Search Results

The monitor is indicated for use by healthcare professionals whenever there is a need for monitoring the physiological parameters of patients.

The monitor is intended to be used for monitoring and recording of, and to generate alarms, for, multiple physiological parameters of adults, pediatrics, and neonates. The monitor is intended for use by trained healthcare professionals in a hospital environment.

The monitor is also intended for use during patient transport inside and outside of the hospital environment.

The monitor is only for use on one patient at a time. It is not intended for home use. Not a therapeutic device. The monitor is for prescription use only.

The ECG measurement is intended to be used for diagnostic recording of rhythm and detailed morphology of complex cardiac complexes (according to AAMI EC 11).

ST segment monitoring is intended for use with adult patients only and is not clinically validated for use with neonatal and pediatric patients.

The IntelliVue Patient Monitors MP2, MP5, MP5, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90, MX400, MX430, MX450, MX500, MX550, MX600, MX700, MX800 and the Multi-Measurement Module X2 acquire multiple physiological patient signals, display measurement values, waves and trends, generate physiological and technical alarms, provide data recording and support patient data management. The monitors support multiple non-invasive and invasive measurements such as ECG, arrhythmia, ST, QT, SpO2, respiration rate, pulse rate, heart rate, invasive and noninvasive blood pressure, temperature, CO2, tcpO2/ tcpCO2, C.O., CCO, intravascular SO2, Sv02, Scv02, spirometry, EEG, BIS, NMT, and gas analysis.

The monitors offer a monitoring solution optimized for the surgical, cardiac, medical and neonatal care environments. They are located in the patient vicinity at the bedside. Several monitor models can also be used mobile, during patient transport inside or outside of hospitals.

The monitors have a color display with touch-screen and/or keys and a navigation point as a primary input device. They also support a specialized remote control, keyboard and pointing devices such as a mouse. External displays can be connected to a built-in video port to provide an adaptive duplicate image of the primary display.

The monitors can interact with several compatible external measuring and auxiliary devices locally at the bedside or in transport situations and with the Central Station via LAN or wireless link.

The software of the IntelliVue Patient Monitors MP5, MP5T, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90, MX400, MX430, MX450, MX550, MX600, MX700, and MX800, was modified to provide the feature Alarm Advisor. Legally marketed IntelliVue Patient Monitors provide the features Graphic Trends (displays for configurable time in a graphic form patient measurement data to show how this data develops over time) and Alarm Limits window (displays in a graphic form 15 min trends, alarm limits, and measurement values, and allows operator changing the limits manually on the basis of the displayed information).

In the new software Rev. M.0 of the subject devices MP5 to MX800, these functionalities were combined in one feature called Alarm Advisor in order to display in a graphic format for a configurable time trends, alarm limits, and measurement values and to allow operator changing the alarm limits manually.

Compared to Graphic Trends and Alarm Limits window, Alarm Advisor provides two enhancements: it gives feedback in case of recurring or continuous alarm limit violations in form of a notification and it allows operator to try out new alarm limits before setting them, with the help of the graphical trend information. When an operator tries a new alarm limit, Alarm Advisor shows the effect the new alarm limit would have had on the occurred alarm limit violations. The Alarm Advisor itself does not propose any specific alarm limit values. It also does not make any automatic alarm limit settings.

The combination of existing trending and alarm limit setting features and their enhancement joint in the Alarm Advisor feature, supports clinician in adapting alarm limits more specifically for individual patients.

The software of the IntelliVue Patient Monitors MP2, X2, MP5, MP5T, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90, MX400, MX430, MX450, MX500, MX550, MX600, MX700, MX800, and the IntelliVue X2 Multi-Measurement Module was additionally modified to support configurable source of QRS tone. In the previously cleared IntelliVue Patient Monitors, the QRS tone can be derived from either HR or Pulse, depending on which is currently selected as the alarm source. In the modified IntelliVue Patient Monitors software Rev. M.0 this limitation has been eliminated so that the source of the QRS tone is free selectable between HR and Pulse.

The provided text describes software modifications to Philips IntelliVue Patient Monitors and the Multi-Measurement Module X2, focusing on the "Alarm Advisor" feature and configurable QRS tone source. The documentation outlines the verification and validation (V&V) activities undertaken to demonstrate the substantial equivalence of these modified devices to their previously cleared predicate devices.

Here's an analysis of the acceptance criteria and the study as presented in the document:

1. A table of acceptance criteria and the reported device performance:

The document doesn't provide a specific table contrasting acceptance criteria with numerical performance data in the traditional sense of diagnostic accuracy (e.g., sensitivity, specificity). Instead, the acceptance criteria are implicit in the pass/fail criteria of the various tests conducted, and the reported "performance" is that these criteria "have been met."

The primary acceptance criteria seem to be related to:

• Functionality: Correct operation, control, configuration, and functioning of the new features (Alarm Advisor and configurable QRS tone source) as specified and according to labeling claims.
• Safety and Effectiveness: Maintaining safe and effective operation of unchanged functions and adhering to relevant safety standards (e.g., IEC 60601-1-8 for the alarm system).
• Reliability: Meeting all defined reliability requirements and performance claims.

Since specific numerical performance metrics are not given, a table like the one requested cannot be fully constructed. However, we can represent the described V&V outcomes:

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

The document does not specify a "test set" in terms of patient data or case numbers. The V&V activities described are primarily software testing, including functional tests, regression tests, and hazard analysis.

• Sample Size: Not applicable in the context of patient data for performance evaluation in this document. The "sample" would be the software itself and its functionalities.
• Data Provenance: Not applicable as it's not a study on clinical data. The tests were likely conducted on simulated environments or test benches in a laboratory setting by the manufacturer, Philips Medizin Systeme Boeblingen GmbH (Germany).

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 the V&V activities relate to software functionality and technical standards rather than clinical diagnostic performance, the "ground truth" would be established by technical specifications, design documents, and relevant industry standards (e.g., AAMI EC 11 for ECG, IEC 60601-1-8 for alarms). Expert clinical review for establishing a "ground truth" on patient data is not described for these specific software modifications.

4. Adjudication method for the test set:

Not applicable. The V&V activities described are technical tests against predefined internal and external (standards-based) criteria, not clinical case adjudication.

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:

No, an MRMC comparative effectiveness study was not done. The device modifications ("Alarm Advisor" and configurable QRS tone) are enhancements to existing monitoring features and do not describe an AI component that would assist human readers in interpretation or diagnosis. The Alarm Advisor
"supports clinicians in adapting alarm limits more specifically for individual patients" by providing graphical trend information and allowing "trying out" new alarm limits, but it "does not propose any specific alarm limit values" nor "make any automatic alarm limit settings." Therefore, it's not an AI-assisted diagnostic tool as typically evaluated by MRMC studies.

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

No, a standalone algorithm-only performance study was not done for a diagnostic algorithm. The Alarm Advisor and configurable QRS tone are integrated software features of a patient monitor, and their performance is evaluated in the context of their functional correctness and compliance with specifications, not as a standalone diagnostic algorithm.

7. The type of ground truth used:

The ground truth for the V&V activities was based on:

• Technical Specifications: Internal design documents and functional requirements for the software features.
• Industry Standards:
  • AAMI EC 11 for ECG measurement (mentioned in the Indications for Use for various monitor models).
  • IEC 60601-1-8 for the alarm system (specifically mentioned for regression tests of the alarm system).
• Hazard Analysis: Ensuring risks are mitigated as per established safety protocols.
• Predicate Device Performance: Pass/fail criteria were based on specifications cleared for the predicate devices, ensuring substantial equivalence.

8. The sample size for the training set:

Not applicable. This document describes V&V activities for software modifications to existing patient monitors, not the development or training of an AI algorithm from a dataset.

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

Not applicable, as there is no mention of a training set for an AI algorithm.

Ask a specific question about this device