Search Results

The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-Lead ECG, heart rate, respiratory rate, pulse rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure (NIBP) continuously, and patient posture and activity. VMS allows for the input of non-invasive blood pressure and body temperature and can display data from peripheral devices. VMS can generate alerts when rate-based cardiac arrhythmias are detected and when physiological vital signs fall outside of selected parameters.

The non-invasive Blood Pressure Tracking feature is based on Pulse Arrival Time (PAT), which is obtained utilizing ECG and PPG signals following a calibration process using an FDA-cleared oscillometric blood pressure monitor. This feature is not intended for use in critical care environment.

The Vios Central Station Monitor (CSM) and Central Server (CS) Software (SW) is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSM SW and CS SW receives, stores, manages, and displays patient physiological and waveform data and alarms generated by Vios proprietary patient vitals monitoring software.

The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals.

The VMS includes a proprietary monitoring software, Chest Sensor, Finger Adapter and Central Server and Central Monitoring Station.

The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices.

The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile multiple use, and rechargeable sensor that acquires 3-channel ECG, bioimpedance, 2-channel pulse oximetry, and tri-axial accelerometer data. The sensor contains signal acquisition firmware (embedded software) and wirelessly communicates acquired data via standard communication protocols (Bluetooth™) to the BSM SW for analysis and display. The Chest Sensor has a button that, when pressed, sends a patient call alert to the BSM SW.

VMS Chest Sensor Adapter Models L2050F (Pulse Ox Finger Adapter) are plastic, non-sterile, patient-worn, multiple use pulse oxygenation sensors that connect to the Vios Chest Sensor and are secured to the patient via medical grade ECG electrodes.

The provided text describes a 510(k) clearance for the Vios Monitoring System Model 2050, focusing on the addition of a blood pressure tracking feature. Here's an analysis of the acceptance criteria and the study details based solely on the provided document:

Missing Information: It's important to note that the provided FDA 510(k) clearance letter is a summary document and does not contain the detailed clinical study report or the specific acceptance criteria with numerical performance targets. It states that the device meets "all consensus standards requirement" and that "results were within the acceptance criteria," but it does not define those criteria or present detailed performance data in a table format. Therefore, I will have to make assumptions about the typical acceptance criteria for Non-Invasive Blood Pressure (NIBP) devices based on the mentioned standards (ISO 81060-2, IEEE 1708, ISO 81060-3) and then state the general reported outcome from the document.

1. Table of Acceptance Criteria and Reported Device Performance

Given the lack of specific numerical acceptance criteria and performance data in the provided document, the table below will broadly reflect typical NIBP acceptance criteria based on the mentioned standards and the general statement of performance from the text.

Explanation of Assumption: The document explicitly states that "The clinical testing and analysis is performed according to applicable clauses from ISO 81060-2, IEEE 1708, and ISO 81060-3 for validation using reference invasive blood pressure measurement on the radial artery." ISO 81060-2 is the primary standard for non-invasive sphygmomanometers, which outlines specific statistical accuracy requirements (mean difference and standard deviation). Therefore, the acceptance criteria are assumed to be those specified in ISO 81060-2. The document does not provide numerical results for the Vios Monitoring System.

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

• Sample Size for Test Set: Not explicitly stated in the provided document. The text mentions "a range of subjects, representative of the intended population."
• Data Provenance: Not explicitly stated. The document indicates a "clinical study" was performed, but does not specify the country of origin of the data or whether it was retrospective or prospective. Given it's a clinical study for validation, it is most likely prospective.

3. Number of Experts Used to Establish Ground Truth and Qualifications

This information is not provided in the document. The ground truth was established by "reference invasive blood pressure measurement on the radial artery," which is a direct, objective medical measurement, not typically requiring a panel of experts for interpretation in the same way as, for example, image interpretation.

4. Adjudication Method for the Test Set

This information is not applicable/provided as the ground truth for blood pressure measurement (invasive arterial line) is an objective, quantitative measurement that does not require expert adjudication in the same manner as subjective or qualitative assessments.

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

No, an MRMC comparative effectiveness study was not done. This type of study (comparing human reader performance with and without AI assistance) is typically performed for diagnostic imaging or similar interpretation tasks where human perception and decision-making are aided by AI. For a vital signs monitor, the primary assessment is of the device's accuracy against a known reference, not its ability to assist human readers in interpretation.

6. If a Standalone (Algorithm Only) Performance Study Was Done

Yes, a standalone performance study was done. The clinical testing described for "Blood Pressure Tracking" assesses the algorithm's accuracy in autonomously generating blood pressure values from PAT (Pulse Arrival Time) against an invasive blood pressure reference. This is an assessment of the algorithm's standalone performance.

7. The Type of Ground Truth Used

The ground truth used for the blood pressure tracking feature was invasive blood pressure measurement on the radial artery. This is considered a gold standard and highly accurate method for blood pressure determination.

8. The Sample Size for the Training Set

The document does not provide information regarding the sample size for a training set. The descriptions focus on the validation study for the blood pressure tracking feature. It is implied that the algorithm was developed (trained) prior to this validation, but the details of that training are not included in this summary.

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

The document does not provide information on how the ground truth for any training set was established. It only describes the ground truth for the clinical validation study (invasive blood pressure measurement on the radial artery) and the calibration process. The "calibration (initialization)" step uses an "FDA-cleared oscillometric blood pressure monitor" for initial coefficient determination, which is distinct from establishing ground truth for a large-scale training set.

Ask a specific question about this device

The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-lead ECG, heart rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure and activity. VMS allows for the input of body temperature, and can display data from peripheral devices. VMS can generate alerts when the physiological vital signs fall outside of selected parameters.

VMS can also generate alerts when cardias arrhythmias (Tachycardia, Asystole, Ventricular Fibrillation and Atrial Fibrillation/ Atrial Flutter) are detected.

The ECG rhythm analysis is intended for use by medified professionals in the identification of arrhythmia events and to aid in clinical review of arrhythmias and medical interventions.

The Vos CSM/CS Software is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSMCS SW receives, stores, and displays patient physiological and waveform data and alams generated by Vios proprietary patient vitals monitoring software.

The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals. The VMS includes a proprietary monitoring software, Chest Sensor, Finger Adapter and Central Server and Central Monitoring Station. The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices. The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile multiple use,

The Vios Monitoring System (VMS) Model 2050 was evaluated for its arrhythmia detection features, specifically assessing its performance against the ANSI/AAMI EC57:2012 standard and additional database records.

Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance:

The document primarily references compliance with the ANSI/AAMI EC57:2012 standard for cardiac rhythm and ST-segment measurement algorithms. While specific numerical acceptance criteria (e.g., minimum sensitivity, positive predictivity) for each arrhythmia are not explicitly listed in the provided summary, the study's conclusion of meeting "performance requirements as outlined in the consensus standard ANSI/AAMI EC57:2012" implies that the device achieved the performance thresholds defined within that standard for the tested arrhythmias.

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

The document states that the device's performance was evaluated using:

• Records from the ANSI/AAMI EC57 standard. This standard often utilizes a combination of standard ECG databases (e.g., MIT-BIH Arrhythmia Database).
• Additional records from LTAF, AAEL, and VFDB databases.

The specific sample sizes (number of patients or ECG recordings) for each arrhythmia or for the combined test set are not provided in the summary. The provenance of LTAF, AAEL, and VFDB databases is not detailed; however, these are generally recognized public databases of ECG recordings used for algorithm testing, often comprising retrospective data.

3. Number of Experts Used to Establish Ground Truth and Qualifications:

The document does not state the number of experts used or their specific qualifications for establishing the ground truth of the test set. For publicly available and widely used databases like those mentioned (MIT-BIH, LTAF, AAEL, VFDB), the ground truth labels are typically established by multiple expert cardiologists or electrophysiologists using established criteria, often after multiple review rounds. However, this specific information is not in the provided text.

4. Adjudication Method for the Test Set:

The document does not specify the adjudication method used (e.g., 2+1, 3+1). For standard ECG databases, ground truth is usually established via expert consensus, which inherently involves an adjudication process, but the specific mechanics are not described here.

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 to assess how much human readers improve with AI vs. without AI assistance. The testing described is focused on the standalone performance of the device's arrhythmia detection algorithm.

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

Yes, a standalone performance evaluation was done. The summary explicitly states: "The non-clinical tests for evaluation of performance of Vios system with the addition of arrhythmia alarms is based on ANSI/AAMI EC57, showing substantial equivalence to the predicate (K180472). The subject device's performance was also evaluated using additional records from LTAF, AAEL, and VFDB database..." This describes the algorithm's performance without direct human intervention as part of the detection process.

7. Type of Ground Truth Used:

The ground truth for the test was established through expert consensus/annotations from well-known ECG databases (ANSI/AAMI EC57, LTAF, AAEL, and VFDB). These databases contain ECG recordings that have been meticulously reviewed and annotated by medical experts (typically cardiologists or electrophysiologists) to identify and label different cardiac events and arrhythmias,
Pathology and outcomes data are not mentioned as sources for ground truth in this context.

8. Sample Size for the Training Set:

The document does not specify the sample size used for the training set of the Vios Monitoring System's arrhythmia detection algorithm.

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

The document does not specify how the ground truth for the training set was established. However, it is common practice for such algorithms to be trained on large, expertly annotated ECG datasets, similar to those used for testing (expert consensus/annotations).

Ask a specific question about this device

ESSENZ Patient Monitor is a modularly structured program package that is exclusively used with LivaNova Heart-Lung Machines. The system allows detailed recording of perfusion data during cardiopulmonary bypass as well as the processing and evaluation of this data. The data may be recorded automatically or entered manually.

The ESSENZ Patient Monitor is used to collect and view data generated during cardiopulmonary bypass surgery. It interfaces with LivaNova Heart-Lung machines to capture this data.

The ESSENZ Patient Monitor includes the following main components:

• Software: The data-recording software installed on the Perfusion System Monitor hardware; known as "ESSENZ Patient Monitor". It is used to save and process the collected data.
• Hardware: The Perfusion System Monitor. It is used to display and transfer the collected data.
• Hardware: A mast holder to mount the Perfusion System Monitor on a vertical mast of the respective LivaNova HLM.

This document describes the ESSENZ Patient Monitor, a device used with LivaNova Heart-Lung Machines to record, process, and evaluate perfusion data during cardiopulmonary bypass. The information provided is for a 510(k) premarket notification (K212003).

Here's an analysis of the acceptance criteria and supporting studies based on the provided text:

1. Table of Acceptance Criteria and the Reported Device Performance:

The document does not explicitly present a table of acceptance criteria with specific numerical targets. Instead, it states that the device was evaluated against recognized standards and through various non-clinical tests to demonstrate substantial equivalence to a predicate device (Sorin CONNECT, K170460). The general acceptance criterion is that the modified device is "as safe and effective" as the predicate.

For the purpose of this request, we can infer the categories of acceptance criteria from the performed tests and their general outcome:

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

• Test Set Sample Size: The document does not specify a quantitative "test set sample size" in terms of patient data or specific number of tests. The testing described (Electrical Safety, EMC, Performance, Software V&V, Human Factors, Shipping) is related to hardware and software requirements, not clinical data sets in the typical sense of a diagnostic or therapeutic algorithm.
• Data Provenance: The tests conducted are non-clinical hardware and software verification and validation tests performed by the manufacturer, LivaNova Deutschland GmbH. The data provenance is internal to the manufacturer's testing processes. There is no mention of country of origin for a clinical data set because no clinical testing was performed or relied upon. The report states, "No animal testing was submitted to support the substantial equivalence of the modified device to the cleared Sorin CONNECT," and "No clinical testing was conducted in support of ESSENZ Patient Monitor."

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

This information is not applicable to the submitted document. The "ground truth" in this context refers to the compliance with engineering and regulatory standards established through non-clinical testing. These tests are evaluated against predefined specifications and industry standards, not against an expert-established clinical ground truth for a diagnostic outcome.

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

This information is not applicable. Adjudication methods like 2+1 or 3+1 are typically used in clinical studies for interpretation of images or clinical outcomes, which were not part of this 510(k) submission for the given device. The testing was against engineering specifications and recognized standards.

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 conducted or is relevant to this device's submission. The ESSENZ Patient Monitor is a data management system for perfusion data during cardiopulmonary bypass; it is not an AI-assisted diagnostic tool that would involve human readers or image interpretation.

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

The concept of "standalone performance" for an algorithm often applies to diagnostic or predictive AI. In this case, the "standalone performance" can be considered as the device's ability to accurately record, process, and evaluate perfusion data according to its specifications and in compliance with the relevant standards (IEC 60601-1, IEC 60601-1-2, IEC 62304, etc.) without human intervention in the data handling itself. The software verification and validation, along with performance testing, would cover this aspect. However, the device is explicitly used "with LivaNova Heart-Lung Machines" and the data can be "recorded automatically or entered manually," implying it is part of a larger system where human interaction remains.

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

The "ground truth" for the non-clinical testing of the ESSENZ Patient Monitor is compliance with established engineering and safety standards (e.g., IEC 60601 series, IEC 62304, ISO 14971). The ground truth for its functional performance (data recording, processing, evaluation) would be derived from comparisons against expected computational and display outputs based on defined inputs, ensuring accuracy and reliability as specified in the device's design.

8. The sample size for the training set:

This information is not applicable. The ESSENZ Patient Monitor is a data management system, not a machine learning or AI model that requires a "training set." The software is re-engineered from a legacy version and verified/validated against specifications.

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

This information is not applicable, as there is no "training set" for this device.

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 Essence 55SP Large Monitor System (Essence 55SP) is intended to be used by health care professionals to integrate the video output from various commercially-available instruments commonly used in a medical procedure laboratory into a single video display.

The Essence 55SP Large Monitor System is a large color LCD monitor for viewing images derived from several video sources on a single display and to rearrange these images to the situational requirements of the user. The system consists of a 55" TFT color LCD Monitor, and optionally a video wall controller, optical graphic extension module, a common PC, and cables.

The provided document is a 510(k) Summary for the Essence 55SP Large Monitor System. It describes the device and claims substantial equivalence to a predicate device. However, it does not contain the kind of detailed study information (sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, ground truth details for training/test sets) that would typically be found for an AI/ML medical device submission.

This document describes a medical monitor, not an AI/ML device. Therefore, the specific criteria requested, which are typically for assessing the performance of AI/ML algorithms against a clinical ground truth, are not applicable or present in this submission. The tests mentioned are performance tests for the display itself, ensuring it meets technical specifications and is equivalent to the predicate device.

Here's an attempt to answer the questions based on the available information, noting where the requested information is not present due to the nature of the device:

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

The document compares the proposed device (Essence 55SP) with a predicate device (Essence 55S) based on technical specifications. The acceptance criteria essentially appear to be demonstrating "substantial equivalence" to the predicate device, meaning its technical performance is either the same or, if different, the difference does not raise new questions of safety or effectiveness.

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

Not applicable. This is a medical monitor, and the "tests" performed are bench tests and display validation tests to confirm its technical specifications and equivalence to a predicate device. It does not process or analyze medical data in a way that would involve a "test set" of patient data.

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. Ground truth, in the context of AI/ML, refers to clinically verified labels or diagnoses. This device is a display system, not a diagnostic AI. Its performance is assessed against technical specifications, not clinical judgment.

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

Not applicable. There is no test set in the sense of clinical cases requiring adjudication.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. This device is a display monitor, not an AI system. It does not provide AI assistance for human readers, therefore, an MRMC study comparing human readers with and without AI would not be relevant.

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

Not applicable. This is a monitor, not an algorithm.

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

Not applicable. The performance is based on meeting technical specifications as specified by standards and comparison to a predicate device's measured performance. There is no "ground truth" related to medical disease states as one would find in an AI/ML submission.

8. The sample size for the training set

Not applicable. This is not an AI/ML device that requires a training set.

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

Not applicable. There is no training set or medical ground truth for this device.

Ask a specific question about this device

The Vios CSM/CS Software is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSM/CS SW receives, stores, manages, and displays patient physiological and waveform data and alarms generated by Vios proprietary patient vitals monitoring software.

The Vios CS SW enables the Vios Monitoring System to be used in networked mode within a healthcare IT network and runs on commercial IT equipment. The Vios CS SW operates as a communications hub that can pass the data generated by Vios proprietary vitals monitoring software to one or more remote viewing software applications, without modifying the data. The Vios CSM SW is the remote viewing software of the Model 2050 system. It allows up to 16 devices to be displayed on one screen and runs on a commercial IT device that satisfies defined Vios-defined technical specifications.

The provided text does not contain information about the acceptance criteria and study proving device performance for Vios Central Station Monitor/Central Server Software Model 2050. The document is an FDA 510(k) clearance letter and summary, which confirms substantial equivalence to a predicate device but does not detail specific performance studies with acceptance criteria, sample sizes, ground truth establishment, or expert involvement.

Therefore, I cannot fulfill your request for the detailed performance information based on the provided input.

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 and Philips Patient Monitors that are connected through networks.

The IntelliVue GuardianSoftware (866009) is a Clinical Information Management System. It collects and manages vital signs data acquired from the Philips specified measurements and Philips Patient Monitors. The IntelliVue GuardianSoftware provides review, reporting, clinical documentation, remote viewing, operating, interfacing, storage, printing and predictive trend analytics, meaning trending, notification, calculations and clinical advisories including EWS deterioration status. The IntelliVue GuardianSoftware 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 primarily details an FDA 510(k) submission for the Philips IntelliVue GuardianSoftware and an administrative change letter. It does not contain an elaborative study description with acceptance criteria and its proof for device performance in the requested format.

However, based on the general information provided in the 510(k) summary, I can extract and infer some information, but it will not be a complete answer to all your specific questions:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria or detailed device performance metrics in a table format. It broadly states:

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

• Sample Size for Test Set: Not specified. The document only mentions "software testing on integration level (functional testing and regression testing) and software testing on system level (hazard analysis testing and dedicated software performance testing)." It does not indicate the number of patient records or data points used in these tests.
• Data Provenance: Not specified. It does not mention the country of origin of the data or whether the data was retrospective or prospective.

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

Not specified. The document does not describe the establishment of a "ground truth" for the test set using human experts. The testing appears to be functional and performance-based against specifications, not clinical outcomes evaluated by experts.

4. Adjudication method for the test set

Not specified. Since no expert ground truth establishment is mentioned, there's no mention of an adjudication method.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No. The document describes the Philips IntelliVue GuardianSoftware as a Clinical Information Management System for collecting, storing, and managing vital signs data, and providing review, reporting, clinical documentation, remote viewing, operating, interfacing, storage, printing, and predictive trend analytics. It is not an AI-assisted diagnostic device, and therefore, an MRMC comparative effectiveness study comparing human readers with and without AI assistance is not applicable to this device and was not mentioned.

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

Yes, implicitly. The testing described is for the software itself, independently verifying its performance, functionality, and reliability according to specifications and safety standards. The device is a "software only product" and its testing would inherently be standalone.

7. The type of ground truth used

For the software verification and validation, the "ground truth" would be the pre-defined specifications, requirements, and safety standards (e.g., ANSI/AAMI/IEC 62304:2006). The software was tested to ensure it met these established criteria. It does not involve medical ground truth like pathology, expert consensus on images, or outcomes data.

8. The sample size for the training set

Not applicable/Not specified. This device is described as a "Clinical Information Management System" that handles data collection, storage, and management, including predictive trend analytics and clinical advisories. While "predictive trend analytics" could potentially involve machine learning, the document does not elaborate on the specific algorithms used or if a training set, characteristic of machine learning models, was employed or is relevant to its substantial equivalence claim. The focus here is on the functionality and safety of the data management software itself.

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

Not applicable/Not specified, for the same reasons as #8. If predictive trend analytics involve trained models (which is not explicitly stated but hinted at), the method for establishing ground truth for such a training set is not described. The document emphasizes testing against a predicate device's cleared specifications and general software safety standards.

Ask a specific question about this device

The Barco Nexxis OR system is designed to allow transfer, selection and distribution of A/V signals and medical images from various commercially available instruments that are commonly used in a medical procedure laboratory or operating room.

The Barco Nexxis OR system is also designed for transfer, selection and distribution of human interface signals and control signals of non-medical room equipment,

The Barco Nexxis OR system allows control and selection of these signals from a central point.

The Barco Nexxis OR system is not intended to be used for remote or robotically assisted surgery,

The Barco Nexxis OR system is not intended to be used in the vicinity of MRI or other devices that use strong magnetic fields.

The Nexxis OR system is a solution for video distribution in operating rooms and medical procedure laboratories. The Nexxis OR can consist of any possible combination of the Nexxis encoders/decoders that transfer video signals from various available devices to one or more output devices (displays). Additionally the Nexxis components can transfer audio signals and USB signals. The USB communication is intended only for keyboard and mouse control and control signals for non-medical room equipment. The selection of sources and output devices is done by control software (NMS API). The Nexxis OR system can also contain, optionally, the MNC-180 compositor device, a MDSC-8258 MNA display and/or the touch user interface MUIP-2112. The Nexxis OR system may now consist of any combination of the following components: a) Nexxis OR components (Medical network adaptors) b) Nexxis Compositor with NCS composition software (MNC-180) c) Nexxis Management Suite (NMS). d) A 58-inch large screen LCD monitor: Barco MDSC-8258 MNA.(optional) e) touch user interface MUIP-2112 (optional) f) Cables g) Documentation

The provided document is a 510(k) premarket notification for the Barco Nexxis OR system, which is a video distribution solution for operating rooms. The document focuses on demonstrating substantial equivalence to a predicate device rather than detailing specific acceptance criteria and a study to prove meeting those criteria in the context of diagnostic performance.

Therefore, many of the requested elements for a diagnostic device's acceptance criteria and study cannot be extracted from this document.

Here's what can be gathered and what cannot:

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

The document does not provide a table of acceptance criteria in the sense of specific performance metrics (e.g., sensitivity, specificity, accuracy) for a diagnostic output. Instead, the "acceptance criteria" can be inferred as demonstration of similar characteristics in terms of safety and effectiveness compared to the predicate device.

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

This information is not provided in the document. The testing described ("Display bench tests," "Display validation tests," "Nexxis OR qualification tests," "System tests") appears to be engineering and system validation rather than clinical performance testing with a "test set" of medical images or patient data.

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)

This information is not applicable/not provided. The device is a video distribution system, not a diagnostic algorithm that relies on expert interpretation of output.

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

This information is not applicable/not provided.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

This information is not applicable/not provided. This is not a diagnostic device with an AI component for image interpretation.

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

This information is not applicable/not provided. This is a system for distributing video signals, not a standalone diagnostic algorithm.

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

This information is not applicable/not provided. Ground truth in a clinical sense would not be relevant for the device itself, though the medical images it transmits would have their own ground truth established outside the scope of this device.

8. The sample size for the training set

This information is not applicable/not provided. This is not an AI/ML device that requires a training set.

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

This information is not applicable/not provided.

Summary based on information provided in the document:

The Barco Nexxis OR system is a medical video distribution system. The study to demonstrate its performance and meet acceptance criteria primarily consisted of bench tests and system qualification tests. These tests aimed to show that the device has similar characteristics to its predicate device (Nexxis OR cleared under K170537) and did not reveal new issues of safety and effectiveness. The document explicitly states that "Animal or clinical testing have not been performed," indicating that the "study" was not a clinical trial in the traditional sense, but rather engineering and functional validation.

Ask a specific question about this device

The Essence 55S Large Monitor System (Essence 55S) is intended to be used by health care professionals to integrate the video output from various commercially-available instruments commonly used in a medical procedure laboratory into a single video display.

The Essence 55S Large Monitor System is a large color LCD monitor for viewing images derived from several video sources on a single display and to rearrange these images to the situational requirements of the user. Thanks to the advantages of the large widescreen monitor, the data can be collected from the video sources using the optional video wall controller AVS-540 and fed into the large display via the DVI lines and / or DP. The optical graphic extension module M1-201SA-TR can be used to convert / transmit the video signal, and the common PC can be taken as a video device.

The provided 510(k) summary (K172969) describes a medical monitor, the Essence 55S Large Monitor System. The acceptance criteria and the study that proves the device meets them are based on comparisons to a predicate device and bench testing.

1. Table of Acceptance Criteria and Reported Device Performance

The device is a medical monitor, and its "performance" is primarily defined by its technical specifications and its ability to integrate video output for medical professionals. The acceptance criteria are implicitly met by demonstrating substantial equivalence to a predicate device and successful bench and system tests.

Comparison Table for Key Technical Specifications (Excerpt from Table 2 in document):

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

This is a medical display device, not an AI or diagnostic imaging device. Therefore, the concept of a "test set" in the context of patient data or clinical images is not applicable. The "tests" performed are engineering and performance validation tests.

• Sample Size: Not applicable in the context of patient data. The "sample" would be the device itself (Essence 55S Large Monitor System).
• Data Provenance: Not applicable. The "data" are technical specifications and test results generated from the device in a laboratory setting.

3. Number of Experts Used to Establish Ground Truth and Qualifications

Not applicable. Ground truth, in the context of expert consensus on medical images, is not relevant for a medical display device. The "ground truth" for this device's performance is its adherence to technical specifications and safety standards, as verified through engineering tests.

4. Adjudication Method for the Test Set

Not applicable. Adjudication methods (like 2+1 or 3+1) are used for resolving disagreements among human readers in interpreting medical images. This device is a display, not an interpretation tool.

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

No, an MRMC comparative effectiveness study was not done. Such studies are typically performed for diagnostic devices or AI algorithms that assist in interpretation, to measure the impact of the device on human reader performance. This device is a monitor, not an interpretative aid.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, but not in the typical sense of an "algorithm-only" performance for a diagnostic task. The "standalone" performance here refers to the device's technical specifications and functionality as a display system, independent of a human's diagnostic interpretation using the displayed images. The "Display bench tests," "Display validation tests," and "System tests" are essentially standalone performance evaluations of the monitor.

7. The Type of Ground Truth Used

The "ground truth" for this device is based on:

• Technical Specifications: Adherence to defined physical and electrical parameters (e.g., resolution, brightness, contrast, response time).
• Regulatory Standards: Compliance with relevant medical device safety and performance standards (e.g., EN60601-1, ANSI/AAMI ES60601-1, FCC-B, RoHS).
• Predicate Device Equivalence: The performance and characteristics of the legally marketed predicate device (RadiForce Large Monitor System) serve as a benchmark for substantial equivalence.

8. The Sample Size for the Training Set

Not applicable. This device is a hardware display system, not a machine learning model that requires a "training set" of data.

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The device is a modularly structured program package that is exclusively used with Sorin/Stockert heart lung machines. The system allows detailed recording of perfusion data during cardiopulmonary bypass as well as the processing and evaluation of this data. The data may be recorded automatically or entered manually.

The Sorin CONNECT is used to collect and view data generated during cardiopulmonary bypass surgery. It interfaces with Sorin Heart-Lung machines to capture this data.

The Sorin CONNECT includes the following main components:

• The Datapad display monitor. It's used to display the collected data.
• The data recording software installed on the Datapad; known as "CONNECT Recorder". . lt's used to save the collected data.
• The PC software for reviewing data; known as "CONNECT Manager". It's used to view ● the recorded data and manually enter additional data including clinician's comments.
• . An RFID card reader used to transfer the data from the Heartlink card to the Datapad.
• . A pole mounting system (holder) to attach the Datapad to an IV pole.

The provided text is a 510(k) summary for the Sorin CONNECT, a data management system for heart-lung machines. It focuses on demonstrating substantial equivalence to a predicate device and outlines hardware and software updates. However, it does not contain information regarding acceptance criteria and a study proving the device meets those criteria, as typically found in clinical performance studies of AI/ML devices.

Specifically, the document states:

• NON CLINICAL TEST RESULTS: Electrical safety (IEC 60601-1) and electromagnetic compatibility (IEC 60601-1-2) were determined.
• IN VITRO TEST RESULTS: "Verification, validation, and testing activities, were conducted to demonstrate compliance to the product's specifications and compliance to safety and effectiveness requirements."

This implies that the testing performed for this 510(k) submission was primarily focused on hardware updates, software compatibility, and meeting electrical and EMC standards, rather than evaluating the performance of an AI/ML algorithm against a predefined set of diagnostic or predictive acceptance criteria.

Therefore, for your specific request regarding acceptance criteria and a study proving the device meets them, the following information is not present in the provided text:

1. Table of acceptance criteria and reported device performance: Not available. The document refers to "product's specifications" and "safety and effectiveness requirements" in a general sense, but no specific performance metrics or acceptance thresholds are listed.
2. Sample size used for the test set and data provenance: No test set involving patient data or clinical outcomes is described. The "testing activities" refer to non-clinical and in-vitro testing for compliance.
3. Number of experts used to establish the ground truth and qualifications: Not applicable, as there's no clinical performance evaluation involving expert consensus on patient data.
4. Adjudication method: Not applicable.
5. Multi Reader Multi Case (MRMC) comparative effectiveness study: Not applicable.
6. Standalone (algorithm only) performance: Not applicable, as it's a data management system hardware/software update, not an AI/ML algorithm.
7. Type of ground truth used: Not applicable.
8. Sample size for the training set: Not applicable, as no AI/ML model training is described.
9. How the ground truth for the training set was established: Not applicable.

In summary, the provided document describes a 510(k) submission for updates to a medical device focused on data management (Sorin CONNECT), demonstrating substantial equivalence through non-clinical and in-vitro testing for hardware/software functionality, electrical safety, and EMC. It does not provide the kind of performance data, acceptance criteria, or study details typically associated with AI/ML device evaluations.

Ask a specific question about this device