K Number
K122146
Date Cleared
2013-04-22

(277 days)

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

The Spacelabs Healthcare Xhibit Central Station, Model 96102 intended use is to provide clinicians with central monitoring of adult, pediatric and neonatal patient data of patients connected to networked Spacelabs Healthcare patient monitors and telemetry transmitters. Data includes physiological waveforms and calculations, cardiac arrhythmia and ST data, and patient demographic information to monitor adequacy of treatment or to exclude causes of symptoms. The Spacelabs Healthcare Xhibit Central Station, Model 96102 is a prescription device intended for use under the direct supervision of a licensed healthcare professional.

Device Description

The Spacelabs Healthcare (Spacelabs) Xhibit Central Station, Model 96102 (Xhibit), is a new version of currently marketed Spacelabs product. Xhibit offers remote surveillance of patient data for those patients connected to a Spacelabs Healthcare Ultraview, Ultraview SL bedside monitor, or telemetry system. Xhibit provides for data communication using the TCP/IP network protocol employed in the Spacelabs Patient Care Management network of hardwired and/or telemetry monitored patients. Xhibit is not the primary alarming device for the Ultraview or Ultraview SL telemetry system.

AI/ML Overview

The provided 510(k) summary (K122146) details the Spacelabs Healthcare Xhibit Central Station, Model 96102. The document describes various performance tests conducted to establish its safety and effectiveness.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based solely on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly present a table of quantitative acceptance criteria with corresponding performance metrics for the device's clinical efficacy (e.g., arrhythmia detection accuracy). Instead, the performance testing focuses on compliance with established standards and internal requirements.

Test TypeAcceptance Criteria (Implied)Reported Device Performance
Software TestingCompliance with regulatory guidance and IEC 62304:2006"Test results indicate that the Xhibit complies with its predetermined specifications and the applicable standards and guidance documents."
Electromagnetic Compatibility TestingCompliance with IEC 60601-1-2:2007"Test results indicated that Xhibit complies with the Standard."
Performance TestingCompliance with IEC 60601-1-8:2006 and IEC 62366:2007, and internal requirements"Test results indicate that Xhibit complies with its predetermined specifications and the applicable standards."

2. Sample size used for the test set and the data provenance

The document does not provide information regarding a specific "test set" in the context of clinical performance data, such as a dataset of patient physiological waveforms for evaluating alarm accuracy or arrhythmia detection. The testing described is primarily focused on engineering and software validation. Therefore, there is no information on sample size or data provenance (country of origin, retrospective/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. Since there's no mention of a clinical test set requiring expert ground truthing, this detail is absent.

4. Adjudication method for the test set

This information is not provided. As no clinical test set requiring ground truth is mentioned, an adjudication method is not applicable in the documented testing.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not described or referenced in the provided text.

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

The device is a "Central Station Remote Monitor" that displays physiological data and alarms. Its function is to facilitate human monitoring, not to operate as a standalone diagnostic algorithm. Therefore, a standalone algorithmic performance study, as typically understood for AI-based diagnostic devices, was not reported. The performance testing focuses on the system's compliance with safety and operational standards.

7. The type of ground truth used

For the engineering and software testing described, the "ground truth" would be the specifications and requirements defined by the manufacturer and the relevant national and international standards (e.g., IEC 62304, IEC 60601-1-2, IEC 60601-1-8, IEC 62366). There's no mention of clinical ground truth derived from expert consensus, pathology, or outcomes data for assessing diagnostic accuracy.

8. The sample size for the training set

This information is not provided. The document describes a traditional medical device submission, not one for an AI/ML-based device that would typically involve a separate training set. The "software development process" mentioned refers to conventional software engineering, not machine learning model training.

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

This information is not provided, as no training set for an AI/ML model is mentioned.

Summary of Device and Study Focus:

The K122146 submission for the Spacelabs Healthcare Xhibit Central Station, Model 96102, primarily focuses on demonstrating substantial equivalence to a predicate device (Philips Medical Systems Intellivue M3290A). The studies cited are primarily engineering validation and verification tests ensuring compliance with established medical device safety, software development, electromagnetic compatibility, and alarm system standards. The document does not present a clinical performance study with defined acceptance criteria for diagnostic accuracy, sensitivity, or specificity, nor does it involve clinical ground truth, expert readers, or AI/ML components requiring training and test sets in the context of this summary. The "performance testing" referenced is about the system's operational adherence to standards, not a clinical trial of its diagnostic capabilities.

§ 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.