Search Results

The INOmax® DSIR Plus delivery system delivers INOMAX® (nitric oxide for 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® DSIR Plus provides continuous integrated monitoring of inspired O2, NO2, and NO, and a comprehensive alarm system.

The INOmax® DSIR Plus incorporates a battery that provides up to 6 hours of uninterrupted NO delivery in the absence of an external power source.

The INOmax® DSIR Plus includes a backup NO delivery capability that provides a fixed flow of NO which along with user supplied 10 L/min of oxygen provides 20 ppm in the gas flow to a patients breath. 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 DSR® Plus 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.

The INOmax® DSIR Plus delivery system delivers INOMAX® (nitric oxide for 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® DSIS Plus provides continuous integrated monitoring of inspired O2, NO2, and NO, and a comprehensive alarm system.

The INOmax® DSIR Plus incorporates a battery that provides up to 6 hours of uninterrupted NO delivery in the absence of an external power source.

The INOmax® DSIR Plus 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.

All revisions of INOmax DSm® Plus utilize component technology to deliver Nitric Oxide gas to the patient. The components consist of the Delivery System unit, the blender, a stand/cart and the NO gas tanks. In this revision of the INOmax DSm® Plus, the only changes to the device includes the labeling for compatibility with respiratory care device.

This document, K200389, is a 510(k) premarket notification for the INOmax DSIR Plus, a nitric oxide administration apparatus. It focuses on demonstrating substantial equivalence to a predicate device (K131686), specifically by adding compatibility with new ventilator and breathing devices.

Based on the provided text, the device performance assessment relies entirely on nonclinical (bench) testing and comparison to a previously cleared predicate device. There is no evidence of clinical studies involving human subjects or AI algorithms in this document. Therefore, many of the requested points regarding AI/MRMC studies, expert ground truth adjudication, and training/test set sample sizes are not applicable to the information presented.

Here's the breakdown of what can be extracted from the document:

1. A table of acceptance criteria and the reported device performance

The document does not provide a specific table of acceptance criteria with corresponding performance metrics like "accuracy > X%". Instead, it refers to a "Ventilator/Gas Delivery System Validation Test Protocol" used for the predicate device (K131686) and states that this same protocol, with "insignificant differences," was used for the INOmax DSIR Plus. The general acceptance criterion implied is that the device "performs within published specifications" and that "the hazards were mitigated" based on this protocol.

• Acceptance Criteria (Implied): Performance according to "published specifications" and mitigation of identified hazards, as demonstrated through the "Ventilator/Gas Delivery System Validation Test Protocol."
• Reported Device Performance: "Ultimately, the requirements necessary for the operation of the INOmax DSIR passed." and "This Bench Testing was conducted across all platforms to demonstrate that the INOmax DSIR® Plus performs within published specifications."

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: Not explicitly stated as a number of patient cases or images. The "test set" in this context refers to the bench testing conducted on the device's compatibility with a list of new ventilator and breathing devices. The document lists 11 specific additional ventilator devices that were tested for compatibility:
  • Covidien PB 980 (K131252)
  • GE Healthcare Carescape R860 (K142679)
  • Fisher & Paykel Healthcare RT330 Breathing Circuit and Optiflow Jr (Class I, 510(k) Exempt under 21 CFR 868.5340)
  • Bunnell Inc Life Pulse 204 (P850064)
  • Drager Perseus A500 (K133886)
  • Fisher & Paykel Healthcare Airvo 2 (K131895)
  • Drager Carina (K072885)
  • Maquet Servo u/n (K151814)
  • Hamilton C3 (K161450)
  • IMT Medical Bellavista (K163127)
  • Maquet Flow-i (K160665)
  • Bio-Med TV-100 (K173973)
  • Phillips V60 (K102985)
• Data Provenance: The data originates from bench testing (laboratory) rather than clinical patient data. Country of origin for the testing is not specified but is presumed to be associated with the manufacturer (Mallinckrodt Manufacturing, LLC, based in Madison, Wisconsin, USA). The testing is prospective in the sense of being conducted specifically for this submission, although it leverages a protocol from a previous clearance.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

Not applicable. This device is a hardware apparatus for administering nitric oxide, not an AI algorithm requiring expert human interpretation of medical images or data for ground truth. The "ground truth" for the nonclinical testing would be the engineering specifications and expected performance, verified through the validation protocol.

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

Not applicable, as no human expert adjudication of data (like medical images or clinical outcomes) was performed. The "adjudication" of the bench test results would be whether the device passed or failed the predefined engineering/performance criteria in the validation protocol.

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 document explicitly states, "The subject of this premarket submission... did not require clinical studies to support substantial equivalence." This means no human-in-the-loop performance study, MRMC study, or AI assistance was involved.

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

No. This device is a physical medical device, not an AI algorithm.

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

The "ground truth" used for this device's validation was engineering specifications and performance criteria established in the "Ventilator/Gas Delivery System Validation Test Protocol," likely determined by design requirements and regulatory standards for medical devices of this type.

8. The sample size for the training set

Not applicable. There is no AI component or training set mentioned in this submission.

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

Not applicable. There is no AI component or training set mentioned in this submission.

Ask a specific question about this device

The INOmax DSIR® Plus MRI delivery system is indicated for delivery of INOMAX® (nitric oxide for inhalation) therapy gas into the inspiratory limb of the patient breathing circuit in a way that provides a constant on of nitric oxide (NO), as set by the user, to the patient throughout the inspired breath. The INOmax DSIR® Plus MRI is indicated for use only with MR Conditional ventilators validated to be compatible, as identified in the device labeling.

The INOmax DSIR® Plus MRI is indicated for continuous integrated monitoring of inspired 02, NO2, and NO.

The INOmax DSIR® Plus MRI is considered MR Conditional with the use of 1.5 Tesla static magnetic field scanners ONLY in areas where the field strength is less than 100 gauss.

The target patient population is controlled by the drug labeling for INOMAX® and is currently neonates. The primary targeted clinical setting is a clinical 1.5 Tesla and 3.0 Tesla diagnostic imaging environment.

The INOmax DSIR® uses a "dual-channel" design to provide 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 specially designed injector module enables tracking of the ventilator waveforms and the delivery of a synchronized and proportional dose 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 a comprehensive alarm system. The dual-channel approach to delivery and monitoring permits INOMAX® delivery independent of monitoring but also allows the monitoring system to shut down INOMAX® delivery if the monitored NO concentration exceeds 100 ppm for 12 consecutive seconds. The delivery system can also shut down delivery if it detects certain serious problems with the monitoring system.

The INOmax DSIR Plus MRI incorporates a battery that provides up to 6 hours of uninterrupted NO delivery in the absence of an external power source.

The INOmax DSIR Plus MRI 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 of NO to a patient breathing circuit. The INOblender® can also be used for backup.

The provided document is a 510(k) summary for the INOmax DSIR® Plus MRI, a nitric oxide administration apparatus. It outlines the device description, intended use, technological characteristics, and a comparison to a predicate device, as well as a summary of nonclinical tests performed.

However, the document does not contain the specific information requested about acceptance criteria and a study proving the device meets those criteria in the context of typical AI/ML medical device submission requirements.

Here's why and what information can be extracted or deduced:

This document describes a hardware medical device, not an AI/ML powered software or diagnostic device. Therefore, the concepts of "acceptance criteria" and "device performance" as typically discussed for AI/ML models (e.g., sensitivity, specificity, AUC) are not directly applicable in the same way. The "performance" here refers to the device's functional operation meeting engineering specifications.

Let's address each point based on the available information:

1. A table of acceptance criteria and the reported device performance

• Acceptance Criteria (Deduced from testing goals): The document implies acceptance criteria are related to the device's functional performance:

  • O2 dilution: The device should not unacceptably dilute oxygen concentration.
  • Effect on delivered pressures: The device should not adversely affect ventilator delivered pressures.
  • INOmax DSIR® delivery accuracy: The device should accurately deliver Nitric Oxide.
  • NO2 generation: The device should not generate unacceptable levels of Nitrogen Dioxide.
  • MRI Compatibility: Device classified as MR Conditional for 1.5 Tesla and 3.0 Tesla static magnetic field scanners in areas where field strength is less than 100 gauss (via ASTM standards and other tests).
  • Electrical Safety & EMC: Conformity to IEC 60601-1 and IEC 60601-1-2.
  • Alarm Systems: Conformity to IEC 60601-1-8.
  • Software Functionality: Software version 3.1.2 meets specified requirements.
  • Usability: Meets human factors engineering requirements (ANSI/AAMI HE75).
  • Backup delivery: Provides fixed flow of 250 mL/min of NO.

• Reported Device Performance:

  • "The INOmax DSIR® performed within published specifications when used with each of the ventilators in both primary and backup delivery."
  • "The INOmax DSIR® Plus MRI meets its system level requirements and that the new/modified features function as specified."
  • Compliance with specific FDA recognized consensus standards (IEC 60601-1, IEC 60601-1-2, IEC 60601-1-8, ASTM F2052-06, ASTM F2119-07, ASTM F2503-13).

Table of (Deduced) Acceptance Criteria and Performance:

Regarding AI/ML specific questions (2-9), the following applies since this is not an AI/ML device:

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not applicable as this is a hardware device. Testing involved physical device performance and compatibility with other medical equipment, not analysis of a data set. The document mentions "Five INOmax DSIR® settings were used [0 (baseline), 5. 10. 20. 40. and 80 ppm] for each mode of ventilation, as well as the Backup mode." This describes test parameters, not a patient sample size or data provenance.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable. Ground truth for a hardware device's functional performance is established through engineering and medical device standards (e.g., accuracy of gas delivery, safety limits). Not expert interpretation of data.

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

• Not applicable. This concept pertains to resolving discrepancies in expert labeling or diagnoses for AI/ML ground truth.

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 device intended to interpret data for human readers.

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

• Not applicable. This is a standalone medical device, but not in the context of an algorithm's performance.

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

• For a hardware device, "ground truth" relates to its adherence to established engineering specifications, safety standards, and functional requirements. For example, the ground truth for "NO delivery accuracy" would be calibration standards and expected physical/chemical properties.

8. The sample size for the training set

• Not applicable. This device does not have a "training set" in the context of AI/ML.

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

• Not applicable. This device does not have a "training set" for AI/ML.

Ask a specific question about this device