Search Results

The Avalon CL Fetal & Maternal (F&M) Pod & Patch is a device indicated for use by healthcare professionals in a clinical setting for non-invasive monitoring of maternal heart rate (aHR), fetal heart rate (aFHR), and uterine activity (aToco) in women who are at >36 completed weeks, in labor, with singleton pregnancy, using surface electrodes on the maternal abdomen.

The Avalon CL Fetal & Maternal (F&M) Pod and the Avalon CL Fetal & Maternal (F&M) Patch is a beltless battery-powered maternal-fetal monitoring system that non-invasively measures abdominal fetal heart rate (aFHR), abdominal uterine activity (aToco), and abdominal maternal heart rate (aHR). The Avalon CL Fetal & Maternal (F&M) Patch is a single-use disposable adhesive electrode patch designed to be affixed to the maternal abdomen. The Avalon CL Fetal & Maternal (F&M) Pod is a reusable device which, when connected to the Avalon CL Fetal & Maternal (F&M) Patch, picks up electrical signals and converts it to Short Range Radio (SRR). The Avalon CL Fetal & Maternal Pod communicates the data measurement values to the Avalon CL Base Station using Short-Range Radio (SRR). The Avalon CL Base Station in turn relays the information to the connected Philips Fetal-Maternal (FM) Monitor (i.e., FM20, FM30, FM40, and FM50).

The provided FDA 510(k) summary for the Philips Avalon CL Fetal & Maternal (F&M) Pod & Patch focuses heavily on demonstrating substantial equivalence to a predicate device through non-clinical testing and comparison of technical characteristics rather than a detailed clinical study report with specific acceptance criteria and performance metrics for the device's accuracy in monitoring FHR, MHR, and UA.

Therefore, much of the requested information regarding "acceptance criteria and the study that proves the device meets the acceptance criteria" in terms of clinical performance (e.g., accuracy, sensitivity, specificity, agreement with ground truth for FHR, MHR, and UA) is not explicitly detailed in this document. The document primarily discusses non-clinical tests for safety, electrical performance, and biocompatibility.

However, based on the information provided, here's what can be extracted and inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table with specific clinical performance acceptance criteria (e.g., accuracy ranges for FHR) and reported device performance from an effectiveness standpoint. Instead, it details non-clinical technical acceptance criteria related to safety, electrical performance, and biocompatibility, which the device met.

Regarding MHR/FHR/UA accuracy, the document states for "Performance Bench" that "MHR/FHR/UA accuracy after stored in room (23℃), high (32℃) and low (2-8℃) temperature" were conducted and "met the acceptance criteria as defined in the test requirements." However, the specific numerical acceptance criteria for accuracy (e.g., mean absolute difference, percentage agreement, etc.) and the reported numerical performance regarding MHR/FHR/UA accuracy are not provided in this summary. This suggests that these accuracy tests were likely bench tests under controlled conditions, not a clinical trial comparing device readings to a clinical ground truth.

2. Sample Size for Test Set and Data Provenance

The document does not explicitly mention a "test set" in the context of a clinical performance study with human subjects to evaluate the accuracy of FHR, MHR, and UA measurements. The in-vivo testing mentioned under "Performance Bench" refers only to "integrity, detachment/reattachment, and performance (impedance, noise level, MHR, conductivity) after shower and usage (8 hours/32 hours) for the patch (Novii Patch)." This does not sound like a large-scale clinical accuracy study.

Therefore, based on the provided text alone:

• Sample size for the test set: Not explicitly stated for clinical performance as commonly understood for device accuracy. The "in vivo testing" details are too limited to determine sample size or its direct relation to device accuracy claims.
• Data provenance: Not explicitly stated. The type of testing suggests it might be internal company testing rather than an independent clinical trial.

3. Number of Experts and Qualifications for Ground Truth

Given the lack of a detailed clinical performance study report, there is no information provided regarding the number or qualifications of experts used to establish ground truth for a clinical test set for FHR, MHR, or UA.

4. Adjudication Method

Again, due to the absence of a detailed clinical performance study, there is no information provided on any adjudication method (e.g., 2+1, 3+1) for a clinical test set.

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

No. The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study, nor does it discuss human readers or AI assistance in this context. This device appears to be a monitoring system for physiological parameters, not an AI-assisted diagnostic imaging or interpretation tool.

6. Standalone Performance

The device itself is a "standalone" monitoring system in the sense that it performs its measurements (aHR, aFHR, aToco) via its electrodes and pod, then relays this data to a Philips Fetal-Maternal (FM) Monitor for display. The performance tests ("Performance Bench") assess the device's ability to measure these parameters. However, the exact "standalone" clinical accuracy metrics (e.g., sensitivity, specificity, accuracy vs. a gold standard) are not provided. The phrase "standalone performance" is generally associated with diagnostic algorithms, which doesn't seem to be the primary claim here.

7. Type of Ground Truth Used

For the non-clinical performance "MHR/FHR/UA accuracy after stored in room (23℃), high (32℃) and low (2-8℃) temperature," the type of ground truth used is not specified. It likely refers to controlled laboratory measurements against calibrated reference standards, rather than clinical ground truth like pathology, expert consensus, or outcomes data. For clinical performance data (which is not detailed), common ground truths for FHR, MHR, and UA would be internal fetal monitoring (IUPC for UA, fetal scalp electrode for FHR) or expert interpretation of existing monitoring tracings (though this isn't mentioned).

8. Sample Size for the Training Set

No information is provided about a "training set." This term is typically associated with machine learning or AI algorithm development. While the device uses signal processing (template matching, filtering, confidence tagging) to identify fECG and mECG complexes, the document does not describe the development or training of such algorithms or any associated data sets used for this purpose.

9. How Ground Truth for the Training Set Was Established

As no training set is discussed, there is no information provided on how ground truth for a training set was established.

In summary, the provided FDA summary focuses on demonstrating substantial equivalence through technical and non-clinical performance and safety testing. It lacks detailed clinical performance data (e.g., accuracy, sensitivity, specificity) against a clinical ground truth, specific sample sizes for clinical evaluations, or information about expert consensus or adjudication methods for such clinical data, which are typically found in clinical study reports for devices claiming diagnostic or interpretative capabilities.

Ask a specific question about this device

Intended Use:

The devices are intended to be used for monitoring and recording of, and to generate alarms for multiple physiological parameters of adults, pediatrics, and neonates.

Indications for Use:

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 only for use on one patient at a time.

The monitors are 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.

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 quide 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 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 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 Masimo rainbow SET measurement is indicated for the noninvasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate, carboxyhemoglobin saturation (SpCO), methemoglobin saturation (SpMet), total hemoglobin concentration (SpHb), and/or respiratory rate (RRac). The Masimo rainbow SET measurement is indicated for use during both no motion and motion conditions, and for patients who are well or poorly perfused.

The noninvasive Masimo O3 Regional Oximeter System and accessories are intended for use as an adjunct monitor of absolute and trended regional hemoglobin oxygen saturation of blood (rSO2) in the cerebral region under the sensors. The Masimo O3 Regional Oximeter System and accessories are indicated for use on adults ≥40 kg and on pediatrics >5 kg and

All features and technological characteristics of the primary predicate IntelliVue Patient Monitors MX750 (866471), MX850 (866470) and IntelliVue 4-Slot Module Rack FMX-4 (866468) remain unchanged and are still applicable to the IntelliVue Patient Monitors, subject of this submission.

The proposed modifications for the IntelliVue Patient Monitors MX750/MX850 and IntelliVue 4-Slot Module Rack FMX-4 include:

• 1. A new software version, designated as IntelliVue Software P.01. The new software version introduces following new features:
  • . New alarm sounds designated as "Philips 2021" sounds, based on a joint development of Philips and Sen Sound researchers who focus on transforming the experience of sound in healthcare.
  • . New Visual Patient feature, which displays patients's vital signs in an animated patient avatar alongside the conventional vital sign waveforms and numerics.
  • . configurable alarm management, limiting changes in alarm settings to pre-defined authorized personnel.

It further enhances following existing features

• Manual Selection of QRS /Pulse Tone
• Introduction of Lead Diagram for ECG
• . Enhancement of Visual Presentation for "Global Alarm Off" State

This document describes the Philips IntelliVue Patient Monitor MX750/MX850 and IntelliVue 4-Slot Module Rack FMX-4. The submission references a prior clearance (K221348) as the primary predicate device, indicating that the current submission is for modifications to an existing device.

Here's the breakdown of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state "acceptance criteria" for performance in a table format with numerical values. Instead, it details that the device passed various tests related to electrical safety, EMC, wireless coexistence, software integration, software functionality within the system, essential performance, and human factors. The acceptance criterion for each of these tests is implied to be "PASSED" against recognized consensus standards and internal requirements.

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

The document does not specify the sample sizes used for any of the tests mentioned (e.g., how many devices were tested for electrical safety, or how many users were involved in human factors testing). It also does not specify the data provenance (e.g., country of origin, retrospective or prospective) for any of these non-clinical tests.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

This information is not provided in the document. The tests described are primarily engineering and software validation tests rather than clinical studies requiring expert ground truth for interpretation. For "Human Factors," it would involve users, but their qualifications and numbers are not detailed.

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

This information is not provided. The nature of the tests (compliance with standards, software functionality) suggests that a formal adjudication method like 2+1 or 3+1 for ground truth establishment, typical in clinical studies, would not be applicable here.

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:

A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted. This device is a patient monitor with software enhancements, not an AI-assisted diagnostic tool that would typically involve human readers interpreting output.

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

The document indicates "Software Testing" was performed, which would involve testing the algorithms and functionalities of the software in a standalone manner. However, it's not a standalone diagnostic algorithm in the typical sense; it's the core operating software of the patient monitor. The new features like "new alarm sounds," "Visual Patient feature," and "configurable alarm management" were tested for their functionality and integration.

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

The "ground truth" for the tests described is primarily based on:

• Recognized consensus standards: For electrical safety (IEC 60601-1, IEC 60601-1-8, IEC 62304), EMC (IEC 60601-1-2).
• System requirements/specifications: For software integration, software functionality, and essential performance.
• Usability principles: For Human Factors testing.

There is no mention of expert consensus, pathology, or outcomes data being used as ground truth, as these are non-clinical hardware and software validation tests.

8. The sample size for the training set:

This information is not applicable as this document does not describe an AI or machine learning model that requires a training set. The changes described are software updates for existing functionalities and introduction of new display/alarm features, not the development of a predictive algorithm from data.

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

This information is not applicable for the same reason as point 8.

Ask a specific question about this device

Intended Use:

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.

Indication for Use:

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

The monitor is only for use on one patient at a time. The monitor is not a therapeutic device. Caution: 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 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 Integrated Pulmonary Index (IPI) is intended for use with adult and pediatric (1 to 12 years) patients only.

Warning: 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 Masimo rainbow SET measurement is indicated for the nonitoring of functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate, carboxyhemoglobin saturation (SpCO), methemoglobin saturation (SpMet), total hemoglobin concentration (SpHb), and/or respiratory rate (RRac). The Masimo rainbow SET measurement is indicated for use during both no motion and motion conditions, and for patients who are well or poorly perfused.

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 the hospital environment. It is not intended for home use.

Warning: The monitor is not intended for use in an MRI environment or in an oxygen-enriched environment (for example, hyperbaric chambers).

Contraindications: There are no known contraindications for the IntelliVue MX100/X3 Patient Monitor/Multi-Measurement Module.

The Multi-Measurement Module X3 and the IntelliVue Patient Monitor MX10
0, 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 devices offer a monitoring solution optimized for the surgical, cardiac, medical and neonatal care environments. They can be located in the patient vicinity at the bedside or can be used mobile, during patient transport inside hospitals. The X3 and MX100 can interact with the Central Station via LAN or wireless link.

The Multi-Measurement Module X3 and IntelliVue Patient Monitor MX100 are compact, rugged, lightweight monitors with built-in invasive and non-invasive measurements, namely ECG (including arrhythmia and ST), respiration, SpO2, NBP, dual invasive pressure, temperature, and CO2. It can further extend the measurement capabilities when connecting to the legally marketed IntelliVue Multi-Measurement Extensions

The X3 can be used in two ways: as a multi-measurement module for the Philips IntelliVue family of patient monitors and as a stand-alone monitor.

The provided document, an FDA 510(k) summary for the Philips IntelliVue Patient Monitor MX100 and IntelliVue Multi-Measurement Module X3, describes a device that has undergone technical modifications, primarily software updates, rather than being a novel AI-powered diagnostic or assistive tool.

Therefore, the document does not contain the information requested regarding acceptance criteria for an AI-powered diagnostic device, a study proving it meets those criteria, sample sizes for test and training sets, expert usage for ground truth, adjudication methods, MRMC studies, or standalone algorithm performance.

The document focuses on demonstrating substantial equivalence to a predicate device, as per FDA 510(k) requirements. This typically involves showing that the device has the same intended use, similar technological characteristics, and that any differences do not raise new questions of safety or effectiveness.

Here's why the requested information is absent and what is discussed:

1. Acceptance Criteria for AI Performance and Reported Performance: Not applicable as this is not an AI diagnostic device. The acceptance criteria mentioned are related to compliance with general medical device safety and performance standards (e.g., electrical safety, EMC, software lifecycle, usability, alarm systems).
2. Sample Sizes and Data Provenance: Not applicable for AI model testing. The document states "No new issues of safety or effectiveness as compared to the predicate are introduced because of using this device," indicating that the focus was on validating the software changes within the existing framework of a patient monitor, not on an AI algorithm's diagnostic performance on a specific dataset. There is no mention of a "test set" in the context of AI performance.
3. Number of Experts and Qualifications: Not applicable. Ground truth establishment for AI models is not relevant to this submission.
4. Adjudication Method: Not applicable.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: Not applicable. The device is a patient monitor, not an AI-assisted diagnostic tool that would improve human reader performance.
6. Standalone Algorithm Performance: Not applicable. There is no standalone AI algorithm being assessed.
7. Type of Ground Truth: Not applicable in the context of AI. The "ground truth" for this device would be the accurate measurement of physiological parameters (e.g., ECG, SpO2, NBP), which is assessed through bench testing and compliance with recognized standards, not "expert consensus" or "pathology" in the AI sense.
8. Sample Size for Training Set: Not applicable. There is no AI model training described.
9. How Ground Truth for Training Set Was Established: Not applicable.

What the document does demonstrate (in lieu of AI performance data):

The document primarily focuses on software changes and the continued compliance with established medical device standards to prove substantial equivalence:

• Software Changes: The key difference from the predicate device is a new software version (P.01) introducing new alarm sounds, configurable alarm management, enhancing Early Warning Score Validation, additional SpO2 fallback configuration, additional Lead Diagram presentation for ECG, and enhancement of the global "alarm off" state.
• Non-Clinical Bench Tests and Harmonized Standards: The device has passed safety tests demonstrating compliance with recognized standards like ANSI AAMI ES60601-1 (general safety), IEC 60601-1-2 (EMC), IEC 60601-1-6 (Usability), IEC 60601-1-8 (Alarm Systems), and IEC 62304 (Medical device software lifecycle).
• No Clinical Studies: The submission explicitly states, "The subject devices, like the primary predicate devices, did not require clinical trials." This further indicates that the changes were not considered to introduce new safety or effectiveness concerns requiring human subject data for validation.
• Substantial Equivalence: The conclusion is that the modified devices "do not raise different questions of safety and effectiveness when compared to the predicate, perform as intended, and have performance characteristics that are substantially equivalent to the predicate devices."

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 only for use on one patient at a time.

The monitors are 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.

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 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 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 Intelli Vue 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 Masimo rainbow SET measurement is indicated for the nonitoring of functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate, carboxyhemoglobin saturation (SpCO), methemoglobin saturation (SpMet), total hemoglobin concentration (SpHb), and/or respiratory rate (RRac). The Masimo rainbow SET measurement is indicated for use during both no motion and motion conditions, and for patients who are well or poorly perfused.

The noninvasive Masimo O3 Regional Oximeter System and accessories are intended for use as an adjunct monitor of absolute and trended regional hemoglobin oxygen saturation of blood (rSO2) in the cerebral region under the sensors. The Masimo O3 Regional Oximeter System and accessories are indicated for use on adults ≥40 kg and on pediatrics ≥5 kg and

The IntelliVue Patient Monitors MX400, MX450, MX500 and MX550 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 non-invasive blood pressure, temperature, CO2, tcpO2/ tcpCO2, C.O., CCO, intravascular SO2, SvO2, ScvO2, 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 at the patient bedside vicinity and can also be used during patient transport inside hospitals. The monitors have a color display with touchscreen 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.

This document is a 510(k) Summary for the Philips IntelliVue Patient Monitor MX400, MX450, MX500, and MX550. It does not describe a study involving an AI/algorithm that requires detailed acceptance criteria, ground truth establishment, or specific human reader studies as typically seen for AI-enabled medical devices. Instead, this submission focuses on demonstrating substantial equivalence to a predicate device, primarily due to software and hardware modifications allowing integration with external measurement devices like the Masimo SedLine Sedation Monitor.

Therefore, many of the requested points, particularly those related to AI/algorithm performance studies (e.g., sample size for test set/training set, expert adjudication, MRMC studies, standalone performance, specific effect sizes), are not applicable to this type of 510(k) submission.

However, I can extract information related to the overall device performance and testing as described in the document.

Here's an analysis of the provided text in relation to your request, with an emphasis on what is and is not present:

Device: IntelliVue Patient Monitor MX400, MX450, MX500, MX550

Study Type: This is a 510(k) premarket notification primarily demonstrating substantial equivalence (predicate pathway) for modifications to an existing patient monitor, specifically related to software updates and integration of an external monitoring module (Masimo SedLine Sedation Monitor). It is not a de novo submission for a new AI/algorithm.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present a table of specific quantitative acceptance criteria for an AI/algorithm's performance (e.g., accuracy, sensitivity, specificity metrics) nor does it provide a "reported device performance" table in that context.

Instead, the "acceptance criteria" can be inferred from the non-clinical tests performed to demonstrate compliance with recognized standards for medical electrical equipment. The "reported device performance" is that the device "passed all safety tests" and "perform as intended."

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

• Test Set Sample Size: Not applicable/not specified for an AI/algorithm test set. The testing described is primarily for system-level safety, performance, and software validation.
• Data Provenance: Not applicable in the context of an AI/algorithm dataset. The document discusses compliance with various electrical, safety, software, and usability standards for the device itself.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable. Ground truth establishment by experts is typically for diagnostic AI/imaging algorithms. This submission is for a patient monitor system.

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

Not applicable. Adjudication methods are relevant for expert review of images or clinical data for AI algorithm validation.

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 device is a patient monitor, not an AI-assisted diagnostic tool that would typically undergo MRMC studies to evaluate human reader performance with or without AI assistance.

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

Not applicable. This is not an AI/algorithm in the sense of a diagnostic or predictive model being evaluated in standalone mode. It's a medical device system. While it has "software," the performance evaluation is centered on its functionality as a patient monitor and its compliance with relevant standards.

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

Not applicable. The "ground truth" for this device's performance validation is its ability to correctly acquire, display, and alert on physiological parameters according to established benchmarks and safety standards (e.g., AAMI EC11 for ECG, IEC standards for electrical safety). It's not a diagnostic AI's ground truth based on clinical diagnoses or pathological findings.

8. The sample size for the training set

Not applicable. This is not an AI/ML model generated from a training set in the typical sense of deep learning or machine learning algorithms.

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

Not applicable. (See #8)

Summary of what the document does discuss regarding validation and performance:

The document emphasizes non-clinical bench tests and compliance with harmonized standards (e.g., IEC 62304 for software, ANSI AAMI ES60601-1 for basic safety, IEC 60601-1-8 for alarms, IEC 60601-1-6 for usability). The "performance data" section primarily lists these standards and states that the devices "passed all safety tests."

Key statements from the document regarding performance:

• "The subject devices have passed all safety tests for demonstrated compliance with the recognized standards below." (See table in section 1.8 Performance Data)
• "No new issues of substantial equivalence are introduced because of using this device." (Section "Non-clinical Bench Tests")
• "The subject devices, like the primary predicate devices, did not require clinical trials. Any clinical studies performed for the Masimo SedLine parameter are still valid as the measurements are not modified; they are only being connected to an additional host patient monitor." (Section "Clinical Studies")
• "Compliance to the FDA Quality System Regulations, FDA recognized standards, FDA guidance documents, harmonized standards, verification and validation, software validation, usability validation, and risk management activities have taken place for the subject devices." (Section "Clinical Studies")
• "The results of the substantial equivalence assessment, taken together with non-clinical bench testing, electrical safety and electromagnetic compatibility, software verification and validation, human factors, usability and interoperability testing, demonstrate that the modified devices do not raise different questions of safety and effectiveness when compared to the predicate, perform as intended, and have performance characteristics that are substantially equivalent to the predicate devices." (Section 1.9 CONCLUSIONS)

In conclusion, this 510(k) submission for the Philips IntelliVue Patient Monitor MX series primarily relies on demonstrating compliance with recognized electrical safety, performance, and software development standards, along with a comparison to predicate devices, rather than an AI/algorithm performance study with specific metrics, expert adjudication, or MRMC studies.

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 only for use on one patient at a time. They are not intended for use in transport situations. 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.

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 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 Masimo rainbow SET measurement is indicated for the noninvasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate, carboxyhemoglobin saturation (SpCO), methemoglobin saturation (SpMet), total hemoglobin concentration (SpHb), and/or respiratory rate (RRac). The Masimo rainbow SET measurement is indicated for use during both no motion and motion conditions, and for patients who are well or poorly perfused.

The 4-Slot Module rack FMX-4 is intended to connect up to four particular plug-in physiological measurement modules to the dedicated host patient monitors.

The IntelliVue Patient Monitors MX750 and MX850 acquire multiple physiological patient signals, display measurement values, waves and trends, generate physiological and technical alarms, provide data recording and support patient data management. They operate with the external Measurement Modules and the IntelliVue 4-Slot Module Rack FMX-4, which establishes the connection between the individual plug-in measurement modules and the MX750 and MX850 monitors.

The monitors support multiple non-invasive and invasive measurements such as ECG, arrhythmia, ST, QT, SpO2, respiration rate, pulse rate, invasive and non-invasive blood pressure, temperature, CO2, tcpO2/ tcpCO2, C.O., CCO, intravascular SO2, Sv02, ScvO2, 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. These devices have a color display with a touch-screen as a primary input device. They also support keyboard and pointing devices such as a mouse.

The monitor models MX750 and MX850 differ mainly in size. Whilst MX750 has a 19" flat panel display, MX850 has a 22" display.

The hardware of the new 4-Slot Module Rack FMX-4 is very similar to that of its 8 years old predicate 4-Slot Module Rack FMS-4. The new FMX-4 has the same housing, which is made of the same material as FMS-4 but has a slightly different shade of color (same shade of color as the new MX750 and MX850 monitors). The FMX-4 has a new Printed Circuit Assembly with standard hardware components like CPU and memory being replaced by state of the art electronic components.

The software modifications comprise the following changes:

• Support of the new state-of-the-art electronic components.
• Modified elements of the Graphical User Interface.
• Implementation of a feature called Electronic Strip Recording. This feature allows electronic strips that can be reviewed on the monitor and printed out as a report on the printer.
• Modification of the existing feature Remote Applications to support HTML5 and PDF format.

This document is a 510(k) summary for the Philips IntelliVue Patient Monitors MX750 and MX850 and the IntelliVue 4-Slot Module Rack FMX-4. It states that these devices are substantially equivalent to previously cleared predicate devices (Philips IntelliVue Patient Monitor MX800 and Philips IntelliVue 4-Slot Module Rack FMS-4). The submission primarily focuses on hardware and software modifications to existing devices.

The information provided does not detail specific acceptance criteria and device performance in the format of a table with numerical values for metrics like sensitivity, specificity, or accuracy, as would be common for an AI/ML device study. Instead, it describes compliance with recognized consensus standards and general V&V activities. This is likely because the device is a patient monitor, and the modifications are primarily hardware updates and minor software changes to support the new hardware and improve existing functionalities, not a new AI/ML algorithm requiring extensive clinical performance validation against a pre-defined ground truth for diagnostic accuracy.

Therefore, many of the requested items (e.g., sample size for test set, number of experts for ground truth, adjudication method, MRMC comparative effectiveness study, standalone performance) are not explicitly addressed in the provided text as they pertain more to novel diagnostic or AI algorithms rather than general patient monitoring device updates.

I can, however, extract information about the types of tests conducted and general statements about meeting requirements.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table with specific numerical acceptance criteria and corresponding device performance metrics (e.g., sensitivity, specificity, AUC) for the various physiological parameters monitored by the device. Instead, it states that "Test methods and acceptance criteria were the same as those for the predicate devices and test results showed substantial equivalence with respect to safety and effectiveness."

The V&V activities focused on compliance with various international standards:

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

The document does not specify a "test set" in terms of subject count or data record count for performance evaluation in the context of, for example, diagnostic algorithm accuracy. The studies described are primarily engineering validation and verification tests against established standards. Therefore, information regarding data provenance (e.g., country of origin, retrospective/prospective) is not provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

As there is no "test set" described for a diagnostic algorithm, this information is not applicable and not provided in the document. The human factors engineering testing involved "focus groups" and "expert reviews," but the number and qualifications of these experts are not specified, nor were they establishing ground truth for a diagnostic outcome.

4. Adjudication method for the test set

Not applicable, as no dedicated "test set" requiring adjudication for ground truth of a diagnostic outcome is described.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done

No MRMC comparative effectiveness study is mentioned. The device is a patient monitor, and the submission concerns updates to an existing monitoring platform, not a new AI diagnostic aid that would typically warrant such a study.

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

This concept is less applicable to a patient monitoring device update. The performance evaluation focuses on the device's ability to accurately measure and display physiological parameters and generate alarms in compliance with safety and performance standards, rather than an autonomous diagnostic algorithm. The document states the monitors are "for use by trained healthcare professionals."

7. The type of ground truth used

For the various measurement parameters (ECG, SpO2, etc.), the "ground truth" implicitly aligns with the accuracy and performance specifications outlined in the referenced standards (e.g., AAMI EC11 for ECG, ISO 80601-2-61 for pulse oximetry). These standards define acceptable deviations from known physical or simulated physiological signals. The document does not describe the establishment of ground truth in the context of expert consensus, pathology, or outcomes data, as would be relevant for a diagnostic AI algorithm.

8. The sample size for the training set

This information is not provided. The document primarily describes hardware and software updates to an existing system, rather than the development and training of a new AI/ML algorithm.

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

Not applicable, as the document does not describe the development or training of a new AI/ML algorithm.

Ask a specific question about this device

The IntelliVue GuardianSoftware is intended for use by healthcare providers whenever there is a need for generation of a patient record.

The IntelliVue GuardianSoftware is indicated for use in the collection, storage and management of data from Philips specified measurements, Philips Patient Monitors and qualified 3rd party measurements that are connected through networks.

The IntelliVue GuardianSoftware is a stand-alone 'Clinical Information Management System (CIMS)' software application with client-server architecture and designed to be used in professional healthcare facilities (i.e. hospitals, nursing homes) and is intended to be installed on a 'customer-supplied', compatible off-the-shelf (OTS) information technology (IT) equipment.

The IntelliVue GuardianSoftware is a documentation, charting, and decision-support software that is configurable by the hospital to suit the needs of individual clinical units. The device collects data/vital signs from the following Philips compatible patient monitor/measuring devices.

Using the collected data, the device provides trending, review, reporting and notification. The 'Guardian Early Warning Score (EWS)' application is integrated into the IntelliVue GuardianSoftware to provide the healthcare professional/provider basic assessment and the ability to recognize early signs of deterioration in patients.

The IntelliVue GuardianSoftware is not an alarming device and displays alarms from patient monitors as supplemental information only.

Here's an analysis of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not contain specific quantitative acceptance criteria or a side-by-side performance comparison of the new device versus these criteria. Instead, the document focuses on demonstrating substantial equivalence to a predicate device. The acceptance is implied by the successful software verification and validation, as well as human factors testing, which collectively show the device "met all safety and reliability requirements and performance claims."

The closest we get to "performance" in the context of the comparison is in the "Substantial Equivalence Determination" column, which consistently states "IDENTICAL" or provides explanations for differences that do not affect substantial equivalence.

Key areas assessed for equivalence (and thus, implicit "performance" against the predicate):

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. The evaluation relies on:

• Software Verification and Validation Testing: This is typically performed on software builds and simulated environments, not directly on patient data.
• Human Factors and Usability Testing: This involves human users interacting with the device. The sample size for this specific testing is not mentioned.
• Data Provenance: Not applicable in the context of patient data testing, as no patient data was used for performance evaluation of the software itself.

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 evaluation focused on software verification/validation and human factors/usability, and not on clinical performance with patient data requiring expert ground truth, this type of detail is absent.

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

No adjudication method is mentioned, as there was no test set requiring expert adjudication for clinical ground truth.

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 comparative effectiveness study was conducted or mentioned. The device is a "Clinical Information Management System" and not an AI-assisted diagnostic tool for human readers. It collects, stores, and manages data, and provides decision support (e.g., Early Warning Score), but it doesn't appear to directly assist human readers in interpreting medical images or other complex data where "improvement" with AI would be measured.

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

The device is inherently a "Clinical Information Management System (CIMS) software application" that operates in a standalone manner as software. However, its function as data collection, storage, management, and providing decision support (like EWS) means it is intended for use by healthcare providers and is integrated into clinical workflows. The performance testing focuses on its software functionality, reliability, and human factors, rather than a diagnostic algorithm's standalone performance. The "Guardian Early Warning Score (EWS)" is an algorithm, and its performance would be assessed for accuracy in calculating scores, but the document doesn't provide details on its standalone performance metrics.

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

For the software verification and validation, the "ground truth" would be the expected functional behavior and output of the software as defined by its requirements and specifications. For human factors testing, the ground truth would be the expected safe and effective interaction of users with the device. There isn't an external clinical ground truth (like pathology or outcomes) applied to the software's performance itself in this submission.

8. The sample size for the training set:

Not applicable. This is not an AI/machine learning model where a specific training set (of patient data) would be used. The software is developed based on engineering principles and regulatory requirements.

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

Not applicable, as there is no training set for an AI/machine learning model.

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 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 transcutaneous gas measurement (tcGas) with the M1018A plug-in module 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 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 Masimo rainbow SET measurement is indicated for the noninvasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate, carboxyhemoglobin saturation (SpCO), methemoglobin saturation (SpMet), total hemoglobin concentration (SpHb), and/or respiratory rate (RRac). The Masimo rainbow SET measurement is indicated for use during both no motion and motion conditions, and for patients who are well or poorly perfused.

The noninvasive Masimo O3 Regional Oximeter System and accessories are intended for use as an adjunct monitor of absolute and trended regional hemoglobin oxygen saturation of blood (rSO2) in the cerebral region under the sensors. The Masimo O3 Regional Oximeter System and accessories are indicated for use on adults ≥40 kg and on pediatrics ≥5 kg and

The IntelliVue Patient Monitors MX500 and MX550 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, invasive and noninvasive blood pressure, temperature, CO2, tcpO2/ tcpCO2, C.O., CCO, intravascular SO2, SvO2, ScvO2, 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 at the patient bedside vicinity and can also be used during patient transport inside hospitals.

The monitors have a color display with touchscreen 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.

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

This submission is a 510(k) for modifications to an existing device, the IntelliVue Patient Monitors MX500 and MX550. The acceptance criteria and supporting studies primarily focus on demonstrating that the modifications do not introduce new questions of safety or effectiveness and that the modified device remains substantially equivalent to the predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is an update to an existing device focusing on integrating new measurement modules (Masimo O3, IRMA CO2, ISA CO2) and updating EMC standards, the "acceptance criteria" are primarily related to meeting established performance standards for patient monitors and demonstrating that the new modules function as intended without compromising the overall device safety or efficacy. The document doesn't present specific numerical acceptance criteria for all physiological parameters of the overall monitor, but rather confirms compliance with recognized standards.

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 unit 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 Masimo rainbow SET measurement is indicated for the noninvasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate, carboxyhemoglobin saturation (SpCO), methemoglobin saturation (SpMet), total hemoglobin concentration (SpHb), and/or respiratory rate (RRac). The Masimo rainbow SET measurement is indicated for use during both no motion and motion conditions, and for patients who are well or poorly perfused.

The transcutaneous gas measurement (tcGas) with the M1018A plug-in module 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 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 MP5, MP5SC, MX100, MX400, MX430, MX450, MX500, MX550, MX700, MX800 and IntelliVue Multi-Measurement Module X3 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, ScvO2, 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 further local input devices such as specialized remote control, keyboard, and 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.

With the current software Rev. N.0 the following modifications have been introduced:

• Implementation of the existing feature Alarm Advisor into the IntelliVue Patient Monitor MX100 and Multi-Measurement Module X3. Alarm Advisor provides feedback on recurring and continuous alarm limit violations based on configured criteria. The information provided by the Alarm Advisor supports device operator in adapting alarm limits more specifically. This is the same functionality as that in other IntelliVue Patient Monitors: MP5, MP5SC, MX400, MX430, MX450, MX500, MX550, MX700, and MX800 (cleared with K161531).
• Modification of a few specific elements of the Graphical User Interface (GUI) of the IntelliVue Patient Monitors MP5, MP5SC, MX100, MX400, MX430, MX450, MX500, MX550, MX700, MX800, and the Intelli Vue Multi-Measurement Module X3:
  • The key 'Silence' has been renamed to 'Acknowledge',
  • A new default configuration for the Pause/Switch off of alarms via 'Acknowledge' key combined with a specific pop-up window has been added to all monitor models,
  • New default configurations of visual alarm indicators with other colors and flashing behavior of the alarm numerics and limits have been added.

The provided document is a 510(k) premarket notification from Philips Medizin Systeme Boeblingen GmbH to the FDA for their IntelliVue Patient Monitors. This document primarily focuses on demonstrating substantial equivalence to previously cleared predicate devices and addressing minor software modifications, specifically the implementation of an "Alarm Advisor" feature and GUI changes related to alarm management.

The document does not contain the specific details required to answer all parts of your request, particularly regarding clinical performance studies with specific acceptance criteria, sample sizes for test and training sets, expert consensus, or MRMC studies for an AI device. This is because the submission is for a patient monitor and its software updates, not an AI-powered diagnostic device in the sense that would require such extensive clinical validation to demonstrate improved human reader performance or standalone algorithm performance.

However, I can extract information related to the acceptance criteria and study proving the device meets its acceptance criteria, based on the scope of this type of submission.

Here's an analysis based on the provided text, while acknowledging the limitations for a full AI device performance study:

Acceptance Criteria and Device Performance (as evident from this 510(k) submission):

For this type of device (patient monitors with software updates), the "acceptance criteria" and "device performance" are primarily demonstrated through compliance with recognized standards, hazard analysis, and functional/regression testing rather than a clinical trial with a defined performance metric like sensitivity/specificity for a diagnostic AI.

Study Details (based on the provided document):

Given that this is a 510(k) for patient monitors with minor software updates, the "study" is primarily a series of verification and validation (V&V) activities focused on engineering and software aspects, rather than a clinical trial for an AI diagnostic.

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

   • The document does not specify a "test set" in the context of a dataset for an AI model. Instead, it refers to V&V activities that include:
     • Hazard Analysis Testing: "All specified pass/fail criteria have been met." (No specific sample size of incidents/scenarios mentioned, typically an engineering analysis).
     • Functional System Level Tests: Performed on a variety of monitor models (MP5, MP5SC, MX100, MX400, MX430, MX450, MX500, MX550, MX700, MX800, Multi-Measurement Module X3) for the new features (Alarm Advisor, blinking numerics, Alarm Acknowledge, Pause/Switch off Alarms). No specific number of test cases or "patients" is provided.
     • Regression Tests: Performed on the same range of monitor models to ensure unchanged functions still work.
   • Data Provenance: Not applicable in the context of clinical data for AI model evaluation. The tests are performed on the device itself and its software.

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

   • Not described as "ground truth" establishment in this context. For usability testing, it mentions "expert reviews" as part of formative evaluations, but the specific number and qualifications of these experts are not detailed. These would typically be human factors engineers, clinical specialists, or design experts.

3. Adjudication Method for the Test Set:

   • Not applicable as there is no "test set" of clinical cases requiring adjudication. The V&V activities are based on engineering specifications and standard compliance.

4. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done:

   • No. An MRMC study is relevant for diagnostic imaging AI systems where human readers interpret medical images with and without AI assistance. This submission is for patient monitors and their alarm management and GUI features, which do not involve diagnostic interpretation in that manner. The "Alarm Advisor" provides feedback on alarm limit violations, which is a clinical decision support tool related to device settings, not an image interpretation aid.

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

   • Yes, to an extent, in the sense that the new software features were functionally tested independently of human interaction (e.g., "Functional tests... All tests have been passed"). The "Alarm Advisor" functionality and GUI changes needed to perform as specified by the algorithm/software design. However, this is not a "standalone performance study" in the context of an AI diagnostic that might output a diagnosis or risk score. It's more about verifying software logic and output.

6. The Type of Ground Truth Used:

   • Engineering Specifications and Standards Compliance. For the new features and existing functionalities, the "ground truth" is whether the software performs according to its design specifications, established industry standards (e.g., IEC 60601-1-8 for alarms), and internal quality requirements. For usability, "user feedback" (from focus groups, usability tests) serves as the basis for improvement.

7. The Sample Size for the Training Set:

   • Not applicable. This device is not an AI model that undergoes a "training phase" from a clinical dataset in the traditional machine learning sense. The software development process involves design, coding, and V&V activities.

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

   • Not applicable for the same reason as above.

Ask a specific question about this device

The Early Vue VS30 is intended to measure, display, alarm and, record physiological information of adult, pediatric and neonatal patients in hospitals and in out-of-hospital patient care is administered by a healthcare professional (such as clinics, outpatient surgery facilities, long-term care facilities, and physician offices). It is not intended for use in mobile settings such as ambulances and aircraft. Clinical users may use the monitor during patient transport within a healthcare facility.

The intended use of measurement parameters for each patient type is shown in table below (Parameter (patient types)): Non-invasive BP--NBP (Adult, Pediatric, Neonatal); SpO2 --Masimo rainbow SET or Philips FAST (Adult, Pediatric, Neonatal); Pulse Rate -- PR -- derived from SpO2 or NBP (Adult, Pediatric, Neonatal); Temperature-Predictive, Temporal (Adult, Pediatric, Neonatal); end tidal CO2--etCO2 (Adult, Pediatric, Neonatal); Respiration Rate: airway respiration--awRR (Adult, Pediatric, Neonatal); Respiration Rate: acoustic respiration--RRa (Adult, Pediatric);

Non-invasive Total Hemoglobin--SpHb (Adult, Pediatric)

Contra-indications: Not for transport outside the healthcare facility. Not for use in home setting.

The subject device EarlyVue VS30 is a platform redesigned from the predicate device Suresign VS4 to provide the measurement of the same physiological parameters. It is a multi-parameter compact, portable monitor, offering several configurations and optional features that are intended to meet the customer's needs. The VS30 is designed with a simple, intuitive user interface for ease of operation. It is used to measure or monitor NBP, SpO2, SpHb, RRa, CO2 and optional temperature primarily in non-acute settings.

The subject VS30 also provides the wireless option. The wireless functions for VS30 are for the monitors to communicate with the hospital EMR system or to communicate with Philips IGS software over the hospital's wireless infrastructure.

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

Device: EarlyVue VS30 Vital Signs Monitor

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the EarlyVue VS30 are implied by its comparison to the predicate device, Philips SureSigns VS4. The document asserts that the VS30 has the "same fundamental technological characteristics" and that "performance data demonstrates the subject device Early Vue VS30 is as safe and effective as the predicate device for all the measurements." Therefore, the predicate device's specifications serve as the de facto acceptance criteria for each measurement parameter.

Ask a specific question about this device

The Intelli Vue XDS Software is intended for use as an additional, independent display for viewing screens, generated by specified network-connected Philips patient monitors. The IntelliVue XDS Software alone is not intended for remotely monitoring patients without caregivers in vicinity (unattended patients).

It is indicated for local and remote operation of these Philips patient monitors. It is indicated for printing reports as generated by these Philips patient monitors. It is indicated to be used by trained healthcare professionals.

Rx Only: Caution, U.S. Federal Law restricts this device to sale by or on the order of a physician.

The IntelliVue XDS Software (867019) is a bedside information system. The IntelliVue XDS Software provides network services, printing services, patient monitor remote display services, launch pad services, input device sharing services and XDS database services.

The IntelliVue XDS Software can be connected to one or more specified Philips patient monitors and allows the remote viewing of the patient monitor generated data. Depending on the configuration, the remote operation of the network-connected patient monitor with standard off-the shelf information technology equipment input devices (touch screen, keyboard, and mouse) is also supported.

The IntelliVue XDS software does not modify or alter the Philips specified patient monitor. nor does it generate any data on its own. It is solely displaying the patient monitor generated data. It also displays the current alarm and INOP states for the patient, but does not provide an auditory alarm signal announciation function. The IntelliVue XDS Software is not a primary monitoring or alarming device.

The IntelliVue XDS Software is a software only product. It is intended to be installed on customer supplied compatible off-the shelf information technology equipment that meet the technical requirements as specified by Philips.

The provided text describes a 510(k) submission for the Philips IntelliVue XDS Software. It focuses on the substantial equivalence of the modified software (Rev. M.1) to a previously cleared version. However, it does not contain the detailed acceptance criteria and a specific study proving the device meets those criteria, as typically found in a clinical study report.

Here's an analysis based on the information provided, highlighting what is present and what is missing, and making inferences where possible:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table of acceptance criteria with corresponding performance metrics. It generally states:

• "Pass/Fail criteria were based on the specifications cleared for the predicate device and all test results showed substantial equivalence."
• "The results demonstrate that the Philips IntelliVue XDS Software (SW Rev.M.1) meets all safety and reliability requirements and performance claims."

This indicates that the acceptance criteria were likely related to maintaining the functionality, safety, and reliability of the predicate device. Specific performance metrics (e.g., accuracy, latency, resolution) are not detailed.

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

The document states:

• "Testing involved software testing on integration level (functional testing and regression testing) and software testing on system level (hazard analysis testing and dedicated software performance testing)."

This refers to software engineering testing rather than a clinical study with a "test set" of patient data. Therefore, the concept of sample size for a test set of patient data and data provenance (country of origin, retrospective/prospective) is not applicable to the type of testing described. The testing focused on the software itself rather than its performance on a dataset of patient cases.

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

As the testing described is not a clinical study on patient data but rather software verification and validation, there is no mention of experts establishing ground truth for a test set in the context of medical image or signal interpretation.

4. Adjudication Method

Given the nature of the testing described (software verification and validation), an adjudication method (like 2+1 or 3+1) for a test set is not applicable.

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

An MRMC study compares human reader performance with and without AI assistance. The provided document describes software that acts as an "additional, independent display" and allows "remote operation" of patient monitors. It explicitly states:

• "The IntelliVue XDS Software alone is not intended for remotely monitoring patients without caregivers in vicinity (unattended patients)."
• "The IntelliVue XDS Software is not a primary monitoring or alarming device."

This indicates the device is an accessory display/control system, not an AI interpreting data or aiding human readers in diagnosis. Therefore, an MRMC comparative effectiveness study is not applicable and was not performed.

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

The described device is software that displays and allows remote operation of patient monitor data. It "does not modify or alter the Philips specified patient monitor, nor does it generate any data on its own." It "solely displays the patient monitor generated data."

While software verification and validation were performed on the algorithm itself, this is not a "standalone performance study" in the sense of an AI algorithm producing diagnostic outputs without human intervention. The software's function is to mirror existing monitor data and enable control, not to independently interpret or diagnose.

7. Type of Ground Truth Used

For the software verification and validation, the "ground truth" would be the expected functional behavior and performance defined by the software's specifications and the predicate device's characteristics. It is not based on expert consensus, pathology, or outcomes data related to patient conditions.

8. Sample Size for the Training Set

The document pertains to the verification and validation of a software application for displaying and interacting with patient monitor data, not an AI/ML algorithm that is "trained" on a dataset. Therefore, there is no concept of a "training set" as understood in AI/ML, and thus no sample size for a training set is provided or applicable.

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

As there is no training set for an AI/ML algorithm, this question is not applicable.

Summary of what is present and missing:

• Acceptance Criteria/Performance: General statements about meeting safety, reliability, and performance claims, and substantial equivalence to the predicate device. Specific quantitative criteria are not provided.
• Study Details (Test Set, Experts, Adjudication, MRMC, Standalone, Ground Truth): Not applicable or not performed in the context of a clinical study or AI performance evaluation, as the device is a display/control software, not an AI diagnostic tool.
• Training Set: Not applicable, as the device is not an AI/ML algorithm that requires training.

The provided document describes a software verification and validation process to ensure the new software version maintains the same functionality, safety, and performance as its predicate, rather than a clinical study to establish new performance claims against a defined ground truth for medical interpretation.

Ask a specific question about this device