(28 days)
Indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters patients. Intended for monitoring, recording and alarming of 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.
EASI 12-lead ECG is only for use on adult and pediatric patients.
ST Seqment monitoring is restricted to adult patients only.
The transcutaneous gas measurement (tcp02/tcpCO2) is restricted to neonatal patients only.
The names of the devices are the Philips MP20, MP30, MP40, MP50, MP60, MP70, and MP90 IntelliVue Patient Monitor. The modification is the introduction of Release B.1.1 software for the IntelliVue patient monitor devices, MP20, MP30, MP40, MP50 interfacing the Gas Analyzer model M1013A EGM (K041956). The modified devices have the same technological characteristics as the legally marketed predicate devices.
Here's a breakdown of the acceptance criteria and study information for the Philips IntelliVue Patient Monitor, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text does not explicitly state specific quantitative acceptance criteria (e.g., "accuracy must be >95%") or detailed reported device performance in a numerical format for individual parameters. Instead, it makes a general statement about meeting specifications and reliability.
| Acceptance Criteria (Implied) | Reported (General) Device Performance |
|---|---|
| Conformance to specifications cleared for the predicate devices | Meets all reliability requirements |
| Performance of the modified device with respect to the predicate | Meets all performance claims |
| Functionality of the modified device with respect to the predicate | Established |
| Reliability of the modified device with respect to the predicate | Established |
| Safety testing pass/fail based on hazard analysis | Pass/Fail criteria met |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated. The document mentions "system level tests, performance tests, and safety testing from hazard analysis" but doesn't quantify the number of test cases, patient data, or specific scenarios used.
- Data Provenance: Not explicitly stated. It's unclear if the testing involved real patient data, simulated data, or a combination, nor the country of origin. The regulatory submission is from Germany, suggesting testing might have occurred there or within Phillips' global network. It is implied to be prospective testing, as it's for a new software release.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
Not mentioned in the document. The type of device (patient monitor) suggests that ground truth would likely be based on established physiological measurement standards and potentially clinical expert review, but this is not detailed.
4. Adjudication Method for the Test Set
Not mentioned in the document.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
No, an MRMC comparative effectiveness study is not applicable and was not performed. This device is a physiological patient monitor, not an AI-assisted diagnostic tool for human readers. Its primary function is to measure and display physiological parameters, and alarm if they fall outside set limits. There's no AI component for improving human interpretation in the way one would see in an imaging AI application.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, the testing described appears to be a standalone evaluation of the device's performance, functionality, and reliability, without explicitly involving human-in-the-loop performance for its core functions. The software Release B.1.1 itself is the "algorithm only" component that was tested.
7. The Type of Ground Truth Used
The document does not specify the exact "type of ground truth" in the way one might for an imaging algorithm (e.g., pathology, outcomes data). For a patient monitor, ground truth would be established through a combination of:
- Known physical inputs/simulations: Using calibration equipment or simulators to generate precise physiological signals (e.g., a known ECG rhythm, a specific blood pressure waveform) and verifying the device's output against these known inputs.
- Comparison to reference devices: Comparing the monitor's readings to those of other validated and highly accurate reference monitoring devices.
- Technical specifications: Verifying that the device's measurements fall within the specified accuracy and precision limits for each parameter.
8. The Sample Size for the Training Set
Not applicable. This device is a patient monitor, not an AI/machine learning algorithm that requires a "training set" in the conventional sense. The "training" would involve the development and engineering process of the software itself, not a data-driven training pipeline for a predictive model.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no "training set" in the context of an AI/machine learning algorithm for this device.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).