(238 days)
NOxBOXi Nitric Oxide Delivery System is intended for use by healthcare professionals for the delivery and monitoring of a constant (user set) concentration of nitric oxide (NO) and the monitoring of NO2 and O2 in the inspiratory ventilator lines of a patient undergoing nitric oxide therapy (iNO).
The NOxBOXi Nitric Oxide Delivery System includes:
- The NOxBOXi head unit, which delivers NO gas while in the intelligent delivery mode.
- Continuous monitoring and alarms for NO, O2, and NO2.
- The integrated NOxMixer which provides a backup NO delivery capability that is intended to deliver a continuous flow of NO, mixed with O₂, for iNO therapy and provides a continuous treatment option during transit and transfer conditions within hospitals.
The NOxBOXi Nitric Oxide Delivery System must only be used in accordance with the indications, contraindications, warnings and precautions described in the nitric oxide drug packaging inserts and labeling (currently neonates). Refer to this material prior to use.
The NOxBOXi Nitric Oxide Delivery System (NOxBOXi) simultaneously delivers Nitric Oxide (NO) medical gas, while monitoring Nitric Oxide, Nitrogen Dioxide (NO2), and Oxygen (O2) levels in the inspiratory limb of a ventilator for patients undergoing inhaled Nitric Oxide Therapy.
The system is designed for use by healthcare professionals to administer treatment to patients undergoing inhaled Nitric Oxide (iNO) therapy. The NOxBOXi will deliver nitric oxide in a synchronous manner to a single patient.
An integrated component to the NOxBOXi, the NOxMixer is intended to deliver a continuous flow of Nitric Oxide from the NOxBOXi, mixed in line with O₂ for use in iNO therapy. The NOxMixer will be used in conjunction with manually bagging a patient.
The NOxBOXi includes the NOxBOXi Head Unit, a NOxFLOW sample line, two NO feed hoses, two regulators (connector type dependent on the gas supplier), a test circuit, NO, O2, and NO2 monitors, power supply, drainage syringe, Operating Manual & Technical Guide.
This submission is for the introduction of new compatible ventilators including the addition of pediatric categories for existing ventilators, an additional optional software mode which disables the "Vent Flow Idle" alarm to reduce this alarm which may not be necessary and is considered a "nuisance" alarm in certain situations. Alarm initiations are still recorded in the log file. Additionally, language choices other than English have been disabled for this mode. There are no changes to the indications for use of the product, patient population of neonates, and there are no significant design changes.
The provided text is a 510(k) summary for the NOxBOXi Nitric Oxide Delivery System, focusing on changes to compatible ventilators and an optional software mode. It does not present a study proving the device meets acceptance criteria in the manner typically associated with AI/ML-enabled devices, which often involve performance metrics like sensitivity, specificity, or AUC against a defined ground truth.
Instead, this document describes a modification to an already cleared medical device (NOxBOXi Nitric Oxide Delivery System). The "study" here refers to non-clinical performance testing to demonstrate that these changes do not alter the substantial equivalence of the modified device to its predicate. The acceptance criteria are therefore related to the safety and performance parameters of the delivery system itself, rather than diagnostic or analytical accuracy of an AI model.
Therefore, many of the requested points related to AI/ML study design (like sample size for test/training sets, expert ground truth establishment, MRMC studies, or standalone performance for an algorithm) are not applicable to this document's content.
However, I can extract information related to the device's technical specifications and the testing performed for this submission.
Here's an interpretation based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are implicitly defined by the existing performance characteristics of the predicate device (K231823) and regulatory standards. The reported "performance" for this submission is that the device, with the new ventilator compatibility and software mode, continues to meet these original performance specifications and does not raise new questions of safety or effectiveness.
| Performance Parameter / Acceptance Criteria | Reported Device Performance (with new changes) |
|---|---|
| NO & NO2 Monitoring Accuracy | +/- 2% or 0.2ppm (No Change) |
| NO Dosing Accuracy (Manual Mode) | +/- 20% or 2 ppm (5-80 ppm NO); +/- 40% or 4 ppm (0-80-185 ppm NO) (No Change) |
| Battery Backup Capability | 4 hours without AC power (No Change) |
| Ventilator Compatibility | Various models from listed manufacturers, including new additions and pediatric categories for existing models. |
| Optional Software Mode Functionality | Disables "Vent Flow Idle" alarm; alarm initiations still recorded. Language choices (other than English) disabled for this mode. |
| Safety and Effectiveness | No new questions of safety or effectiveness raised. Passed all testing. |
| Compliance with Standards/Guidance | Verified and validated to comply with ISO 14971, ISO 10993 (various parts), IEC 60601-1, IEC 60601-1-2, IEC 62366, ISO 80601-2-55, IEC 62304, ISO 15223-1, and relevant FDA guidance documents. |
| VOC & Particulate Matter in delivered gases | VOC levels three orders of magnitude below OSHA permissible exposure levels. Particulate levels well below EPA's maximum limits. |
2. Sample size used for the test set and the data provenance:
- Test Set Description: The "test set" here refers to the specific modifications being evaluated: the compatibility with additional ventilators and an optional software mode.
- Sample Size: Not quantified in terms of a "sample size" of patients or images, as this is a hardware/software modification submission. The testing involves specific ventilator models and configurations, and the software mode itself.
- Data Provenance: Not applicable in the context of clinical data or patient-derived data for an AI/ML model. The testing is non-clinical, likely bench testing, and usability testing.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable in the context of this 510(k) summary. Ground truth as typically understood for AI/ML diagnostic devices (e.g., expert radiological reads) is not established here. The "truth" is based on the engineering specifications and performance of the device under various conditions and its compliance with regulatory standards.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not applicable. This relates to clinical endpoint adjudication, which is not described.
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:
- No. This is not an AI-enabled diagnostic device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- No. This is a medical device for gas delivery and monitoring, not a standalone algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The "ground truth" for this device's performance, as demonstrated in this submission, is based on:
- Engineering specifications and design requirements.
- Validated test methods conforming to international standards (e.g., ISO, IEC).
- Compliance with FDA guidance documents related to nitric oxide delivery apparatus and software.
- Bench testing results for parameters like accuracy, flow rates, alarm functionality, and gas purity.
8. The sample size for the training set:
- Not applicable. This document does not describe an AI/ML model with a training set.
9. How the ground truth for the training set was established:
- Not applicable. This document does not describe an AI/ML model with a training set.
Summary of the study conducted:
The "study" or testing performed for this 510(k) submission was non-clinical performance testing and usability testing. The purpose was to demonstrate that adding compatibility with new ventilators (including pediatric categories for existing ones) and an optional software mode does not adversely impact the safety or effectiveness of the NOxBOXi Nitric Oxide Delivery System, and that it remains substantially equivalent to its predicate device (K231823). The testing focused on validating that the changes did not introduce new safety concerns or alter the specified performance characteristics of the device. This involved testing against international standards and FDA guidance relevant to medical devices, particularly those for nitric oxide delivery systems. No clinical testing was required for this specific submission given the nature of the changes.
§ 868.5165 Nitric oxide administration apparatus.
(a)
Identification. The nitric oxide administration apparatus is a device used to add nitric oxide to gases that are to be breathed by a patient. The nitric oxide administration apparatus is to be used in conjunction with a ventilator or other breathing gas administration system.(b)
Classification. Class II. The special control for this device is FDA's “Guidance Document for Premarket Notification Submissions for Nitric Oxide Administration Apparatus, Nitric Oxide Analyzer, and Nitrogen Dioxide Analyzer.”