(73 days)
The INOmax DS delivery system delivers INOmax® (nitric oxide of inhalation) therapy gas into the inspiratory limb of the patient breathing circuit in a way that provides a constant concentration of nitric oxide (NO), as set by the user, to the patient throughout the inspired breath. It uses a specially designed injector module, which enables tracking of the ventilator waveforms and the delivery of a synchronized and proportional dose of NO. It may be used with most ventilators.
The INOmax DS provides continuous integrated monitoring of inspired O2, NO2, and NO, and a comprehensive alarm system.
The INOmax DS incorporates a battery that provides up to 6 hours of uninterrupted NO delivery in the absence of an external power source.
The INOmax DS includes a backup NO delivery capability that provides a fixed flow of 250 mL/min of NO which along with user supplied 10 L/min of oxygen provides 20 ppm in the gas flow to a patients breathing circuit. It may also use the INOblender for backup.
The target patient population is controlled by the drug labeling for INOmax and is currently neonates. The primary targeted clinical setting is the Neonatal Intensive Care Unit (NICU) and secondary targeted clinical setting is the transport of neonates.
The INOmax DS Delivery System provides a constant dose of INOmax (nitric oxide) therapy gas into the inspiratory limb of the ventilator circuit. The INOmax DS Delivery System uses a "dual-channel" design to ensure the safe delivery of INOmax.
The first channel has the delivery CPU, the flow controller and the injector module to ensure the accurate delivery of NO. The second channel is the monitoring system, which includes a separate monitor CPU, the gas cells (NO, NO2 and O2 cells) and the user interface including the display and alarms. The dual-channel approach to delivery and monitoring permits INOmax delivery independent of monitoring but also allows the monitoring system to shutdown INOmax delivery if it detects a fault in the delivery system such that the NO concentration could become greater than 100 ppm. INOmax drug is stored as a gas mixture of NO/N2 in an aluminum cylinder at a nominal pressure of 2200 psig.
The cylinder is attached to a high pressure requlator which incorporates a pressure gauge that indicates cylinder pressure when the cylinder valve is open. The cylinder regulator is attached via tubing to the INOmax DS Delivery System using one of the two NO/NO2 quick connect inlets on the back of the machine.
The INOmax enters the back of the INOmax DS Delivery System, passes through a filter, then a safety shutoff valve, which is open under normal operations.
An injector module is placed in the ventilator gas flow between the ventilator inspiratory outlet and the humidifier. Based on the ventilator flow, the INOmax cylinder concentration and set INOmax dose, the proportional solenoid delivers INOmax into the ventilator circuit via the injector module. This allows the INOmax DS Delivery System to deliver a constant dose of INOmax regardless of the ventilator flow pattern or breath rate.
A flow sensor inside the INOmax DS Delivery Systém also monitors the NO flow out of the machine. A check valve is included prior to the INOmax DS Delivery System drug outlet to prevent pressure effects from the ventilator breathing circuit interfering with the NO flow sensor reading.
The INOmax DS Delivery System gas monitoring system provides monitored values for inspired NO, NO2, and O2 The sample gas is withdrawn from the breathing circuit and goes through a water trap to remove excess water, a zero valve, a sample pump and finally a sample flow sensor to the gas monitoring cells. The zero valve allows the gas cells to be zeroed (during low calibration) without having to disconnect the sample line from the breathing circuit. The pump and sample flow sensor ensure a constant sample gas flow rate is maintained to the monitoring cells.
The gas monitoring cells are electrochemical; they are specific to each gas and provide an electronic signal, which is proportional to the concentration of gas present.
If the delivery system does go into shutdown, the INOmax DS Delivery System has an integrated backup function which provides a fixed flow of INOmax (0.25L/min) into the injector module using a pneumatic on/off switch and a restrictor built into the delivery side of the system. This fixed flow of INOmax will provide 20 ppm of NO when the continuous ventilator gas flow is 10 L/min. The backup is only for short term use until a replacement delivery system can be obtained. An alarm will warn the user if the backup system is turned on while the main delivery system is in use for INOmax delivery.
The provided text describes a medical device, the INOmax DS (Delivery System), and its regulatory submission (K0909258). However, it does not contain the specific details required to complete your request for acceptance criteria and the comprehensive study information.
The document is a 510(k) summary for a medical device (nitric oxide administration apparatus). A 510(k) submission typically focuses on demonstrating substantial equivalence to a predicate device rather than presenting extensive clinical study data with detailed acceptance criteria for diagnostic performance metrics like accuracy, sensitivity, or specificity, as would be common for AI/ML devices.
Here's a breakdown of what can be extracted and what is missing, based on your requested points:
1. Table of Acceptance Criteria and Reported Device Performance
- Acceptance Criteria: The document mentions that "Testing indicated the INOmax DS Delivery System met its design input specifications, design output specifications and risk analysis requirements." (page 4) and that "The INOmax DS Delivery System was designed to comply with the applicable portions of the following product standards" (page 5, listing IEC, ASTM, and FDA guidance documents). There are also specific performance specifications for gas monitoring and NO delivery (pages 1-2).
- Reported Device Performance: The document provides specifications for the INOmax DS in comparison to a predicate device (INOvent Delivery System). These are more akin to design specifications rather than performance results from a clinical study for diagnostic accuracy.
What's Missing for a comprehensive table:
The document does not explicitly state "acceptance criteria" in a pass/fail quantifiable sense for a study evaluating diagnostic performance. It talks about meeting design specifications and complying with standards, which are different. It also does not provide specific numerical results from a study that can be directly compared against acceptance criteria for metrics like sensitivity, specificity, or accuracy, as would be relevant for an AI/ML device.
2. Sample size used for the test set and the data provenance
- Sample Size for Test Set: This information is not provided. The document mentions "Validation of ventilators" as part of testing (page 4), but no details on the number of cases or data points, or how the test set was constituted.
- Data Provenance: This information is not provided. There's no mention of country of origin, or if the data 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. The device is an administration and monitoring system, not one that requires human expert interpretation for ground truth in the way an AI diagnostic tool would.
4. Adjudication method for the test set
- This information is not provided. Not applicable in the context of this device and the type of testing 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
- Such a study was not done and is not applicable. This device is not an AI diagnostic tool that assists human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- This concept is not applicable in the context of this device. The device is a system for delivering and monitoring nitric oxide; its "performance" is about accurate gas delivery, measurement, and alarms, not AI algorithm output.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- "Ground truth" as understood for diagnostic AI/ML devices (e.g., pathology for disease presence) is not applicable here. The "ground truth" for this device's performance would be the actual concentration of gases, flow rates, and system functionality as measured by calibrated instruments and against established engineering specifications and physical principles.
8. The sample size for the training set
- This information is not provided. The document describes a medical device, not an AI/ML algorithm that is "trained" on a dataset in the typical sense.
9. How the ground truth for the training set was established
- This information is not provided. Not applicable as per point 8.
Summary of what the document does provide regarding "testing":
The document states:
- "Testing indicated the INOmax DS Delivery System met its design input specifications, design output specifications and risk analysis requirements." (page 4)
- "Testing completed included: Validation of ventilators." (page 4)
- The device was designed to comply with several product standards (IEC, ASTM, FDA guidance) (page 5).
- It provides a comparison of specifications between the INOmax DS and a predicate device, for features like battery backup duration, physical dimensions, ventilator compatibility, NO delivery resolution/accuracy, and gas monitoring resolution/accuracy (pages 1-2). For example, it lists INOmax DS NO accuracy as "+/- 20% indicated or 2 ppm whichever greater" and NO accuracy for gas monitoring as "+/- 20% of reading +0.5 ppm" (page 1-2). These could be interpreted as performance metrics, but they are stated specifications rather than results from a specific study.
Conclusion:
The provided K0909258 document is a 510(k) summary for a medical device that delivers and monitors Nitric Oxide. It focuses on demonstrating substantial equivalence to predicate devices and adherence to design specifications and relevant standards. It is not a submission for an AI/ML diagnostic or assistive device and therefore does not contain the detailed clinical study data, acceptance criteria for diagnostic metrics, or information about ground truth establishment, expert adjudication, or reader studies that your request asks for. The "testing" mentioned is likely engineering verification and validation testing to ensure the device performs according to its technical specifications and safety requirements, rather than a clinical study establishing diagnostic performance against a ground truth.
§ 868.2375 Breathing frequency monitor.
(a)
Identification. A breathing (ventilatory) frequency monitor is a device intended to measure or monitor a patient's respiratory rate. The device may provide an audible or visible alarm when the respiratory rate, averaged over time, is outside operator settable alarm limits. This device does not include the apnea monitor classified in § 868.2377.(b)
Classification. Class II (performance standards).