(29 days)
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 (tcp02/tcpC02) is restricted to neonatal patients only.
The Philips MP20, MP30, MP30, MP50, MP60, MP70 and MP90 Patient Monitors, Release C.00.
The Philips IntelliVue Patient Monitors (MP30, MP30, MP50) with Release C.00 software, along with the M3014A Capnography Extension interfacing the Philips Mainstream CO2 Sensor model M2501A, underwent verification, validation, and testing activities to establish performance, functionality, and reliability, demonstrating substantial equivalence to predicate devices.
Here's the breakdown of the information requested, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Meets all reliability requirements and performance claims. | "The results demonstrate that the Philips IntelliVue Patient Monitor meets all reliability requirements and performance claims." |
| Functional equivalence to predicate devices. | "Testing the modified device with respect to its predicate... results showed substantial equivalence." |
| Safety equivalence to predicate devices. | "Testing... performance tests, and safety involved system level tests... Pass/Fail criteria were based on testing from hazard analysis." |
| Performance equivalence to predicate devices. | "Testing... performance tests, and safety involved system level tests... Pass/Fail criteria were based on testing from the predicate and creating and test the specifications cleared for the predicate." |
| Intended use as monitoring, recording, and alarming of multiple physiological parameters for adults, pediatrics, and neonates in hospital environments. | "The modified devices have the same intended use as the legally marketed predicate devices. They are intended for the monitoring, recording, and alarming of multiple physiological parameters of adults, pediatrics, and neonates in hospital environments." |
| ST Segment monitoring restricted to adult patients. | "ST Segment monitoring is restricted to adult patients only." |
| Transcutaneous gas measurement (tcp02/tcpC02) restricted to neonatal patients. | "The transcutaneous gas measurement (tcp02/tcpC02) is restricted to neonatal patients only." |
2. Sample Size Used for the Test Set and the Data Provenance
The document does not explicitly state the specific sample size used for the test set (number of patients, records, or data points). It broadly mentions "system level tests, performance costs, and on the based on testing from hazard analysis" and refers to "the predicate" without detailing the specific data used.
The data provenance is not specified beyond implicitly being related to the device development and testing within Philips Medizin Systeme Boeblingen GmbH, Germany. It does not mention country of origin or whether it was retrospective or 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 in the document. The document refers to "Pass/Fail criteria were based on testing from hazard analysis" and "specifications cleared for the predicate," implying internal technical specifications and hazard assessments rather than expert-established ground truth for a test set in the traditional clinical or algorithmic sense.
4. Adjudication Method for the Test Set
This information is not provided in the document. The testing described appears to be technical verification and validation against pre-defined specifications and safety criteria, not clinical judgment necessitating an adjudication method.
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
This information is not provided. The devices are patient monitors, and their performance evaluation focuses on the accuracy and reliability of physiological parameter measurement, not on AI-assisted analysis that would typically involve human readers.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
The document describes the introduction of "Release C.00 software" into patient monitoring devices. The testing activities ("system level tests, performance tests, and safety") inherently evaluate the performance of the device's software and hardware in a standalone manner as a monitoring system. While the device is intended for use by "health care professionals," the performance evaluation described does not seem to involve human-in-the-loop performance in the context of an "AI effect size" study. It assesses the device's ability to accurately measure and alarm on physiological parameters.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
The "ground truth" for the tests appears to be based on:
- Technical Specifications and Predicate Device Performance: "Pass/Fail criteria were based on testing from the predicate and creating and test the specifications cleared for the predicate."
- Hazard Analysis: "Pass/Fail criteria were based on testing from hazard analysis."
- Reliability Requirements and Performance Claims: The stated outcome is that the device "meets all reliability requirements and performance claims."
This suggests a technical and engineering-based ground truth, comparing the new device's output to established benchmarks, previous device performance, and safety standards, rather than direct human clinical expert consensus, pathology, or outcomes data in a diagnostic accuracy study.
8. The Sample Size for the Training Set
This information is not provided as the device and its software are described in the context of traditional medical device validation (verification and validation of performance, functionality, and reliability), not as a machine learning model that would typically have a distinct "training set."
9. How the Ground Truth for the Training Set Was Established
Since a "training set" in the machine learning sense is not indicated, this information is not applicable/not provided. The software's functionality would have been developed according to engineering principles and validated against specifications and predicate device performance.
§ 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.