilator System with a pressure based breath mode that targets tidal volume by adjusting the delivered pressure targets on a breath-to-breath basis. This modification includes Pressure Regulated Volume Control (PRVC) and Volume Support (VS). This option also includes Automode which allows patients the backup safety support of mandatory breaths if they stop breathing and transition back to their spontaneous mode when they are again breathing spontaneously. These modifications are implemented on the Inspiration™ Ventilator through additional functionality in software only. The existing modalities, pneumatic design, breath delivery control algorithms, electrical circuitry and user interface have remained unchanged from the cleared Inspiration™ ventilator device.
The provided text describes a 510(k) premarket notification for the eVent Medical Ltd. Inspiration™ Ventilator System with Smart Positive Airway Pressure (SPAP) and Volume Targeted Ventilation (VTV) options. This submission focuses on demonstrating substantial equivalence to predicate devices rather than directly presenting acceptance criteria and a detailed study outcome to prove achievement of those criteria in the format typically used for AI/ML device evaluations.
Therefore, many of the requested elements (like sample sizes for test/training sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance metrics, and detailed ground truth establishment for training) are not explicitly present in the provided document, as it predates the common structured evaluation reporting for these types of technologies.
However, based on the information available, here's a breakdown of what can be extracted:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not provide a formal table of quantitative acceptance criteria with specific performance metrics (e.g., accuracy, sensitivity, specificity, or error rates) and corresponding device performance values. Instead, it relies on demonstrating substantial equivalence to existing, legally marketed predicate devices.
The "acceptance criteria" are implied to be that the new software modifications (SPAP and VTV) function similarly to the predicate devices' equivalent modes without introducing new questions of safety or effectiveness. The "reported device performance" is the conclusion that:
- The SPAP feature is "substantially equivalent to the BiVent mode on the Siemens Servoi ventilator (K022132)."
- The VTV modification (including PRVC and VS) is "substantially equivalent to PRVC and VS and on the Siemens Servoi Ventilator (K022132)."
- The Automode feature is "substantially equivalent to Automode on the Siemens Servoi Ventilator (K022132)."
- Overall, the device "meets its specifications and is safe and effective for its intended use."
This is a qualitative assessment of equivalence, not a quantitative performance measurement against predefined thresholds.
2. Sample Size Used for the Test Set and Data Provenance
Not explicitly stated. The document refers to "verification and validation testing" and "combined testing and analysis of results," but no specific sample sizes for a "test set" (in the context of AI/ML evaluation) are provided. The testing would have been conducted on the device itself, likely involving various simulated patient conditions and scenarios to verify correct functionality of the new software modes.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
Not applicable in the context of this submission. The "ground truth" here is the expected mechanical and physiological response of the ventilator under various settings and patient conditions, and its equivalence to the predicate devices. This would typically be assessed by engineers, respiratory therapists, and physicians through functional testing, not by a panel of experts establishing a consensus ground truth for image interpretation or diagnosis as seen in AI/ML studies.
4. Adjudication Method for the Test Set
Not applicable. There's no mention of an adjudication method, as the evaluation is not based on expert review of ambiguous cases.
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 clinical decision support device. It is a continuous ventilator with new software-driven ventilation modes. An MRMC study is not relevant to its evaluation.
6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done
The device itself is a standalone system with new software algorithms for ventilation control. Its performance was evaluated as such. There is no "human-in-the-loop" component in the sense of an AI assisting a human in a diagnostic task; the human (clinician) operates the device, and the device's algorithms control ventilation. The entire testing would, by definition, be "standalone" performance of the machine.
7. The Type of Ground Truth Used
The ground truth used for evaluating the ventilator's performance would be:
- Engineering specifications and expected physiological responses: The modes (SPAP, VTV) should control pressure and volume as designed and as observed in the predicate devices. This involves mechanical testing, simulations, and possibly animal or human subject testing (though not detailed here) to confirm that the delivered ventilation parameters (e.g., tidal volume, pressure) match the set parameters and physiological models within acceptable tolerances.
- Predicate device behavior: The "ground truth" for substantial equivalence is the established safe and effective performance of the predicate ventilators (Siemens - Elma AB. Servoi Ventilator with BiVent, K022132). The new device's modes are compared to the predicate's modes to ensure similar function.
8. The Sample Size for the Training Set
Not applicable. As a traditional medical device (ventilator) with software modifications, there is no "training set" in the context of machine learning. The software was developed and validated, but not "trained" on a dataset like an AI algorithm would be.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no training set in the AI/ML sense. The "ground truth" for the software development would be the engineering requirements, clinical specifications, and intended functionality derived from established medical knowledge and predicate device capabilities.
§ 868.5895 Continuous ventilator.
(a)
Identification. A continuous ventilator (respirator) is a device intended to mechanically control or assist patient breathing by delivering a predetermined percentage of oxygen in the breathing gas. Adult, pediatric, and neonatal ventilators are included in this generic type of device.(b)
Classification. Class II (performance standards).