(210 days)
The Vigileo APCO/Oximetry Monitor is indicated for continuously measuring hemodynamic parameters such as cardiac output and oximetry to assess oxygen delivery and consumption. When connected to an Edwards oximetry catheter, the monitor measures oximetry in adults and pediatrics. The monitor also displays parameters, such as stroke volume and stroke volume variation, used to assess fluid status and vascular resistance. The Vigileo APCO/Oximetry Monitor may be used in all setting in which critical care is provided.
The Vigileo Arterial Pressure Cardiac Output (APCO)/Oximetry Monitor (Vigileo Monitor) is a microprocessor-based instrument. When used with the FloTrac sensor, the Vigileo Monitor continuously measures key parameters of arterial pressure cardiac output (CO), cardiac index (CI), oxygen delivery (DO2), oxygen delivery index (DO2I), stroke volume (SV), stroke volume variation (SVV), stroke volume index (SVI), systemic vascular resistance (SVR) and systemic vascular resistance index (SVRI). When used with Edwards oximetry catheters, the Vigileo Monitor measures central venous oxygen saturation (ScvO2) and mixed venous oxygen saturation (SvO2). The instrument software has been revised to enhance the SVV algorithm, improve the GUI and add compatibility with additional external devices for data output.
The provided text describes the Vigileo Arterial Pressure Cardiac Output (APCO)/Oximetry Monitor. This submission is a 510(k) for a revised version of an existing device, focusing on software enhancements rather than a new clinical application. As such, the study described is a comparison to a predicate device, aiming to demonstrate substantial equivalence, rather than a clinical trial establishing effectiveness against acceptance criteria in the way a novel device might.
Here's an analysis of the available information:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not explicitly state formal "acceptance criteria" in terms of specific performance metrics (e.g., accuracy, sensitivity, specificity, or error bounds for CO/SVV measurements) that the device must meet against a predefined gold standard. Instead, the focus is on substantial equivalence to a predicate device (K082308, an earlier version of the Vigileo Arterial Pressure Cardiac Output/Oximetry Monitor).
The reported device performance is described in a qualitative manner:
| Performance Aspect | Reported Performance |
|---|---|
| Comparative Analysis (Clinical Data) | "Verification and validation testing was conducted to compare the performance and functionality of the pending and the predicate devices. This testing regimen included side-by-side bench and pre-clinical studies, and comparative analysis of clinical data. The Vigileo Monitor has been shown to be safe and effective and substantially equivalent to the cited predicate device for its intended use in the OR and ICU environments." |
| Functional/Safety Testing (Software, Mech, Elec, Bench, Pre-clinical) | "The Vigileo Monitor has successfully undergone functional and performance testing, including software verification and validation, mechanical and electrical testing, bench studies, pre-clinical animal studies, comparison testing of clinical cases, and clinical usability. The Vigileo Monitor has been shown to be safe and effective and substantially equivalent to the cited predicate devices for their intended use in the OR and ICU environments." |
2. Sample Size Used for the Test Set and Data Provenance:
The document mentions "comparison testing of clinical cases" and "comparative analysis of clinical data" but does not provide specific numbers for the sample size (e.g., number of patients, number of data points) used in these clinical comparisons.
The data provenance (country of origin, retrospective/prospective) is not specified.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
This information is not provided. Given that the study is a comparison to a predicate device for substantial equivalence with minor software revisions, it's unlikely that independent experts were used to establish a new "ground truth" for the test set in the same way one might for a diagnostic imaging AI with unknown pathology. The "ground truth" for comparison would likely be the measurements obtained from the predicate device itself, or potentially highly accurate invasive measurements (e.g., thermodilution cardiac output) if those were used to validate both the predicate and the revised device in parallel. The document does not specify this.
4. Adjudication Method for the Test Set:
This information is not provided. As above, for a device modification showing substantial equivalence to a predicate, a complex adjudication process by multiple human annotators is less likely to be applicable.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:
No, an MRMC comparative effectiveness study was not done. The device itself is a monitor for physiological parameters, not a diagnostic imaging aid that human readers interpret. Therefore, the concept of "human readers improving with AI vs. without AI assistance" does not apply to this device. The "AI" here refers to algorithms for calculating hemodynamic parameters, not an assistance tool for human interpretation.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Yes, the primary evaluation described is a standalone performance assessment. The Vigileo Monitor, with its enhanced SVV algorithm, directly generates numerical outputs for various hemodynamic parameters. The testing involved comparing these outputs from the revised device against those from the predicate device (and potentially against a gold standard method if available, though not explicitly stated as such for this submission). There is no "human-in-the-loop" aspect to the output generation from the device itself.
7. The Type of Ground Truth Used:
The document implies that the ground truth for comparison was the measurements obtained from the predicate device (K082308). It states "comparative analysis of clinical data" between the "pending and the predicate devices." While it's possible that a more invasive, established gold standard (like thermodilution for cardiac output) was also used in the original validation of the predicate device, it's not explicitly stated as the ground truth for this particular submission's comparison. The software enhancements were validated against the behavior of the previous software version.
8. The Sample Size for the Training Set:
This information is not provided. The document makes no mention of a "training set" in the context of machine learning, which is a modern concept for AI. The "SVV algorithm enhancement" is more likely a traditional algorithmic improvement rather than a deep learning model trained on a large dataset. Therefore, the concept of a "training set" as understood in current AI contexts is unlikely to apply directly here.
9. How the Ground Truth for the Training Set was Established:
As per point 8, the concept of a "training set" for a machine learning model is not explicitly mentioned or implied. If the SVV algorithm was "enhanced," it would likely have been refined based on established physiological principles and potentially validated against existing physiological data or expert consensus on wave-form analysis, rather than through a machine learning training process with a distinct ground truth dataset. The document doesn’t provide details on the specific method of algorithm enhancement or its associated ground truth establishment.
§ 870.1435 Single-function, preprogrammed diagnostic computer.
(a)
Identification. A single-function, preprogrammed diagnostic computer is a hard-wired computer that calculates a specific physiological or blood-flow parameter based on information obtained from one or more electrodes, transducers, or measuring devices.(b)
Classification. Class II (performance standards).