K Number
K112652
Date Cleared
2011-10-11

(29 days)

Product Code
Regulation Number
870.1130
Panel
CV
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

SureSigns VS2*: Indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients. Standard and optional parameters include: NBP, SpO2, and Temperature. Intended for monitoring, recording, and alarming of multiple physiological parameters of adults, pediatrics and neonates in healthcare environments. Additionally, the monitors may be used in transport situations within a healthcare facility.

SureSigns VSi: Indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients. Standard and optional parameters include: NBP, SpO2, and Temperature. The SureSigns VSi vital signs monitor is intended for measurement of multiple physiological parameters of adults, pediatrics and neonates in healthcare environments. Additionally, the monitor is intended for use in transport situations within a healthcare facility.

Device Description

The SureSigns VS2* Vital Signs Monitor and the SureSigns VSi Vital Signs Monitor are multi-parameter patient monitors. Standard and optional parameters include: NBP, SpO2, and Temperature. Modifications include the addition of an internal radio module, addition of several new accessories (SpO2 sensor and tabletop mount), and EMC Emissions Class changed to Class A.

AI/ML Overview

This 510(k) summary (K112652) describes modifications to existing Philips SureSigns Vital Signs Monitors (VS2+ and VSi), specifically the addition of an internal radio module and new accessories. The core functionality and algorithms of the devices remain unchanged from their predicate versions (K111114 for VS2+ and K110803 for VSi).

Given the nature of this submission, which focuses on hardware and EMC (Electromagnetic Compatibility) changes rather than a new algorithm or diagnostic capability, a typical "device performance" and "acceptance criteria" table as one might find for an AI/ML-based diagnostic device is not directly applicable or explicitly detailed in the provided documents. Instead, the "acceptance criteria" here refers to demonstrating that the modified devices continue to meet the safety and effectiveness standards of their predicates and relevant regulatory specifications.

Here's a breakdown based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

As a direct table of specific numerical acceptance criteria for a diagnostic algorithm and corresponding performance metrics is not present for this type of device modification, a general interpretation of the implied acceptance criteria and reported performance is provided below. The "performance" here refers to maintaining the established safety and effectiveness of the existing predicate devices.

Acceptance Criteria CategoryDescriptionReported Device Performance
Substantial EquivalenceThe modified devices (SureSigns VS2+ and VSi with software B.01 and internal radio module) must be substantially equivalent to their legally marketed predicate devices (SureSigns VS2+ and VSi with software B.00).The submission asserts and FDA agrees that the devices are substantially equivalent to the predicate devices. The modifications did not alter the fundamental technological characteristics.
Intended UseThe intended use and indications for use of the modified devices must remain the same as the predicate devices.The subject devices have the same intended use and indications for use as the legally marketed predicate devices.
Fundamental TechnologyThe subject devices must use the same design and algorithms as the predicate devices.The subject devices use the same design and algorithms as the predicate devices.
Performance TestingSystem-level tests, performance tests, and safety testing must confirm the performance, functionality, and reliability characteristics relative to predicates and hazard analysis.Testing involved system level tests, performance tests, and safety testing from hazard analysis.
Pass/Fail CriteriaPass/Fail criteria for testing were based on specifications cleared for predicate devices, and specifications of subject devices.Test results showed substantial equivalence. The results demonstrate that the monitors meet all reliability requirements and performance claims.
EMC EmissionsThe device's Electromagnetic Compatibility Emissions Class may change but must meet relevant standards (Class A in this case).EMC Emissions Class changed to Class A (implies successful testing to meet Class A standards, though specific results are not detailed).

2. Sample Size Used for the Test Set and the Data Provenance

The document does not detail specific sample sizes for a "test set" in the context of diagnostic accuracy, as this submission is for a device modification rather than a new diagnostic algorithm. The "testing" mentioned refers to engineering verification and validation activities (system level, performance, safety testing) to ensure the modified hardware and software continue to function as intended and meet established specifications.

  • Test Set Sample Size: Not specified in terms of patient data or clinical accuracy. Testing would involve engineering samples of the modified devices.
  • Data Provenance: Not applicable in the context of clinical data for a diagnostic algorithm. The "data" here would be electrical, mechanical, and software test results.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts

This information is not applicable to this 510(k) submission. "Ground truth" established by clinical experts (like radiologists) is relevant for diagnostic devices that interpret images or physiological signals to make a diagnosis. This submission concerns a vital signs monitor, where the output (e.g., NBP, SpO2, Temperature) is a direct measurement, and the "ground truth" for its accuracy typically relies on calibrated reference equipment and standardized test methods, not expert consensus on interpretations.

4. Adjudication Method for the Test Set

Not applicable. Adjudication methods (e.g., 2+1, 3+1) are used to resolve disagreements among multiple experts when establishing ground truth for diagnostic or interpretative tasks. This is not relevant for the type of verification and validation testing described for this vital signs monitor modification.

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. MRMC studies are designed to assess the impact of a diagnostic aid (often AI) on human reader performance. This submission is for a vital signs monitor, which provides physiological measurements, not an interpretive aid for human readers. No AI component is described that would assist human readers in a diagnostic task.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

While the device itself operates in a standalone mode to measure vital signs, the concept of "standalone performance" in the context of AI/ML algorithms, which typically refers to the algorithm's diagnostic accuracy without human intervention, is not directly applicable here. The device's measurements (NBP, SpO2, Temp) constitute its "performance," and this performance is validated against established accuracy standards for such physiological measurements. The document confirms that the device uses the "same design and algorithms as the predicate devices," implying that the core measurement algorithms' performance has been previously established and remains unchanged.

7. The Type of Ground Truth Used

For vital signs monitors, the "ground truth" for performance testing typically involves:

  • Reference Standards: Calibrated reference instruments or patient simulators that provide known, accurate physiological values (e.g., a known blood pressure, SpO2 level, or temperature).
  • Clinical Studies (for initial device clearance): For predicate devices, this would have involved comparing device measurements against invasive reference methods (e.g., arterial line for NBP) or other gold standard clinical measurements.
  • Technical Specifications: The "ground truth" for the current submission's testing is adherence to the technical specifications and performance claims established for the predicate devices, as well as relevant national and international standards for medical devices (e.g., for biocompatibility, electrical safety, EMC).

8. The Sample Size for the Training Set

Not applicable. This device does not inherently have an "AI" or "machine learning" algorithm that requires a "training set" in the conventional sense of computational learning. Its algorithms are fixed, deterministic computational methods for processing physiological signals.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as there is no "training set" for an AI/ML algorithm described in this submission.

§ 870.1130 Noninvasive blood pressure measurement system.

(a)
Identification. A noninvasive blood pressure measurement system is a device that provides a signal from which systolic, diastolic, mean, or any combination of the three pressures can be derived through the use of tranducers placed on the surface of the body.(b)
Classification. Class II (performance standards).