Search Results

Navigator Applications Suite (Navigator) is a software package that includes Navigator Therapy, Navigator Protocol and Navigator Device. Navigator software is loaded into a medical grade PC physically mounted to the Anesthesia Delivery System and receives data from supported Anesthesia Delivery Systems, Anesthesia Patient Monitors and Intravenous Drug Infusion Pumps.

Navigator Therapy displays pharmacokinetic, pharmacodynamic (PK/PD) and synergistic PD modeling information. Navigator Therapy provides the heath care provider with information about the modeled effect of supported anesthesia pharmaceuticals delivered to the patient.

Models only apply to the following patient populations:

Calculated drug concentrations and effects are based on published models, and do not represent actual measurements from a patient. Drug models are calculated and displayed assuming a healthy patient.

Navigator Protocol allows facilities to load electronic versions of care protocols. This feature can be configured with selected patient monitoring parameters available for viewing in conjunction with the care protocol.

Navigator Device is a troubleshooting aid with access to certain Anesthesia Delivery System alarm information.

The system is designed for facility use and should only be used under the orders of a clinician.

The Navigator Applications Suite is a product that integrates information from an anesthesia delivery system, intravenous drug infusion pumps, and patient monitor. The three main functions of the Navigator are;

• . Navigator Therapy: Visualization of the modeled effect of the anesthesia drugs on the patient, displayed on a point-of-care Navigator computer. The visualization is based on pharmacokinetic and pharmacodynamic (PK/PD) models and multi-drug models for propofol and four analgesic drugs. Navigator also supports automatic data capture from supported intravenous drug infusion pumps to minimize manual data entry.
• Navigator Protocol: Framework to enable access to facility-selected care protocols at the . point of care.
• t Navigator Device: Electronic and interactive instructions for users to address technical issues with anesthesia delivery systems.

The Navigator Applications Suite has been modified to work in a network environment.

This document (K081941) is a 510(k) Premarket Notification for the Navigator Applications Suite, a software package that integrates information from an anesthesia delivery system, intravenous drug infusion pumps, and patient monitor. The notification focuses on modifications to the device to work in a network environment, with no changes to the intended use or fundamental scientific technology. Therefore, the information provided primarily concerns non-clinical testing for safety and compliance with standards, rather than clinical performance or AI-specific validation.

Here's a breakdown of the requested information based on the provided text:

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

The document does not specify quantitative acceptance criteria in terms of clinical performance metrics (e.g., sensitivity, specificity, accuracy) because the submission is for a modification that doesn't alter core functionality or intended use. Instead, the acceptance criteria are implicitly tied to compliance with relevant medical device standards and software validation.

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

The document does not describe a "test set" in the context of clinical data for performance evaluation. The testing described is primarily non-clinical, focusing on software verification and validation, and compliance with standards. Therefore, information on sample size, data provenance, or retrospective/prospective studies is not applicable or provided.

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)

This information is not provided as the submission concerns non-clinical testing and regulatory compliance for a software modification, not a clinical performance study requiring expert ground truth.

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

Not applicable, as no clinical test set requiring adjudication is 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

Not applicable. This submission is for a medical device software that provides information and tools (PK/PD modeling, protocols, troubleshooting) for anesthesia management, not an AI-based diagnostic or assistive tool that would typically involve a multi-reader multi-case study to evaluate human reader improvement. The "AI" aspect here (PK/PD modeling) is based on published models, not machine learning trained on images or diagnostic data.

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

The Navigator Applications Suite, particularly the Navigator Therapy component, contains algorithms (pharmacokinetic and pharmacodynamic models). The document states: "Calculated drug concentrations and effects are based on published models, and do not represent actual measurements from a patient." and "Drug models are calculated and displayed assuming a healthy patient." This indicates that the algorithms operate in a "standalone" computational manner based on pre-defined models. However, the output is "displayed" to a healthcare provider, implying a human-in-the-loop for interpretation and clinical decision-making. The "standalone performance" in this context would refer to the accuracy of the model calculations based on inputs, which is implicitly validated by the software testing and reliance on "published models." Specific metrics for this standalone performance are not provided beyond the general statement of "thoroughly tested through verification of specifications and validation."

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

For the PK/PD models, the "ground truth" is implied to be published pharmacokinetic and pharmacodynamic models. The software's validation would focus on correctly implementing these models and calculations. For the other functionalities (Protocol and Device), the "ground truth" would relate to the correct display of protocols and troubleshooting information, which is validated through software testing against design specifications.

8. The sample size for the training set

Not applicable. The device's "AI" component (PK/PD modeling) is based on published mathematical models, not on a machine learning approach requiring a training set of data.

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

Not applicable, as no training set (in the machine learning sense) is mentioned. The ground truth for the underlying PK/PD models would have been established through extensive prior research, clinical trials, and scientific consensus leading to their publication. The device uses these established models rather than training its own.

Ask a specific question about this device