Search Results

The monitors are indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients.

The monitors are intended to be used for monitoring and recording of, and to generate alarms for, multiple physiological parameters of adults, pediatrics, and neonates. The monitors are intended for use by trained healthcare professionals in a hospital environment. The monitors are additionally intended for use in transport situations within hospital environments.

The monitors are only for use on one patient at a time. They are not intended for home use. Not therapeutic devices. The monitors are 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 EC11). ST segment monitoring is intended for use with adult patients only and is not clinically validated for use with neonatal and pediatric patients.

The transcutaneous gas measurement (tcGas) is restricted to neonatal patients only. The SSC Sepsis Protocol, in the ProtocolWatch clinical decision support tool, is intended for use with adult patients only.

The Integrated Pulmonary Index (IPI) is intended for use with adult and pediatric (1 to 12 years) patients only. The IPI is an adjunct to and not intended to replace vital sign monitoring.

The derived measurement Pulse Pressure Variation (PPV) is intended for use with sedated patients receiving controlled mechanical ventilation and mainly free from cardiac arrhythmia. The PPV measurement has been validated only for adult patients.

The IntelliVue NMT Module is intended to be used as an objective neuromuscular transmission monitor, using accelerometry for measuring the muscle contraction following an electrical stimulation of a peripheral nerve. The NMT Module is intended to be used with adult and pediatric patients.

The subject devices Intelli Vue Patient Monitors MX400, MX450, MX500, and MX550 are display units with a TFT LCD flat panel display and built-in CPU. The specific models differ in the size of their flat panel displays and in the number of supported external measurement modules.

MX400 has a 9" display, MX450 and MX500 have a 12" display and MX550 has a 15" display. In addition to the MX400 and MX450, the MX500 and MX550 models have three integrated slots for use with the dedicated external plug-in modules.

The monitors do not have any built-in measurements. They are intended to be connected to any one of the external IntelliVue family physiological multi-measurement modules and/or (MX500/MX550 only) to the IntelliVue plug-in measurement modules.

The monitors support multiple non-invasive and invasive measurements such as ECG, arrhythmia, ST, QT, SpO2, respiration rate, pulse rate, invasive and noninvasive blood pressure, temperature, CO2, C.O., CCO, intravascular SO2, spirometry, EEG, gas measurements, and NMT. The interaction with the patient depends on the monitored physiological parameter(s).

The monitors acquire multiple physiological patient signals (via connected external measurement modules), display measurement values, waves and trends, generate physiological and technical alarms, provide data recording and support patient data management.

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. The monitors can also be used mobile, during patient transport in a hospital setting.

The measurement sensors of the connected external measurement modules are applied at diverse bodily locations, depending on the actual physiological parameters monitored, e.g. on a patient's finger for the pulse oximetry or on a patient's upper arm for the non-invasive blood pressure.

The monitors have a color display with touch-screen as a primary input device. They also support a specialized remote control, keyboard and pointing devices such as a mouse. One external display, which provides an adaptive duplicate image of the primary display, can be connected to a built-in video port.

The monitors interact with the connected external measurement devices locally at the bedside or in transport situations and with the Central Station via LAN or wireless link.

The modification, which is subject of this Premarket Notification, enables the IntelliVue Patient Monitors MX400, MX450, MX500, and MX550 via software update to support two additional features: Remote Display application and Remote Applications, The Remote Display application feature provides the possibility to view an independent monitor screen on an external display and to operate patient monitor from the external display.

The Remote Applications feature allows the user of the patient monitor to access remotely hosted, pre-configured applications made available by the hospital.

The added functionalities are the same as those already provided by other legally marketed Philips IntelliVue Patient Monitors, such as predicate model MX800. For access to the Remote Applications, the predicate Intelli Vue Patient Monitor MX800 supports commercial application server technology, whereas the modified IntelliVue Patient Monitors MX400, MX450, MX500, and MX550 support commercial application server technology as well as the HTML5 protocol for compatibility with standard web application servers

Here's a breakdown of the acceptance criteria and study information for the Philips IntelliVue Patient Monitors MX400, MX450, MX500, and MX550, based on the provided 510(k) summary:

This submission describes a software update to existing patient monitors, adding "Remote Display application" and "Remote Applications" features. Therefore, the V&V activities primarily focus on confirming the correct functioning of these new software features and ensuring that previously cleared functionalities are not negatively impacted.

1. Table of Acceptance Criteria and Reported Device Performance

Since this submission is a software update for existing devices, the "acceptance criteria" are primarily related to the successful implementation and verification of the new features and the continued performance of existing features. The document highlights the meeting of existing specifications and "pass/fail criteria" from previous clearances.

• Correct presentation of parameter data on the Remote Display.
• Correct presentation of alarm and/or INOP information on the Remote Display.
• Correct presentation of operating windows on the Remote Display.
• Ability to operate patient monitors from the Remote Display.
  Remote Applications:
• Correct display of remote applications on the monitor screen.
• Operability of remote applications with user input devices. | Remote Display Application:
  "The conducted tests demonstrate that parameter data, alarm and/ or INOP information and operating windows provided by the modified patient monitors are correctly presented on the Remote Display and that the patient monitors can be operated from the Remote Display."
  Remote Applications:
  "The conducted tests demonstrate that the remote applications are correctly shown on the display of the modified patient monitors and can be operated with user input devices." |
  | Safety & Risk Mitigation | - All specified pass/fail criteria from Hazard Analysis met.
• Effectiveness of implemented design risk mitigation measures. | "All specified pass/fail criteria have been met. The test results confirmed the effectiveness of the implemented design risk mitigation measures." |
  | Regression/Non-Interference | Unchanged and unaffected functions from the previous software (Rev. K.10) continue to work correctly with the new software (Rev. K.20).
• Safe, effective, and correct operation according to all specifications and labeling claims of the predicate devices. | "The regression tests demonstrate that the modified patient monitors work safely, effectively, and correctly in accordance with all specifications and labeling claims."
  "Pass/Fail criteria were based on the specifications cleared for the predicate devices and test results showed substantial equivalence." |
  | General Reliability & Performance | Meeting all defined reliability requirements and performance claims. | "The results demonstrate that the Philips Intelli Vue Patient Monitors MX400, MX450, MX500, and MX550 meet all defined reliability requirements and performance claims." |

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

The document does not explicitly state the "sample size" in terms of number of patients or cases for clinical data. Instead, the testing is described as functional and regression testing on the physical devices (monitors).

• Sample Size: Not applicable in the context of clinical patient data. The "sample" would be the specific hardware models (MX400, MX450, MX500, MX550) with the updated software (Rev. K.20). The tests were conducted on these devices.
• Data Provenance: Not applicable as it's not a clinical study involving patient data. The testing was an internal validation and verification (V&V) activity.

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

Not applicable. The ground truth for this type of V&V (functional and regression testing of software features on a patient monitor) is the expected behavior and output of the device as defined by its specifications and design documents. It does not involve expert clinical assessment of patient data.

4. Adjudication Method for the Test Set

Not applicable. This was internal engineering and software testing against predefined functional and non-functional requirements and previous device specifications. It does not involve adjudication of clinical findings.

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. This submission is for a software update to a patient monitor, adding features for remote display and remote application access. It does not involve an AI component for interpretation or diagnosis, nor does it involve human readers assessing cases.

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

Not applicable. The device is a patient monitor, which continuously collects and displays physiological parameters. The new features (Remote Display and Remote Applications) are functionalities that enhance how users interact with and access data from the monitor. There isn't a standalone "algorithm" in the diagnostic or interpretative sense tested separately.

7. The Type of Ground Truth Used

The ground truth used for this V&V was based on:

• Device Specifications: The pre-defined expected outputs and behaviors of the patient monitor and its new features.
• Predicate Device Performance: The established performance and specifications of the previously cleared IntelliVue Patient Monitors (Rev. K.10 and MX800 models).
• Hazard Analysis Requirements: Safety criteria and risk mitigation effectiveness.

8. The Sample Size for the Training Set

Not applicable. This is not a machine learning or AI-based device that requires a training set of data. The "training" for the software involves its development, coding, and internal debugging processes, not a dataset in a machine learning context.

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

Not applicable, as there is no training set in the machine learning sense.

Ask a specific question about this device

The IntelliVue CL Respiration Pod is indicated for use by health care professionals whenever there is a need for intermittent or spot-check acquisition and monitoring of physiological patient parameters respiration rate and pulse rate wirelessly in specific hospital areas. The IntelliVue CL Respiration Pod is mainly indicated for use in general medical and surgery wards and in waiting areas of emergency rooms.

It is not indicated for use in hospital areas in which continuous patient monitoring is needed, such as intensive care units or operating rooms.

The intended use of the IntelliVue CL Respiration Pod when used together with a patient monitor is for intermittent or spot-check monitoring and recording of, and to generate alarms for, respiration rate and pulse rate of adult patients.

The IntelliVue CL Respiration Pod is also intended for acquisition of respiration rate and pulse rate data of adult patients for a clinical information management system.

The IntelliVue CL Respiration Pod is intended for use by health care professionals. It is not intended for home use. It is not a therapeutic device.

The IntelliVue CL Respiration Pod is not intended for use on patients with extremely high values for respiration rate (above 60 rpm).

The IntelliVue CL Respiration Pod is not intended for use on acutely ill cardiac patients with the potential to develop life threatening arrhythmias, e.g. very fast atrial fibrillation or ventricular tachycardia (rapid irregular pulse rate). For monitoring of these patients, a device for continuous ECG monitoring is necessary. The IntelliVue CL Respiration Pod is not a substitute for an ECG monitor.

Warning: Do not use the CL Respiration Pod on patients with rapid, irregular heart rates greater than 110 bpm. Use under these conditions has not been clinically validated.

Rx only: US Federal Law restricts these devices to sale by or on the order of a physician.

The IntelliVue CL Respiration Pod is a small body-worn, cableless, battery powered, respiration rate and pulse rate measuring and monitoring device. It uses specifically designed adhesive attachment (Mobile CL Resp Attachment, cleared with K122223), which holds the CL Respiration Pod at the patient chest.

The CL Respiration Pod provides and communicates measurements values and other information (e.g. battery state) wirelessly via Short Range Radio (SRR) to an assigned compatible IntelliVue Patient Monitor or IntelliVue GuardianSoftware. It can also provide information on basic posture (like supine, prone, upright etc.) and activity of the patient. The CL Respiration Pod can be controlled from the assigned IntelliVue Patient Monitor or IntelliVue GuardianSoftware.

The CL Respiration Pod is a small, battery powered, wireless, and body worn respiration and pulse rate measuring and monitoring device. It is attached to the patient's left costal arch using a specialized accessory, the adhesive Mobile CL Resp Attachment. The CL Respiration Pod has a multicolor LED and a single key to display states and allow basic operation locally. The CL Respiration Pod is connected during its use wirelessly via SRR a compatible IntelliVue Patient Monitor or IntelliVue to GuardianSoftware.

The CL Respiration Pod uses a measurement principle that is based the thoracic movements. Inclination changes of the on incorporated accelerometer sensor, caused by chest and abdomen movements during breathing and heart contraction, produce a voltage signal, from which respiration and pulse rate signals are derived. The modified Philips IntelliVue CL Respiration Pod uses the same measurement principle (respiratory effort and heart contraction/beating) to derive the respiration and pulse signal as the predicate Philips IntelliVue CL Respiration Pod.

With the means of the built-in accelerometer sensor, the modified CL Respiration Pod also detects activity and basic posture of the patient. This is the same technology as used by the legally marketed Philips IntelliVue CL Respiration Pod (K122223).

The Philips IntelliVue CL Respiration Pod aims to measure respiration rate and pulse rate. The study conducted for this 510(k) submission (K132320) is primarily focused on demonstrating substantial equivalence to a predicate device (IntelliVue CL Respiration Pod, K122223) rather than establishing new acceptance criteria or a comparative effectiveness of AI with human readers.

Here's an analysis of the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

The submission describes verification and validation activities, but it doesn't explicitly state quantitative acceptance criteria in a table format that the device needed to meet for de novo clearance. Instead, the study aims to show substantive equivalence to a predicate device.

The reported device performance is described qualitatively as meeting defined specifications and demonstrating substantial equivalence. The document states:

• "The test results have shown that the respiration rate and pulse rate accuracy, resolution, and signal quality met in the whole measurement range the defined specifications."
• "The results of the statistical comparison demonstrate the substantial equivalency of of the modified IntelliVue CL Respiration Pod with the predicate IntelliVue CL Respiration Pod (K122223)."

Without specific numerical criteria for accuracy, resolution, and signal quality, a direct table of acceptance criteria vs. performance cannot be fully constructed from the provided text. The "acceptance criteria" appear to be implicit in the demonstration of substantial equivalence and meeting internal specifications.

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

• Sample Size: The additional clinical data set used for validating algorithm changes consisted of 26 patients (21 male, 5 female).
• Total Duration of Recording: 621 hours and 10 minutes.
• Data Points Used for Comparison: 2,276,855 ECG beats and 255,307 breaths.
• Data Provenance: The document does not explicitly state the country of origin. It mentions "clinical data," which implies real patient data. It is a prospective or, more accurately, retrospective analysis of a prospectively collected dataset, as it explicitly states, "An additional not yet used clinical data set with patient signals was used to validate the algorithm changes." This implies data were pre-existing before being used for this specific validation. It also notes that an "identical data set of K122223 has been reused for the development of the modifications," which would be retrospective for this new device.

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

The document does not mention the use of experts to establish ground truth for the test set. The comparison is statistical, between the modified device and the predicate device.

4. Adjudication Method for the Test Set

No adjudication method is mentioned or implied, as the comparison is statistical against a predicate device's measurements, not against a consensus-based ground truth established by experts.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done. The device is a physiological parameter monitor, and the study focuses on its measurement accuracy and equivalence to another device, not on how it impacts human reader performance or diagnostic tasks. The device itself is not an AI algorithm that assists human readers in interpretation.

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

Yes, the evaluations described are primarily standalone performance assessments of the device itself (or its underlying algorithms for respiration and pulse rate derivation) compared to a predicate device. The clinical performance tests involve a "Bland-Altman statistical comparison between respiration rate and pulse rate performance measured by the modified IntelliVue CL Respiration Pod and the predicate IntelliVue CL Respiration Pod." This is an assessment of the device's output.

7. The Type of Ground Truth Used

The "ground truth" in this context is the measurements obtained from the legally marketed predicate device (IntelliVue CL Respiration Pod, K122223). The study aimed to show that the modified device's measurements are substantially equivalent to those of the predicate device. This is a form of reference standard comparison rather than an independent gold standard like pathology or expert consensus. For bench testing, "simulated values" were used as the reference.

8. The Sample Size for the Training Set

The document states, "Two separate clinical data sets have been used. The identical data set of K122223 has been reused for the development of the modifications." The sample size for this reused dataset (presumably for training or development of the modifications) is not specified in the provided text.

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

The ground truth for the "training set" (the data from K122223 used for development) is implicitly linked to how the original predicate device (K122223) established its performance and potentially its own reference measurements. The current submission does not detail how the ground truth for this development dataset was established but indicates it was previously used for K122223.

Ask a specific question about this device

The monitors are indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients.

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

The monitors are additionally intended for use in transport situations within hospital environments.

The monitors are only for use on one patient at a time. They are not intended for home use. Not therapeutic devices. The monitors are 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 ECI I).

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

The transcutaneous gas measurement (tcGas) is restricted to neonatal patients only.

BIS is intended for use under the direct supervision of a licensed health care practitioner or by personnel trained in its proper use. It is intended for use on adult and pediatric patients within a hospital or medical facility providing patient care to monitor the state of the brain by data acquisition of EEG signals. The BIS may be used as an aid in monitoring the effects of certain anesthetic agents.

Use of BIS monitoring to help guide anesthetic administration may be associated with the reduction of the incidence of awareness with recall in adults during general anesthesia and sedation.

The SSC Sepsis Protocol in the Protocol Watch clinical decision support tool, is intended for use with adult patients only.

The Integrated Pulmonary Index (IPI) is intended for use with adult and pediatric (I to 12 years) patients only. The IPI is an adjunct to and not intended to replace vital sign monitoring.

The derived measurement Pulse Pressure Variation (PPV) is intended for use with sedated patients receiving controlled mechanical ventilation and mainly free from cardiac arrhythmia. The PPV measurement has been validated only for adult patients.

The IntelliVue NMT Module is intended to be used as an objective neuromuscular transmission monitor, using accelerometry for measuring the muscle contraction following an electrical stimulation of a peripheral nerve. The NMT Module is intended to be used with adult and pediatric patients.

The IntelliVue Patient Monitors MX500 and MX550 are modification of the legally marketed IntelliVue Patient Monitor MP50.

The MX500 and MX550 are display units with a TFT LCD flat panel display and built-in CPU. The models MX500 and MX550 differ only in the size of their flat panel displays: MX500 has a 12" and MX550 has a 15" display.

The MX500 and MX550 do not have any built-in measurements. They can be connected to one Philips M3001A Multi-Measurement Server, M3002A (X2) Multi-Measurement Module, any one of the M3012A. M3015A/B or M3016A Measurement Server Extensions. plug-in measurement modules M1006B Invasive Blood Pressure, M1011A Intravascular SQ2, M1012A C.O. /CCO, M1014A Spirometry, M1020B SpQ2, M1027A EEG, M1029A Temperature, 865383 NMT, 865115 IntelliBridge EC10, to the 865298 (TcG10) Transcutaneous Gas Module and to the M1013A (G1) or M1019A (G5) Gas Modules. These external devices provide non-invasive and invasive measurements such as ECG with arrhythmia and ST, respiration, SpO2, NBP, invasive blood pressure, temperature, CO2, C.O., CCO, Intravascular SO2, Spirometry, EEG and NMT.

The MX500 and MX550 acquire multiple physiological patient signals (via connected external measurement modules). display measurement values, waves and trends, generate physiological and technical alarms, provide data recording and support patient data management.

The MX500 and MX550 offer a monitoring solution optimized for the surgical, cardiac, medical and neonatal care environments. They are located in the patient vicinity either at the bedside or used mobile, during patient transport in the hospital.

The MX500 and MX550 have a color display with touch-screen as primary input device. They also support a specialized remote control, keyboard and pointing devices such as a mouse.

The MX500 and MX550 interact with the connected external measurement devices locally at the bedside or in transport situations and with the Central Station via LAN or WLAN.

Here's a breakdown of the acceptance criteria and study information for the Philips IntelliVue Patient Monitors MX500 and MX550 based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes the acceptance criteria not in terms of specific performance metrics or a numerical table, but rather as meeting established standards and specifications. The reported device performance is stated generally as having met all these criteria.

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

The document does not explicitly state a "test set" in the context of clinical data for performance evaluation in the typical sense (e.g., patient cases). Instead, the testing described is primarily focused on engineering verification and validation (V&V) of the hardware and software against technical standards and the predicate device's specifications.

• Sample Size: Not applicable in the context of clinical patient data. The "sample" here refers to the number of IntelliVue Patient Monitor MX500 and MX550 devices tested during V&V activities. The exact number of devices tested is not specified, but it implies multiple units to ensure robustness across manufacturing.
• Data Provenance: The testing was conducted internally by Philips, a German company (Philips Medizin Systeme Boeblingen GmbH). It is retrospective in the sense that it's testing the developed product against predefined engineering and safety standards, rather than a prospective clinical trial gathering new patient data. The document does not mention any data from specific countries of origin related to patient cases.

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

This information is not provided in the document. The "ground truth" in this context refers to engineering specifications and performance expectations, which would typically be established by product design and quality engineers, and regulatory specialists within Philips. There is no mention of external medical experts establishing ground truth for performance in a clinical validation study.

4. Adjudication Method for the Test Set:

This information is not provided. Given that the V&V activities are primarily engineering and safety compliance tests, the "adjudication method" would likely involve internal review and sign-off processes by engineering and quality assurance teams, rather than a clinical adjudication panel.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:

No, an MRMC comparative effectiveness study was not conducted or described in this document. The submission focuses on demonstrating substantial equivalence to a predicate device (IntelliVue Patient Monitor MP50) through engineering and safety testing, not on improving human reader performance with AI assistance. The devices are patient monitors, not AI diagnostic tools.

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

The devices are patient monitors which are inherently "human-in-the-loop" as they provide data for healthcare professionals. There isn't a standalone "algorithm-only" performance described, as the core function is to display physiological parameters for human interpretation and action.

7. The Type of Ground Truth Used:

The ground truth used for these V&V activities is primarily engineering specifications, recognized consensus standards, and the performance characteristics of the predicate device (IntelliVue Patient Monitor MP50). These standards and specifications define what is considered "correct" or "safe" performance for the device. There is no mention of pathology, expert consensus on patient cases, or outcomes data as a ground truth for this submission, as it's a device safety and performance submission, not a clinical diagnostic algorithm submission.

8. The Sample Size for the Training Set:

This information is not applicable and therefore not provided. The IntelliVue Patient Monitors MX500 and MX550 are not AI/ML-based algorithms that require a "training set" in the computational sense. They are hardware devices with embedded software designed to acquire, process, and display physiological signals based on established medical science and engineering principles.

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

This information is not applicable as there is no "training set" for these patient monitors.

Ask a specific question about this device

The monitors are indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients. The monitors are intended to be used for monitoring and recording of, and to generate alarms for, multiple physiological parameters of adults, pediatrics, and neonates. The monitors are intended for use by trained healthcare professionals in a hospital environment. The MP5 and MP5SC monitors are also intended for use during patient transport inside the hospital environment; only the MP5 monitor is for use during patient transport outside of the hospital environment. The MP5 and MP5SC when used with the TRx4841A/TRx4851A IntelliVue Telemetry System Transceiver or with the IntelliVue Cableless Measurement Devices, are intended for use in a hospital environment and during patient transport inside the hospital environment. The monitors are only for use on one patient at a time. They are not intended for home use. Not therapeutic devices. The monitors are 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 Predictive Temperature measurement is intended for use with adult and pediatric patients in a hospital environment. The SSC Sepsis Protocol, in the Protocol Watch clinical decision support tool, is intended for use with adult patients only. The Integrated Pulmonary Index (IPI) is intended for use with adult and pediatric (1 to 12 years) patients only. The IPI is an adjunct to and not intended to replace vital sign monitoring. The derived measurement Pulse Pressure Variation (PPV) is intended for use with sedated patients receiving controlled mechanical ventilation and mainly free from cardiac arrhythmia. The PPV measurement has been validated only for adult patients.

The Philips IntelliVue Patient Monitor family comprises the multi-parameter patient monitor models: IntelliVue Patient Monitors MP5 and MP5SC, that consist of display units including built-in and central processing units (CPU) and physiological measurements. All monitors share the same system architecture and exactly the same software is executed on each monitor. The IntelliVue Patient Monitors measure multiple physiological parameters such as surface ECG, invasive and non-invasive etc., generate alarms, record physiological pressure, signals, store derived data, and communicate derived data and alarms to central stations via the IntelliVue Clinical Network. The subject modification introduces the optional The Philips Tympanic Temperature Module (866149) for the IntelliVue Patient Monitors MP5 and MP5SC. This Tympanic Temperature extends the capability of the IntelliVue Patient Module Monitors MP5 and MP5SC to interface the Genius™ 2 Tympanic Temperature Probe (cleared by Covidien, K060649). Additionally the software revision J.21 is made available for the IntelliVue Patient Monitors MP5 and MP5SC.

The provided text is a 510(k) summary for a patient monitor and mainly focuses on showing substantial equivalence to previously cleared devices. It does not contain the kind of detailed study information (like sample sizes for test and training sets, data provenance, expert qualifications, ground truth establishment, or specific performance metrics with acceptance criteria) that would typically be associated with performance studies for AI/ML devices.

The document discusses "Verification & Validation Activities" but these primarily reference compliance with general safety and EMC standards (IEC 60601-1-2 and IEC 60601-1), environmental testing, and software functionality testing. These tests confirm the device works safely and to specifications, but they don't involve the kind of performance metrics against ground truth that your questions imply for AI/ML models.

The "acceptance criteria" discussed are largely implicit: that the device works safely, effectively, and correctly in accordance with specifications and labeling claims, and that all applicable requirements of the standards are met. "Reported device performance" is also general, stating it "worked safely and according to their specifications" and "met all reliability requirements and performance claims."

Therefore, based on the provided text, I cannot complete the requested tables and information for most of your points. This document is a regulatory submission for a patient monitor with an added temperature module and software update, not a clinical performance study for an AI/ML diagnostic or prognostic device.

If this were a document for an AI/ML device, the detailed information you requested would be crucial. Since it's not, I can only address what is present in the text.

Here's an attempt to answer the questions based only on the provided text, with many fields explicitly stated as "Not Applicable" or "Not Provided" due to the nature of the document:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: Not provided. The document describes engineering and system-level verification and validation, not a clinical trial with a "test set" in the context of AI/ML performance evaluation.
• Data Provenance (country of origin, retrospective/prospective): Not provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable. The "ground truth" for this monitoring device is its adherence to technical specifications, safety standards, and functional claims, not expert-labeled clinical data.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable. No expert adjudication process is described.

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. This is not an AI/ML diagnostic or prognostic device, and no MRMC study is mentioned.

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

• Not applicable. This is a patient monitor, not an algorithm being evaluated for standalone performance in the context of AI/ML. Its performance is inherent in its operation (e.g., accuracy of parameter measurement, alarm functionality).

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• The "ground truth" for this device appears to be defined by its engineering specifications, adherence to recognized consensus standards (like IEC 60601), and functional requirements for safety and effectiveness.

8. The sample size for the training set

• Not applicable. This document does not describe an AI/ML model that requires a training set.

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

• Not applicable. This document does not describe an AI/ML model or a training set.

Ask a specific question about this device

The monitors are indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients.

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

The monitors are additionally intended for use in transport situations within hospital environments.

The monitors are only for use on one patient at a time. They are not intended for home use. Not therapeutic devices. The monitors are 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 ECI1).

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

The SSC Sepsis Protocol, in the ProtocolWatch clinical decision support tool, is intended for use with adult patients only.

The Integrated Pulmonary Index (IPI) is intended for use with adult and pediatric (1 to 12 years) patients only. The IPI is an adjunct to and not intended to replace vital sign monitoring.

The derived measurement Pulse Pressure Variation (PPV) is intended for use with sedated patients receiving controlled mechanical ventilation and mainly free from cardiac arrhythmia. The PPV measurement has been validated only for adult patients.

The IntelliVue Patient Monitor MX400 and MX450 is a modification of the legally marketed IntelliVue Patient Monitor MP30.

The MX400 and MX450 are display units with a TFT LCD flat panel display and built-in CPU. The models MX400 and MX450 differ only in the size of their flat panel displays: MX400 has a 9" and MX450 has a 12" display.

The MX400 and MX450 do not have any built-in measurements. They can be connected to one Philips M3001A Multi-Measurement Server, M3002A (X2) Multi-Measurement Module and any one of the M3012A, M3014A, M3015A/B or M3016A Measurement Server Extensions, as well as to the M1013A (G1) or M1019A (G5) Gas Modules. These external devices provide non-invasive and invasive measurements such as ECG with arrhythmia and ST, respiration, SpO2, NBP, invasive blood pressure, temperature, CO2, C.O., CCO.

The MX400 and MX450 acquire multiple physiological patient signals (via connected external measurement modules), display measurement values, waves and trends, generate physiological and technical alarms, provide data recording and support patient data management.

The MX400 and MX450 offer a monitoring solution optimized for the surgical, cardiac, medical and neonatal care environments. They are located in the patient vicinity either at the bedside or used mobile, during patient transport in the hospital.

The MX400 and MX450 have a color display with touch-screen as primary input device. They also support a specialized remote control, keyboard and pointing devices such as a mouse.

The MX400 and MX450 interact with the connected external measurement devices locally at the bedside or in transport situations and with the Central Station via LAN.

This is a description of the acceptance criteria and study for the Philips IntelliVue Patient Monitor MX400 and MX450.

1. Table of Acceptance Criteria and Reported Device Performance

The provided 510(k) summary focuses on demonstrating substantial equivalence to a predicate device rather than presenting specific numerical performance metrics against predefined acceptance criteria for novel functionalities. The acceptance criteria described are broad and relate to safety, effectiveness, and adherence to established standards.

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

The provided summary does not specify a "test set" in the context of patient data or clinical trials. The testing described primarily involves engineering and system-level verification and validation (V&V) activities. Therefore, there is no sample size for a test set of patient data, nor is there information on data provenance (e.g., country of origin, retrospective/prospective). The validation focuses on the device's adherence to technical standards and its functional performance when connected to existing, already cleared measurement modules.

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

This information is not applicable. The validation described is not a clinical study requiring expert interpretation of medical data to establish ground truth. It is a technical V&V process ensuring the device's proper functioning and adherence to standards.

4. Adjudication Method for the Test Set

This information is not applicable for the reasons mentioned in point 3.

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

No MRMC comparative effectiveness study was done. The submission is for a modification of an existing patient monitor, not an AI-assisted diagnostic tool that would involve human readers interpreting cases.

6. Standalone Performance

The concept of "standalone performance" (algorithm only without human-in-the-loop) is not directly applicable in the context of this traditional patient monitor device. The device itself is a monitor that displays physiological parameters measured by external modules. Its "performance" is evaluated based on its ability to accurately acquire, display, and manage data from these modules, and adhere to safety and functional standards. The summary details regression testing which essentially verifies the standalone functioning of the device's internal components, software, and interfaces according to its specifications.

7. Type of Ground Truth Used

The "ground truth" for the verification and validation activities described in the 510(k) summary are primarily:

• Recognized consensus standards: IEC 60601-1-2, IEC 60601-1, IEC 60601-1-8, IEC 62304.
• Specifications cleared for the predicate device: The MX400 and MX450's performance was compared against the established specifications and performance of the legally marketed IntelliVue Patient Monitor MP30.
• Internal design specifications: The device's own defined specifications for its functions, such as battery operating time, display functionality, and interface performance.

There is no mention of expert consensus, pathology, or outcomes data being used as ground truth for this device's V&V.

8. Sample Size for the Training Set

This information is not applicable. The IntelliVue Patient Monitor MX400 and MX450 are hardware devices with software, not a machine learning or AI algorithm that requires a "training set" of data.

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

This information is not applicable for the reasons mentioned in point 8.

Ask a specific question about this device

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 Predictive Temperature unit is intended for use with adult and pediatric patients in a hospital environment. The SSC Sepsis Protocol, in the ProtocolWatch clinical decision support tool, is intended for use with adult patients only. The derived measurement Pulse Pressure Variation (PPV) is intended for use with sedated patients receiving controlled mechanical ventilation and mainly free from cardiac arrhythmia. The PPV measurement has been validated only for adult patients. The transcutaneous gas measurement (tcGas) is restricted to neonatal patients only. BIS is intended for use under the direct supervision of a licensed health care practitioner or by personnel trained in its proper use. It is intended for use on adult and pediatric patients within a hospital or medical facility providing patient care to monitor the state of the brain by data acquisition of EEG signals. The BIS may be used as an aid in monitoring the effects of certain anesthetic agents. Use of BIS monitoring to help guide anesthetic administration may be associated with the reduction of the incidence of awareness with recall in adults during general anesthesia and sedation.

The Philips IntelliVue Patient Monitors family comprises the multiparameter patient monitor series: MP2, X2, MP5, MP5T, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90 and MX600, MX700, and MX800. Each monitor consists of a display unit including built-in or separate central processing unit (CPU) and physiological measurement modules. All monitors share the same architecture of CPU units and exactly the same software is executed on each monitor. The monitors measure physiological parameters such as: Sp02, pulse, ECG, arrhythmia, ST, QT, respiration, invasive and noninvasive blood pressure, temperature, CO2, spirometry, C.O., CCO, tcp02/ tcpCO2, S02, Sv02, Scv02, EEG, and BIS. They generate alarms, record physiological signals, store derived data, and communicate derived data and alarms to the central station. IntelliVue series MP2, X2, MP5, MP5T, MP5SC, MP20, and MP30 are robust, portable, lightweight, compact in size and modular in design patient monitors with interfaces to dedicated external measurement devices. Models MP2, X2, MP5, MP5T, and MP5SC also incorporate multiple built-in physiological measurements. IntelliVue series MP40, MP50, MP60, MP70, MX600, MX700, and MX800 are patient monitors with built-in central processing unit, flat panel display and interfaces to dedicated external measurement devices. Models MX600, MX700, and MX800 have widescreen displays. IntelliVue series MP80 and MP90 are patient monitors with flat panel display and central processing unit as separate components. They have interfaces to dedicated external measurement devices.

Here's a breakdown of the acceptance criteria and the study information based on the provided text, structured as requested:

Acceptance Criteria and Device Performance Study for Philips IntelliVue Patient Monitors (Software Revision J.04)

Overview:
The submission describes a software modification to existing Philips IntelliVue Patient Monitors (MP2, X2, MP5, MP5T, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90, MX600, MX700, and MX800) to introduce a new SpO2 intelligent alarm delay feature called 'Smart Alarm Delay'. The study aims to demonstrate that this modified device is as safe and effective as the predicate devices.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a quantitative table of acceptance criteria with corresponding performance metrics for the 'Smart Alarm Delay' feature in the format often seen for diagnostic devices (e.g., sensitivity, specificity, accuracy). However, the "Summary of V&V activities" section outlines the general performance goals and outcomes.

2. Sample Size and Data Provenance for the Test Set

• Sample Size: The document does not specify the exact number of individuals (test persons) involved in the clinical evaluation. It refers to "two user groups - one consisting of physicians and one consisting of nurses" and later "the vast majority of test persons." This suggests a qualitative assessment rather than a statistically powered performance study.
• Data Provenance: Not explicitly stated, but clinical evaluation of user understanding implies prospective testing with healthcare professionals. The country of origin for this specific clinical evaluation is not mentioned.

3. Number of Experts and Qualifications for Ground Truth of the Test Set

• The "clinical evaluation" appears to focus on user comprehension and acceptance, not on establishing a traditional clinical "ground truth" for diagnostic accuracy.
• Number of Experts: Two user groups were formed: "one consisting of physicians and one consisting of nurses." The exact number of individuals within each group is not provided.
• Qualifications of Experts:
  • Physicians
  • Nurses
  • No specific years of experience or subspecialty are mentioned.

4. Adjudication Method for the Test Set

Not applicable. The clinical evaluation described is a qualitative assessment of user understanding and perception, not a diagnostic accuracy study requiring adjudication of results.

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

No. The document describes a software modification to an existing patient monitor to add an intelligent alarm delay feature. The "clinical evaluation" focused on user understanding and acceptance of this feature, not on comparing reader performance with and without AI assistance.

6. Standalone Performance Study (Algorithm Only)

No, not in the traditional sense of a standalone diagnostic algorithm performance study. The modification is an alarm delay feature within an existing monitoring system. The document states:

• "The new 'Smart Alarm Delay' feature is isolated from the SpO2 measurement algorithm, i.e. signal acquisition and numeric processing."
• "The devices hardware and all accessories including, but not limited to the SpO2 sensors remain completely unchanged."
• "The modification does not affect device performance in general and device accuracy in particular."
• Performance aspects covered by ISO 9919 from prior V&V are considered still valid.

This indicates that the fundamental SpO2 measurement accuracy itself was not re-evaluated as a standalone algorithm performance, as the algorithm for SpO2 measurement remained unchanged. The focus was on the alarm delay logic and its user-facing implications.

7. Type of Ground Truth Used

For the "clinical evaluation" regarding the 'Smart Alarm Delay' feature, the "ground truth" appears to be user understanding and subjective opinion as gathered directly from physicians and nurses. For the core SpO2 measurement, the ground truth and performance validation are based on prior verification and validation activities conducted according to ISO 9919 for the predicate device, which are deemed still valid.

8. Sample Size for the Training Set

Not applicable. This submission is for a software modification adding an alarm delay feature, not a machine learning or AI algorithm that requires a dedicated training set for model development. The 'Smart Alarm Delay' is described as being "based on the same fundamental principle" as the predicate's 'SatSeconds' alarm management technique, implying a rule-based or empirically derived logic rather than a learned model.

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

Not applicable, as no training set for a machine learning model was described or used.

Ask a specific question about this device

Indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients. Intended for monitoring and recording of and to generate alarms for multiple physiological parameters of adults, pediatrics and neonates in hospital environments. The MP2, MP5, MP5T, MP5SC, X2, MP20, MP30, MP40, and MP50 are additionally intended for use in transport situations within hospital environments. The MP2, X2 and MP5 are also intended for use during patient transport outside of a hospital environment.

The Integrated Pulmonary Index (IPI) is intended for use with adult and pediatric (1 to 12 years) patients only. The IPI is an adjunct to and not intended to replace vital sign monitoring.

The Philips IntelliVue Patient Monitor family comprises the multi-parameter patient monitor models MP2, X2, MP5, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90, MX600, MX700 and MX800 Patient Monitors which consist of display units IntelliVue including build-in or separate flat panel displays and central processing units as well as physiological measurement modules. All monitors share the same system architecture and exactly the same software is executed on each. The Patient Monitor family is a flexible and modular monitoring solution optimized for the surgical, cardiac, general medical and neonatal care environments. The monitors can be connected to the Philips Multi-Measurement Module (MMS) family with its extensions to the IntelliVue family plug-in measurement modules. The and monitors can also be connected to the IntelliVue anesthetic gas modules and to the IntelliVue TcG10 Measurement Module.

The subject modification is the introduction of the Integrated Pulmonary Index (IPI) software module as an extension to the legally marketed Microstream CO2 measurement module as integrated or interfaced to the Patient Monitor family.

The IPI is a numerical integer value ranging from 1 to 10. It is calculated based on the four major parameters from the monitoring of the physiological parameters CO2 and SpO2 in order to provide a simple and clear single parameter indication of the patient's ventilation status. These four major parameters are etCO2 and Respiration Rate (RR) which are received from the Microstream CO2 measurement module, as well as SpO2 and Pulse Rate (PR) which are received from the pulse oximetry module of the host system.

The Philips MP2, X2, MP5, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90, MX600, MX700, and MX800 IntelliVue Patient Monitors, with the Integrated Pulmonary Index (IPI) software module, underwent verification and validation testing to establish their safety, performance, functionality, and reliability.

1. Acceptance Criteria and Reported Device Performance:

The provided document states that "Pass/Fail criteria were based on the specifications cleared for the predicate devices." However, the specific quantitative acceptance criteria for the IPI software module or the overall patient monitor performance are not explicitly detailed in the provided text. The document concludes: "The results demonstrate that the modified Philips MP2, X2, MP5, MP5T, MP5SC, MP20, MP30, MP40, MP50, MP60, MP70, MP80, MP90, MX600, MX700 and MX800 IntelliVue Patient Monitors are as safe and as effective and perform as the predicate devices."

Therefore, based on the provided text, the table is as follows:

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

This information is not provided in the document. The text mentions "Verification and validation testing activities were conducted," but does not specify the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective nature).

3. Number of Experts and their Qualifications for Ground Truth of the Test Set:

This information is not provided in the document.

4. Adjudication Method for the Test Set:

This information is not provided in the document.

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

An MRMC comparative effectiveness study is not mentioned in the document. The study described focuses on the comparison of the modified device to predicate devices in terms of safety and effectiveness, rather than evaluating human reader improvement with AI assistance.

6. Standalone (Algorithm Only) Performance Study:

A standalone performance study of the IPI algorithm without human-in-the-loop is not explicitly detailed as a separate study. The IPI is described as a software module that provides a simple indication of ventilation status based on physiological parameters. The V&V testing would inherently involve evaluating the IPI's calculations and output, which could be considered a form of standalone evaluation of its functionality. However, a dedicated 'standalone performance study' with specific metrics for the IPI algorithm's accuracy in isolation is not described.

7. Type of Ground Truth Used:

The document states that the IPI calculation is based on "four major parameters from the monitoring of the physiological parameters CO2 and SpO2," specifically "etCO2 and Respiration Rate (RR) which are received from the Microstream CO2 measurement module, as well as SpO2 and Pulse Rate (PR) which are received from the pulse oximetry module of the host system." This suggests that the ground truth for evaluating the IPI's calculation would be derived from the measurements of these established physiological parameters from the integrated modules. It does not mention expert consensus, pathology, or outcomes data as direct ground truth for the IPI itself, but rather the accurate processing of existing physiological data.

8. Sample Size for the Training Set:

This information is not provided in the document. The document refers to the IPI as a "software module" and its calculation, but does not describe it as a machine learning or AI model that requires a distinct training set in the conventional sense.

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

As the document does not describe a distinct training set, this information is not applicable/provided. The IPI appears to be a deterministic calculation based on established physiological parameters rather than a learned model.

Ask a specific question about this device

IntelliVue Guardian Software:
The IntelliVue Guardian Software is indicated for use by healthcare providers whenever there is a need for generation of a patient record.
The IntelliVue Guardian Software is intended for use in the collection, storage and management of data from IntelliVue Cableless Measurements and IntelliVue Patient Monitors that are connected through networks.

IntelliVue CL SpO2 Pod:
The IntelliVue CL SpO2 Pod is indicated for use by health care professionals whenever there is a need for acquisition or monitoring of physiological patient parameters Sp02 and pulse rate wirelessly.
The intended use of the IntelliVue CL SpO2 Pod when used together with a patient monitor or with a telemetry system transceiver is for monitoring, recording, and alarming of arterial oxygen saturation and pulse rate of adult and pediatric patients.
The IntelliVue CL SpO2 Pod is also intended for acquisition of arterial oxyger saturation and pulse rate data of adult and pediatric patients for a clinical information management system.
The IntelliVue CL SpO2 Pod is intended for use by health care professionals inside hospitals. It is not intended for home use. It is not a therapeutic device.

IntelliVue CL NBP Pod:
The IntelliVue CL NBP Pod is indicated for use by health care professionals whenever there is a need for acquisition or monitoring of physiological patient parameters non-invasive blood pressure and pulse rate wirelessly.
The intended use of the IntelliVue CL NBP Pod when used together with a patient monitor or with a telemetry system transceiver is for monitoring, recording, and alarming of systolic, diastvlir, and mean pressure and pulse rate of adult and pediatric, patients.
The IntelliVue CL NBP Pod is also intended for acquisition of systolic, diastolic, and mean pressure and pulse rate data of adult and pediatric patients for a clinical information management system.
The IntelliVue CL NBP Pod is intended for use by health care professionals inside hospitals. It is not intended for home use. It is not a therapeutic device.

New IntelliVue Guardian Software:
The new IntelliVue Guardian Software is a Clinical Information Management System. It collects and manages vital signs data acquired from the IntelliVue Cableless Measurements and IntelliVue patient monitors. The Guardian Software provides trending, review, reporting, notification, clinical documentation, calculations, clinical advisories including EWS deterioration status, remote viewing and operating, interfacing, storage, and printing.
The IntelliVue Guardian Software is software only product intended to be installed on a customer supplied PC or Server.

Modified IntelliVue CL SpO2 Pod:
The IntelliVue CL SpO2 Pod is a small, battery powered, wrist worn pulse oximeter device. It contains Philips FAST-Sp02 (Fourier Artifact Suppression Technology) to provide reliable saturation values under various artifact conditions including motion and low perfusion. It provides continuous cperating mode and intermittent operating mode with configurable measuring me intervals. Integrated monochrome LCD display shows measured values, measurement signal quality, battery state, and RF signal strength. It has three hardkeys for basic operation and navigation. It supports specialized Philips reusable and disposable SpO2 sensors.
The IntelliVue CL Sp02 Pod remains unchanged as it is. The modification, which is subject of this Premarket Notification, is solely limited to the labeling change in order to indicate the usage of this device together with the new Philips IntelliVue Guardian Software.

Modified IntelliVue CL NBP Pod:
The IntelliVue CL NBP Pod is a small, battery powered, noninvasive blood pressure and pulse rate measurement device. It uses oscillometric method for measuring NBP. It produces numerics for systolic, diastolic and mean blood pressure values and pulse rate. Integrated monochrome LCD Display shows measured values, battery state, and RF signal strength. It has three hardkeys for basic operation and navigation. It supports specialized Philips reusable and disposable NBP cuffs.
The IntelliVue CL NBP Pod remains unchanged as it is. The modification, which is subject of this Premarket Notification, is limited to the labeling change in order to indicate the usage of this device together with the new Philips IntelliVue Guardian Software.

The provided 510(k) summary describes the IntelliVue Guardian Software and modified IntelliVue CL SpO2 Pod and CL NBP Pod. However, it does not contain the specific details required to fully address all aspects of your request regarding acceptance criteria and a detailed study proving the device meets those criteria.

Here's an analysis based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The document broadly states that the device successfully met its specifications and performed reliably. Specific, quantifiable acceptance criteria (e.g., specific accuracy metrics for data collection, thresholds for system response times) and their corresponding reported performance values are not explicitly provided in this summary. The "performance" is described in general terms of functionality and clinical usefulness.

2. Sample Size for the Test Set and Data Provenance

The summary does not specify a sample size for any test set (e.g., number of patients, number of data points, or number of simulated scenarios).

Regarding data provenance:

• Country of Origin: Not specified.
• Retrospective/Prospective: Not specified for the performance tests, but the "Clinical Evaluation" implies prospective use in a clinical setting to assess usefulness and acceptance by users.

3. Number of Experts and Qualifications for Ground Truth

The summary mentions "clinical users" in the context of the "Clinical Evaluation" for user acceptance. However, it does not specify the number of experts, their qualifications (e.g., radiologists with X years of experience), or their role in establishing ground truth for any performance metrics. The ground truth for this device appears to be primarily related to system functionality and user acceptance, rather than a diagnostic output requiring expert consensus.

4. Adjudication Method

The summary does not mention any adjudication method (e.g., 2+1, 3+1, none) for the test set or for establishing ground truth.

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

The document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done. The device is a Clinical Information Management System and cableless measurement pods, which are generally not subject to MRMC studies in the same way an AI-powered diagnostic tool would be. The focus is on data collection, management, and display.

6. Standalone Performance Study

The summary mentions "Non-Clinical Performance Tests (bench testing)" and "Functionality testing on the new IntelliVue Guardian Software," which imply standalone or algorithm-only evaluation of the software and its components. However, it does not provide specific metrics or results from such a standalone study beyond a general statement of "confirmed static and dynamic performance... according to the specifications."

7. Type of Ground Truth Used

The "ground truth" for the various tests appears to be established as follows:

• Non-Clinical Performance Tests: Adherence to "specifications" for static and dynamic performance. This likely refers to predefined technical requirements and expected system behavior.
• Clinical Evaluation: "Clinical usefulness" and "acceptance by the clinical users." This suggests a qualitative assessment based on user feedback and observation in a clinical setting.
• Functionality Testing: Verification against expected functional behavior of the software and hardware components.

There is no mention of pathology, expert consensus on diagnostic outcomes, or long-term outcomes data as ground truth, as these would typically apply to diagnostic or prognostic devices.

8. Sample Size for the Training Set

This document describes a clinical information management system and monitoring devices. It does not explicitly mention a training set in the context of machine learning or AI. The product is not presented as an AI/ML device that requires a training set in the conventional sense. The "IntelliVue Guardian Software" is described as a "Software only product," and its features like "Early Warning Scoring capability" sound like rules-based algorithms rather than learned models.

9. How Ground Truth for the Training Set Was Established

As no training set is explicitly mentioned for an AI/ML model, the question of how its ground truth was established is not applicable based on the provided text.

Ask a specific question about this device

IntelliVue MP40, MP50, MP60, MP70, MP80, MP90 and MX800 and IntelliBridge EC10 and EC5 IC Module: Indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients.

IntelliVue TcG10 Measurement Module:

Indicated for use by health care professionals whenever there is a need to support the continuous and noninvasive monitoring of transcutaneous partial pressures of blood gas carbon dioxide and oxygen of patients not under gas anesthesia.

The modified Philips MP40, MP50, MP70, MP80, MP90, and MX800 IntelliVue Patient Monitors are a flexible and modular monitoring solution optimized for the surgical, cardiac, general medical and neonatal care environments. The monitors can be connected to the Philips Multi-Measurement Module (MMS) family with its extensions and to the IntelliVue family plug-in measurement modules. The monitors can also be connected to the IntelliVue anesthetic gas modules and to the new Intellivue TcG10 Measurement Module.

The modified Philips IntelliBridge EC10 and EC5 ID modules build an external medical device solution to collect data from external devices at the bedside providing the data to patient monitors, and patient monitoring networks. The modified EC10 and EC5 ID modules support the interface of the IntelliVue patient monitors with the new IntellVue TcG10 Measurement Module.

The new IntellVue TcG10 Measurement Module is a device for the continuous and noninvasive measurement of the transcutaneous partial pressures of blood gas carbon dioxide (pCO2) and oxygen (p02) of patients from all pediatric subgroups and of adult patients not under gas anesthesia in hospital environment. The transcutaneous measurement of pCO2 and pO2 makes use of the fact that carbon dioxide and oxygen gases are able to diffuse through body tissue and skin and can be detected by a sensor placed at the skin surface. By warming up this sensor, a local hyperemia is induced, which increases the supply of arterial blood to the dermal capillary bed below the sensor. The transcutaneous blood gas values (tcpCO2 and tcpO2) have to be interpreted primarily as the blood gas partial pressures prevailing at the level of the arterialized skin tissue. In general, this value correlates well with the corresponding arterial blood gas partial pressure.

The provided 510(k) summary (K110474) describes the Philips IntelliVue TcG10 Measurement Module and related system components. This document focuses on demonstrating substantial equivalence to predicate devices, primarily through non-clinical bench testing. It explicitly states that clinical data are not required for this type of device according to specific guidance documents.

Therefore, the information requested regarding a study proving acceptance criteria for AI performance is largely not applicable to this submission, as it concerns a medical device that measures transcutaneous blood gas pressures, not an AI-powered diagnostic or assistive tool.

However, I can extract the information that is present about performance and testing from the document.

Acceptance Criteria and Device Performance (Based on "within specifications" and "substantially equivalent"):

Study Details:

1. Sample size used for the test set and the data provenance: Not specified for a "test set" in the context of an AI study, as this refers to a medical device's performance testing. The document states "bench performance testing."

   • Data provenance: Not applicable.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for an AI test set is not relevant to this device's non-clinical performance testing.

3. Adjudication method for the test set: Not applicable.

4. 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. This device is a measurement module, not an AI-assisted diagnostic tool for human readers.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable in the context of an AI algorithm. This device is a standalone measurement module. Its performance was tested as a system comprising the measurement module and modified patient monitors/interface modules.

6. The type of ground truth used:

   • For the non-clinical performance tests: The ground truth was based on the specifications cleared for the predicate devices. This implies that measurements from the new device were compared to established engineering and performance standards expected for such devices, likely using calibrated instruments or reference methods in a laboratory setting.
   • "Pass/Fail criteria were based on the specifications cleared for the predicate devices."

7. The sample size for the training set: Not applicable. This is not an AI/machine learning device that requires a training set.

8. How the ground truth for the training set was established: Not applicable.

Additional Notes from the Document:

• Clinical Performance Tests: "Clinical data are not required in accordance to the special controls guidance document... A clinical evaluation was conducted including literature review and clinical acceptance studies with experienced nursing and physician staff." This "clinical evaluation" appears to be an assessment of user experience and acceptance rather than a clinical trial to establish diagnostic accuracy against a ground truth.
• Basis of Equivalence: The primary basis for substantial equivalence is the use of "identical functional measurement and calibration module as the predicate device" and "identical Radiometer tc Sensor 84 and the identical medical accessories." The changes are primarily software modifications for interfacing and an internal power supply.

Ask a specific question about this device

Avalon Fetal/Maternal Monitor FM20: Indicated for use by trained health care professionals whenever there is a need for monitoring of the physiological parameters uterine activity, heart rate, oxygen saturation, non-invasive blood pressure, pulse rate of pregnant women and the fetal heart rates of single fetuses, twins, and triplets in labor and delivery rooms, in antepartum testing areas, in private households and during transports in healthcare facilities.

Avalon Fetal/Maternal Monitor FM30: Indicated for use by trained health care professionals whenever there is a need for monitoring of the physiological parameters uterine activity, heart rate, ECG, oxygen saturation, non-invasive blood pressure, and pulse rate of pregnant women and the fetal heart rates of single fetuses, twins, and triplets in labor and delivery rooms, in antepartum testing areas, in private households and during transports in healthcare facilities.

Avalon Fetal/Maternal Monitor FM40: Indicated for use by trained health care professionals whenever there is a need for monitoring of the physiological parameters uterine activity, heart rate, oxygen saturation, non-invasive blood pressure, and pulse rate of pregnant women and the fetal heart rates of single fetuses, twins, and triplets in labor and delivery rooms and in antepartum testing areas.

Avalon Fetal/Maternal Monitor FM50: Indicated for use by trained health care professionals whenever there is a need for monitoring of the physiological parameters uterine activity, heart rate, ECG, oxygen saturation, non-invasive blood pressure, and pulse rate of pregnant women and the fetal heart rates of single fetuses, twins, and triplets in labor and delivery rooms and in antepartum testing areas.

The legally marketed Philips Avalon Fetal/Maternal Monitors FM20, FM30, FM40, and FM50 offer monitoring of fetal and maternal heart rates, uterine activity, maternal ECG wave, maternal non-invasive blood pressure (NIBP) and oxygen saturation (SpO2) with pulse rate, during antepartum testing and labor and delivery.

The Avalon Fetal/Maternal Monitor FM20 provides the following external measurement parameters: Up to three Fetal Heart Rates (FHR) via ultrasound (US), Fetal Movement Profile, Uterine activity via external Toco, Maternal pulse rate, Maternal Heart Rate via maternal ECG, Non-invasive blood pressure (NIBP), Pulse oximetry (maternal SpO2).

The Avalon Fetal/Maternal Monitor FM30 shares all the features and capabilities of the Avalon FM20. In addition, the Avalon FM30 provides the following external and internal measurement parameters: One Fetal Heart Rate and one fetal DECG wave via direct ECG (DECG), Uterine activity via intrauterine pressure (IUP), Maternal ECG (MECG) wave. Note: maximum three fetal heart rates can be monitored.

The Avalon Fetal/Maternal Monitor FM40 provides the following external measurement parameters: Up to three Fetal Heart Rates (FHR) via ultrasound (US), Fetal Movement Profile, Uterine activity via external Toco, Maternal Pulse Rate, Maternal Heart Rate via maternal ECG, Non-invasive blood pressure (NIBP), Pulse oximetry (maternal SpO2).

The Avalon Fetal/Maternal Monitor FM50 shares all the features and capabilities of the Avalon FM40. In addition, the Avalon FM50 provides the following external and internal measurement parameters: One Fetal Heart Rate and one fetal DECG wave via direct ECG (DECG), Uterine activity via intrauterine pressure (IUP), Maternal ECG (MECG) wave. Note: maximum three fetal heart rates can be monitored.

Device Modifications: Operation of the models FM20 (M2702A) and FM30 (M2703A) with an internal rechargeable power source (optional) to support fetal/maternal monitoring during transport within healthcare facilities. Modification of the existing Toco transducer M2734A to include maternal pulse measurement, using plethysmography at an alternative body location (abdomen). The modified transducer is labeled M2734B 'Toco MP'. Automated antepartum fetal/maternal trace interpretation and printout the resulting non-stress test (NST) report. The new software G.02.xx, which is a modification of the software F.01.xx (cleared with K102958) to support the before listed modifications / additions. Additionally, the option to equip the Avalon Fetal/Maternal Monitors with maternal SpO2 measurement is enabled now also for the model FM20 (M2702A).

This submission describes the Philips Avalon Fetal/Maternal Monitor FM20/30, FM40/50, Release G.0. The primary focus of the provided text regarding new functionalities is on the M2734B 'Toco MP' transducer, which measures maternal pulse rate via plethysmography at the abdomen, and automated antepartum fetal/maternal trace interpretation and NST report generation.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria in a table format for the modified device functionalities. Instead, it states that "Pass/Fail criteria were based on the specifications cleared for the predicate devices and test results showed substantial equivalence." For the new Toco MP transducer, the performance is reported as meeting the requirements through comparison with ECG-derived maternal heart rate.

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

• M2734B Toco MP Transducer Clinical Study: The document states, "For the clinical validation of the M2734B 'Toco MP' transducer a clinical study has been performed. The patient population was covering a variety of body mass indices (BMI) and skin colors."
  • Sample Size: The exact numerical sample size for this clinical study is not specified in the provided text.
  • Data Provenance: The country of origin is not specified. The study is described as a "clinical study," implying it was prospective, gathering new data for the validation.
• Non-clinical Testing: "Some tests included the use of previously recorded patient raw signals and traces." This suggests some retrospective data was used in the non-clinical testing phase. The origin is not specified.

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

This information is not provided in the document. The document describes clinical studies and comparative tests but does not detail the process of establishing ground truth with expert involvement for the test set, nor the number or qualifications of such experts.

4. Adjudication Method for the Test Set

This information is not provided in the document. The text mentions "compared and evaluated" for the Toco MP transducer data, but no specific adjudication method (e.g., 2+1, 3+1, none) is described.

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 MRMC study was mentioned. The device involves "automated antepartum fetal/maternal trace interpretation and printout the resulting non-stress test (NST) report." This implies an algorithmic interpretation. While the NST report might assist human readers, no study comparing human readers with and without this AI assistance, or quantifying an effect size, is described. The comparison was for the algorithm's output against a predicate algorithm (OB TraceVue G.00).

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

• Yes, a standalone performance test for the antepartum trace interpretation algorithm was done. The document states: "Comparative test of antepartum fetal/maternal trace interpretation and NST report against the implementation in OB TraceVue G.00 (K100420)." This testing evaluates the algorithm's output independently by comparing it to an existing cleared algorithm, which is a form of standalone performance evaluation against a defined standard.

7. The Type of Ground Truth Used

• For the M2734B Toco MP Transducer: The ground truth for maternal pulse rate was "ECG derived maternal heart rate (MECG)." This is a well-established and highly accurate physiological measurement, serving as a reliable reference standard.
• For the Automated Antepartum Trace Interpretation/NST Report: The ground truth was the "implementation in OB TraceVue G.00 (K100420)." This means the new algorithm's output was compared to the output of a previously cleared, predicate software. This isn't a direct "pathology" or "outcomes data" ground truth, but rather a comparative standard against a known, accepted performance of another device.

8. The Sample Size for the Training Set

• The document does not specify a training set nor its sample size. The description of modifications primarily concerns new hardware (Toco MP transducer) and software features (NST report, internal power source). While the NST report would likely involve some form of algorithmic development, no details about its training data are provided.

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

• As no training set is described, information on how its ground truth was established is not provided.

Ask a specific question about this device