K Number
K990068
Date Cleared
1999-07-14

(187 days)

Product Code
Regulation Number
870.1025
Panel
CV
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Solar@ 9500 Information Monitoring System is intended for use under the direct supervision of a licensed healthcare practitioner. The Intended use of the system is to monitor physiologic parameter data on adult, pediatric and neonatal patients, in high acuity areas such as operating room (OR), post anesthesia recovery (PARR), critical care, surgical intensive care, respiratory intensive care, coronary care, medical intensive care, pediatric intensive care, or neonatal intensive care. Physiologic data includes electrocardiogram, invasive blood pressure, noninvasive blood pressure, pulse, temperature, cardiac output, respiration, pulse oximetry, carbon dioxide, oxygen, anesthetic gas concentrations and mixed venous oxygen saturation, as summarized in the Solar® 9500 Operator's Manual. The monitoring parameters are contained in Appendix B under Technical Specifications.

The Solar® 9500 Information Monitoring System is also intended to provide physiologic data over the Unity network to clinical information systems and allow the user to access hospital INTRAnet data via a Web Browser at the point-of-care.

Device Description

The Solar 9500 is a patient monitoring system that is designed to display patient physiological data that is received from the GE Marquette Medical Systems' Tram-net network and individual and multiparameter data acquisition modules.

The Solar 9500 Information Monitoring System is comprised of four basic components: the processing unit, color display, Tram modules(s), and Tram-rac housing. Optional components include a remote display.

The Solar 9500 utilizes the GE Marquette's Unity Ethernet LAN allowing communication with monitoring, clinical information and cardiology products. An additional Ethernet connection is provided for connection to the hospital Enterprise Network. The Enterprise network connection allows the user access to the hospital INTRAnet, through an embedded Web Browser on the Solar 9500. This web browsing capabliity enables the user to log on to the hospital INTRAnet directly from the monitor allowing access to information such as patient history, up-to-the-minute lab results and cath reports. Data can also be accessed from non-Marquette platforms via the Enterprise network.

AI/ML Overview

The provided 510(k) summary for the Solar 9500 Information Monitor is a premarket notification for a patient monitoring system. It declares substantial equivalence to predicate devices but does not include a detailed study proving the device meets specific acceptance criteria in the manner requested (e.g., a clinical validation study with specific performance metrics like sensitivity, specificity, or accuracy. It's a physiological monitor, not an AI/CADe device).

Therefore, I cannot fulfill the request to provide a table of acceptance criteria, reported device performance metrics like sensitivity/specificity, or details about ground truth establishment, expert adjudication, or MRMC studies, as these types of studies are not described in the provided document.

Here's an explanation of what the document does describe in relation to device performance and safety:

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

  • Not provided in this document. This 510(k) summary focuses on demonstrating substantial equivalence to predicate devices rather than reporting specific performance metrics against pre-defined acceptance criteria for diagnostic accuracy (common in AI/CADe devices). The device monitors physiological parameters, and its performance is typically assessed through validation of its ability to accurately measure and display these parameters, not through traditional diagnostic performance metrics like sensitivity or specificity.
  • The document states, "The Solar 9500 complies with the voluntary standards as detailed in Section 9 of this submission." However, Section 9 (which would list these standards and likely contain the detailed test results and acceptance criteria) is not included in the provided text.

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

  • Not provided in this document. The summary does not describe any specific clinical test set, patient data, sample sizes, or data provenance. The "Test Summary" refers to internal quality assurance measures (requirements review, code inspections, software/hardware testing, safety testing, environmental testing, final validation) rather than a clinical trial or performance study involving a specific patient dataset.

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/Not provided. Since there's no described clinical test set requiring ground truth establishment (as would be for an AI/CADe device interpreting images or other complex data), information about experts and their qualifications is not present.

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

  • Not applicable/Not provided. No adjudication method is mentioned as there is no test set described for performance evaluation based on expert interpretation.

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 MRMC study was done or mentioned. This device is a patient physiological monitor, not an AI-assisted diagnostic tool for human readers. Therefore, an MRMC study and effects on human readers are not relevant in this context and are not discussed.

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

  • Not applicable/Not provided in the context of diagnostic algorithms. This device is a standalone monitor. Its "performance" refers to its accuracy in measuring physiological parameters, not to its performance as a diagnostic algorithm to be compared with human interpretation of its output in a standalone vs. human-in-the-loop manner. The "Test Summary" describes various internal validation tests that relate to the device's standalone functional integrity and safety.

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

  • Not applicable/Not provided for diagnostic ground truth. For a physiological monitor, accuracy is typically validated against known reference standards (e.g., a precise gas analyzer for CO2 measurement, an invasive pressure catheter for blood pressure, or a calibrated temperature probe for temperature). The document does not specify the ground truth methods used for validating the accuracy of each physiological parameter.

8. The sample size for the training set:

  • Not applicable/Not provided. This document describes a patient monitoring system, which typically does not involve machine learning models with "training sets" in the same way an AI/CADe device would. The software development included "Requirements specification review," "Code inspections," "Software and hardware testing," "Safety testing," "Environmental testing," and "Final validation." These are traditional software and hardware engineering validation steps, not machine learning model training.

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

  • Not applicable/Not provided. As there is no described training set for a machine learning model, the establishment of its ground truth is not discussed.

In summary, the provided 510(k) summary for the Solar 9500 Information Monitor is a regulatory filing focused on demonstrating "substantial equivalence" of a general patient monitoring system to previously cleared predicate devices. It relies on internal quality assurance, safety testing, and compliance with voluntary standards, rather than detailing clinical studies with specific performance metrics, test sets, or ground truth establishment typically found in submissions for AI/CADe devices. This type of submission is common for non-AI medical devices where equivalence in design, materials, and intended use is the primary pathway to market clearance.

§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).

(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.