AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients. Intended for monitoring, recording and alarming of multiple physiological parameters of adults, pediatrics and neonates in hospital environments. The MP20, MP30, MP40 and MP50 are additionally intended for use in transport situations within hospital environments.

ST Segment monitoring is restricted to adult patients only.

The transcutaneous gas measurement (tcp0 2 / tcpCO2) is restricted to neonatal patients only.

Device Description

The Philips MP20, MP30, MP40, MP50, MP60, MP70, MP80 and MP90 IntelliVue Patient Monitors. The modification is the introduction of Release C.02 software for the IntelliVue patient monitor devices, which enhances the monitor to calculate and display a numeric for the Minimum Alveolar Concentration (MAC).

AI/ML Overview

The provided text describes a 510(k) summary for the Philips IntelliVue Patient Monitors (K052801), focusing on a software update (Release C.02) that enhances the monitor to calculate and display a numeric for the Minimum Alveolar Concentration (MAC).

Based on the provided information, here's an analysis of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance:

The document states that "Pass/Fail criteria were based on the specifications cleared for the predicate device and test results showed substantial equivalence." However, it does not explicitly list quantitative acceptance criteria or specific performance metrics. It generally states that the device "meets all reliability requirements and performance claims."

Acceptance Criteria (Stated/Implied)Reported Device Performance
Reliability requirements metAchieved
Performance claims metAchieved
Functionality consistent with predicate deviceAchieved
Safety consistent with predicate deviceAchieved
Substantial equivalence to predicate device specificationsAchieved
Ability to calculate and display numeric MACAchieved (new feature)

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

The document does not provide a specific sample size for the test set used to demonstrate adherence to acceptance criteria. It mentions "Verification, validation, and testing activities," "system level tests, performance tests, and safety testing from hazard analysis."

Data Provenance: Not specified. The document does not indicate the country of origin of the data or whether it was retrospective or prospective.

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

The document does not mention the use of experts or a ground truth establishment process for the test set. The evaluation seems to rely on internal testing against existing specifications for predicate devices.

4. Adjudication Method for the Test Set:

Not applicable, as no external experts or adjudication process are mentioned. The testing appears to be internal verification and validation against established specifications.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No, an MRMC comparative effectiveness study was not conducted or mentioned in this submission. This type of study is typically performed to evaluate the impact of an AI-assisted device on human reader performance, which is not the focus of this 510(k) submission.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

The nature of the device (patient monitor with a software update for MAC calculation) implies that the "performance" is inherently standalone in terms of the algorithm generating the MAC numeric. The testing described focuses on the device's ability to accurately calculate and display this value as per its specifications. However, there isn't a specific section detailing a "standalone study" with explicit metrics in the way one might see for an AI diagnostic algorithm. The verification and validation activities essentially serve as the standalone performance evaluation of the new software functionality.

7. Type of Ground Truth Used:

The ground truth for the testing revolved around the specifications cleared for the predicate device and the accurate calculation of the MAC value based on established physiological principles and measurement inputs. It's not based on external expert consensus, pathology, or outcomes data in the typical sense of a diagnostic device. Instead, it's about the correct implementation of a physiological calculation within the monitor.

8. Sample Size for the Training Set:

Not applicable. This device is a patient monitor with a software update for a specific physiological calculation (MAC). There is no mention of a machine learning or AI algorithm that would require a "training set" in the conventional sense for image analysis or diagnostic prediction. The MAC calculation is based on established physiological formulas.

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

Not applicable, as there is no training set mentioned or implied for this device.

§ 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.