Search Results

The Cogent HMS is intended for patients for whom the monitoring of CCO and calculated hemodynamic parameters is indicated for diagnostic and prognostic evaluation by a clinician. The Cogent HMS is intended for use with ICU Medical pulmonary artery catheters and central venous oximetry catheters and with ICU Medical Cogent sensors. The Cogent HMS is intended to measure and calculate venous oxygen saturation in patients. PulseCO functionality is limited to adult patients.

The Cogent HMS is designed to compute and display cardiac and oximetry parameters relevant to patient care in the hospital acute care areas including Intensive Care Units and the Operating Room. Monitoring parameters include cardiac output and blood oxygen saturation levels, as well as other derived hemodynamic parameters. Measurements are obtained through the compatible ICU Medical pulmonary artery and central venous oximetry catheters, and ICU Medical CardioFlo™ sensors.

Input data for derived parameters may be keyed in by a clinician or may be obtained from a bedside monitor.

The Cogent HMS provides the following functions:

• monitors patient cardiac output continuously (CCO) using continuous thermodilution -(TdCO), and intermittently, using bolus thermodilution (Bolus CO);
• monitors continuous cardiac output (CCO) using pulse power analysis on an arterial pressure waveform;
• monitors venous oxygen saturation (SvO2) by measuring the reflectance spectrum of the blood; and
• provides a general-purpose interface to the analog input/output channels of other monitoring devices.

The Cogent HMS consists of:

• a base unit (patient interface module or PIM);
• a dedicated touch-screen display unit (user interface module or UIM) which allows for patient monitoring remotely (up to 50 feet); and
• associated cables

The PIM and UIM modules communicate with each other in docked, tethered (wired) or wireless mode.

The provided text describes a 510(k) premarket notification for the ICU Medical Cogent™ Hemodynamic Monitoring System (HMS). However, the document focuses on demonstrating substantial equivalence to a predicate device (K152006) primarily due to updates to the operating system (Windows 7 to Windows 10), software (version 1.1.8 to 1.4.0), and minor hardware changes. The submission primarily relies on non-clinical testing and verification, rather than a clinical study with detailed acceptance criteria and performance metrics for a novel algorithm.

Based on the provided text, the device is an updated version of an already cleared hemodynamic monitoring system. Therefore, the "acceptance criteria" discussed are largely related to ensuring the updated device performs equivalently to its predicate and meets relevant safety and performance standards. No specific "acceptance criteria" in terms of clinical performance metrics of an AI algorithm are explicitly stated, as the device is not presented as an AI-powered diagnostic algorithm with a performance threshold to meet.

Here's a breakdown of the information based on your request, as much as can be extracted from the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

As the submission is for an updated version of an existing device, the "acceptance criteria" largely revolve around demonstrating equivalent performance to the predicate device and compliance with relevant standards. The document doesn't provide a table of precise quantitative acceptance criteria for clinical performance (e.g., sensitivity, specificity for a diagnostic algorithm) and corresponding reported performance of a novel AI component. Instead, it states that "the measurement performance of the subject device is equivalent to that of the predicate device."

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

The document explicitly states: "No new human factors, animal, and/or clinical studies were conducted as was determined not required to demonstrate device safety and effectiveness for the subject device."

Therefore, there is no "test set" in the context of clinical data with a sample size or provenance for this specific 510(k) submission. The testing performed was primarily non-clinical (bench testing, software V&V).

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

Since no new clinical studies were conducted for this submission, there is no mention of experts establishing ground truth for a test set.

4. Adjudication Method for the Test Set

Not applicable, as no new clinical test set was used.

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. The device is a hemodynamic monitoring system, not an AI-assisted diagnostic imaging or interpretation tool. The submission focuses on software and hardware updates to an existing monitoring device, not the evaluation of an AI algorithm's impact on human reader performance.

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

The "Cogent System Software Validation" and various algorithm validations (PulseCO, Bolus CO, SO2, CCO) were performed, which could be considered standalone performance evaluations of the specific algorithms within the device. However, these are validations of established medical algorithms for physiological measurements, not novel AI algorithms in the common sense. The text implies these were bench validations, not clinical standalone performance studies.

7. The Type of Ground Truth Used

For the algorithm validations (e.g., PulseCO, Bolus CO, SO2, CCO), the ground truth was established through "in vitro validation" using flow simulators or electronically generated data. This suggests a controlled laboratory environment where the "true" physiological values could be precisely set or simulated.

8. The Sample Size for the Training Set

Not applicable. The document discusses updates to an existing device and its algorithms, not the training of a new AI algorithm that would require a distinct training set. The algorithms mentioned (e.g., thermodilution, pulse power analysis) are based on established physiological principles and are not typically "trained" in the machine learning sense with large datasets.

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

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

Ask a specific question about this device

Hypotension Decision Assist is indicated to acquire, process and display arterial pressure and other key cardiovascular characteristics of adult patients who are at least eighteen years of age that are undergoing surgery where their arterial pressure is being continuously monitored by a vital-signs monitor. It is indicated for use to assist anesthesia healthcare professionals manage the blood pressure, hemodynamic stability and the cardiovascular system during such surgery.

Hypotension Decision Assist (HDA) is a clinical decision support Software as a Medical Device (SaMD) that is installed upon a medically-rated touch-screen computer. HDA connects to a multi-parameter patient monitor supplied by other manufacturers, from which it acquires vital signs data continuously including the arterial blood pressure waveform and cardiovascular-related numeric parameters.

HDA continually processes this data to display, in graphical charts and numeric format, vital signs data and derived variables including mean arterial pressure (MAP), heart rate, systolic and diastolic blood pressure, cardiac output and systemic vascular resistance. HDA compares MAP to user set targets to indicate when MAP is above or below the target range. It allows the user to mark the administration of vasopressors and volume challenges to the MAP trend.

The Hypotension Decision Assist (HDA-OR2) device, as described in the provided FDA 510(k) summary, is a clinical decision support software intended to assist healthcare professionals in managing blood pressure and cardiovascular stability during surgery.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present acceptance criteria in a quantitative table format with corresponding performance metrics for the HDA-OR2 device's intended use (i.e., assisting anesthesia healthcare professionals manage blood pressure, hemodynamic stability, and the cardiovascular system). Instead, the performance data focuses on system verification, measurement accuracy, artifact detection, and software validation.

The "Performance Data" section primarily details verification tests rather than clinical performance acceptance criteria directly related to the device's indications for use. The overall conclusion states that "the accuracy of its measurements is substantially equivalent to its predicate device and that HDA-OR2 performs as well as its predicate device."

Here's an interpretation of the performance data as it relates to implicit acceptance criteria:

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

The document describes bench testing for verification of the device's technical performance (measurement accuracy, artefact detection, power interruption, remote updates, software V&V, electrical safety/EMC).

• Test Set Sample Size: No specific "sample size" of patients or cases is mentioned for the performance data section, as the testing described is primarily technical and bench-level, not clinical. For example, for measurement accuracy, it mentions verification "across the intended use measuring range" and "over the serial and network connections available," implying a range of test conditions and inputs rather than a patient count.
• Data Provenance: The data provenance is not specified as clinical patient data (e.g., country of origin, retrospective/prospective). The described tests are laboratory/bench tests, not studies on patient data. The device acquires data from "multi-parameter patient monitor supplied by other manufacturers," but the testing described here relates to the device's capability to process that signal and interact with its environment, not its performance in specific patient scenarios or outcomes.

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

• Not Applicable: The studies described are technical verification tests (measurement accuracy, artefact detection, electrical safety, software validation), not clinical studies requiring expert ground truth establishment from patient data for diagnostic or prognostic performance. The "ground truth" for these technical tests would be derived from calibrated instruments, known signal inputs, and established engineering standards.

4. Adjudication Method for the Test Set

• Not Applicable: As the described tests are technical verification rather than clinical performance studies using human experts evaluating patient cases, an adjudication method for a test set of clinical data is not mentioned or required.

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

• No MRMC Study was done: The document does not mention any MRMC comparative effectiveness study, or any study involving human readers/users comparing performance with and without AI assistance. The device is a "clinical decision support" tool, implying assistance, but no study is presented to quantify this assistance's effect on human performance. The 510(k) pathway for this device did not require such a study, as it demonstrated substantial equivalence primarily through technical performance and predicate comparison.

6. Standalone (i.e., algorithm only without human-in-the-loop performance) Study

• Standalone Performance Studied (Technically): The performance data presented (measurement accuracy, artifact detection, power interruption, remote updates) represents the standalone technical performance of the algorithm and hardware. The device "continually processes this data to display... vital signs data and derived variables." The verification tests confirm the accuracy and robustness of these processing and display functions.
• However, no clinical outcome study or diagnostic accuracy study (e.g., predicting hypotension with a specific accuracy) was performed in a standalone context. The device's role is to "assist" healthcare professionals, not autonomously diagnose or treat.

7. Type of Ground Truth Used

• Technical/Engineering Standards and Calibrated Inputs: The ground truth for the verification tests was established based on:
  • IEC 60601-2-34 Edition 3.0 2011-05: For measurement accuracy verification using bench testing. This implies using known, precisely controlled electrical or physiological signals as inputs and comparing the device's output to these known inputs.
  • Known Artefacts: For artifact detection, specific types of known signal aberrations were introduced to test the device's ability to detect them.
  • Controlled Power Situations: For power interruption testing, the power supply was intentionally cut.
  • Controlled Electromagnetic Environments: For remote update testing in noisy environments.
  • Software Design Specifications and Requirements: For software verification and validation.

8. Sample Size for the Training Set

• Not applicable / Not disclosed: The document describes a "Software as a Medical Device (SaMD)" but does not specify if it employs machine learning or AI models that require a training set in the conventional sense. The device "aquires, processes and displays" data and "derives and displays" variables. This sounds more like rule-based or signal-processing software rather than a learned AI model, at least not one that would typically require a large training dataset for its core function of calculating and displaying vital signs. If there are any internal predictive or pattern-recognition algorithms, their training data and sample size are not mentioned.

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

• Not applicable / Not disclosed: Since the existence and nature of a training set (in the context of machine learning) are not discussed, the method for establishing its ground truth is also not mentioned.

Ask a specific question about this device

The PulsioFlex Monitoring System is a diagnostic aid for the measurement and monitoring of blood pressure, cardiopulmonary, circulatory and organ function variables. The PulsioFlex Monitoring System is indicated in patients where cardiovascular and circulatory volume status monitoring is necessary. If a patient's biometric data are entered, the PulsioFlex Monitor presents the derived parameters indexed.

• With the PiCCO Module cardiac output is determined both continuously through pulse contour analysis and intermittently through thermodilution technique. Both are used for the determination of other derived parameters.
• With the CeVOX oximetry module connected to a compatible oximetry probe, the PulsioFlex Monitoring System measures continuous venous oxygen saturation to assess oxygen delivery and consumption.
• With the ProAQT Sensor, the PulsioFlex Monitoring System uses arterial pulse contour analysis for continuous hemodynamic monitoring.
  The use of the PulsioFlex Monitoring System is indicated in patients where cardiovascular and organ monitoring is useful. This includes patients in surgical, medical, and other hospital units.

The PulsioFlex Monitoring System is a patient monitoring system that consists of the following components:
a) PulsioFlex Monitor
b) PiCCO Module
c) CeVOX Optical Module
d) ProAQT Sensor

Here's a breakdown of the acceptance criteria and study information for the PulsioFlex Monitoring System with ProAQT Sensor, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not contain a specific table of acceptance criteria with corresponding performance metrics like sensitivity, specificity, or accuracy for the device's diagnostic capabilities. Instead, it focuses on general performance testing, software verification, safety, and biocompatibility.

General Performance Criteria (Implicit from "Performance Data"):

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

The document does not explicitly state a specific "test set" with a defined sample size for a clinical validation or diagnostic performance study in the way one might expect for an AI/ML device. The "Clinical Performance" section mentions "Clinical data demonstrates that the pulse contour algorithm is able to process pressure signals from femoral, brachial, axillary and also radial artery adequately." This suggests a clinical study was performed, but details on sample size (number of patients, number of measurements), country of origin, or retrospective/prospective nature are not provided.

The other performance tests (visual, lifetime, software verification, safety, etc.) are generally performed on a sample of devices or components, but details on those sample sizes are also not provided in this summary.

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

This information is not provided in the document. The type of device (hemodynamic monitor) does not typically rely on "expert ground truth" in the same way an imaging AI diagnostic might. Its ground truth for pulse contour analysis would typically be established by established invasive direct measurement methods (e.g., thermodilution cardiac output) or accepted physiological principles.

4. Adjudication Method for the Test Set

This information is not provided. Given the nature of the device, it is unlikely that a human adjudication method like "2+1" or "3+1" was applied for its performance evaluation, as it's not an AI diagnostic dependent on human interpretation for ground truth.

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

No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not performed or described in this document. This type of study is typically done for AI diagnostic tools that aid human interpretation of complex data (like medical images), which is not the primary function described here.

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

The "Clinical Performance" section states: "Clinical data demonstrates that the pulse contour algorithm is able to process pressure signals from femoral, brachial, axillary and also radial artery adequately." This implies standalone performance of the algorithm in deriving physiological parameters from raw pressure signals. The "PulsioFlex Monitoring System with ProAQT Sensor determines the cardiac output by means of pulse contour analysis. The ProAQT Sensor is connected in series to a pre-installed blood pressure measurement system. The required blood pressure data is measured and transferred to the PulsioFlex Monitor that analyzes the data and calculates and displays the associated parameters." This confirms the algorithm (part of the software) operates in a standalone manner on the input data to calculate parameters.

7. The Type of Ground Truth Used

Based on the description of the device (hemodynamic monitoring using pulse contour analysis), the ground truth for validating its calculated parameters (like cardiac output) would typically be established using:

• Established gold standard measurement methods: For cardiac output, this often includes intermittent thermodilution (e.g., using the PiCCO module itself as a reference, or other established thermodilution techniques), or direct Fick method, although the document doesn't explicitly state the ground truth method used in the clinical data for the ProAQT component.
• The product description for the PiCCO Module does mention: "With the PiCCO Module cardiac output is determined both continuously through pulse contour analysis and intermittently through thermodilution technique." And for the ProAQT Sensor, it states: "Subscripts 'cal' and 'pc' are used to distinguish between different calibration methods for pulse contour analysis: 'pc': Calibration with CO from thermodilution; 'cal': Calibration with CO from user input using an external measurement method." This strongly implies that thermodilution or external measurement methods (like Doppler ultrasound technique, as mentioned for ProAQT calibration) were used as the ground truth or reference for calibrating and validating the continuous pulse contour derived cardiac output.

8. The Sample Size for the Training Set

The document does not provide information on a specific "training set" sample size. The device described appears to be based on established algorithms for pulse contour analysis, rather than a machine learning model that undergoes a distinct training phase. The software updates mentioned likely involve refinements to these algorithms rather than re-training a deep learning model.

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

As no specific "training set" or explicit machine learning model training is described, this information is not applicable/provided. The 'ground truth' for the development of such physiological algorithms would typically come from extensive physiological studies and comparisons to established measurement techniques, which are then encoded as deterministic algorithms within the software.

Ask a specific question about this device

The EV 1000 Clinical Platform is indicated for use primarily for critical care patients in which the balance between cardiac function, fluid status and vascular resistance needs continuous or intermittent assessment. The EV1000 Clinical Platform may be used for the monitoring of hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol. Analysis of the thermodilution curve in terms of mean transit time and the shape is used to determine intravascular and extravascular fluid volumes. When connected to an Edwards oximetry catheter, the monitor measures oximetry in adults and pediatrics. The EV1000 Clinical Platform may be used in all settings in which critical care is provided.

The Edwards Lifesciences Acumen Hypotension Index feature provides the clinician with physiological insight into a patient's likelihood of future hypotensive events (defined as mean arterial pressure

The EV1000 Clinical Platform measures patient physiologic parameters in a minimally invasive manner when it is used as a system with various Edwards' components, including the Edwards pressure transducers, the FloTrac sensor, the components of the VolumeView System, oximetry catheters/sensors, and the corresponding accessories applied to the patient. The EV1000 Clinical Platform includes an Acumen Hypotension Prediction Index (HPI) feature, which is an index related to the likelihood of a patient experiencing a hypotensive event (defined as mean arterial pressure (MAP)

This document is a 510(k) premarket notification for the Edwards Lifesciences EV1000 Clinical Platform. It describes a corrective action related to a hardware change in the AC inlet to prevent liquid ingress. The primary focus of the provided text is on demonstrating the safety and substantial equivalence of this modified device to a previously cleared predicate device, specifically regarding the hardware change.

Therefore, the study information requested (acceptance criteria related to device performance, sample sizes, ground truth establishment, expert adjudication, MRMC studies, standalone performance, and training set details) is not detailed in this document. The document describes a design verification test for a hardware modification, not a clinical performance study of a device feature like the Acumen Hypotension Index (HPI).

Here's a breakdown of what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance:

• Acceptance Criteria: The document states that "a reduction in occurrences of liquid ingress at the AC inlet was achieved." This implies an acceptance criterion related to reducing liquid ingress, but specific quantitative targets (e.g., maximum ingress rate, number of failures allowed) are not provided.
• Reported Device Performance: The document states that the device "successfully passed functional and bench studies to demonstrate that the device is substantially equivalent to the cited predicate device and the Power Adapter Cover reduces the possibility of fluid ingress." Again, specific quantitative performance metrics (e.g., exact reduction percentage, ingress test results) are not provided.

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

• Sample Size: Not specified. The document mentions "functional and bench studies" but does not detail the number of units tested.
• Data Provenance: Not specified, but given it's bench testing for a hardware modification, it would be laboratory data.

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

• Not applicable for this type of hardware verification study. "Ground truth" in the context of device performance, specifically for preventing liquid ingress, would be determined by physical measurements and observations during bench testing, not expert consensus.

4. Adjudication Method for the Test Set:

• Not applicable. Adjudication methods like 2+1 or 3+1 are used for interpreting clinical data or images, not for bench testing hardware modifications.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No, an MRMC study was not done. This document pertains to a hardware modification for liquid ingress prevention, not the clinical performance or AI features of the device. The "Acumen Hypotension Index (HPI) feature" is mentioned as part of the overall device, but this submission is not a study of its effectiveness. It's a special 510(k) for a corrective action related to a physical design change.

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

• Not explicitly stated, but not applicable. This document describes a hardware change, not an evaluation of an algorithm's standalone performance. While the HPI is an algorithm, its performance evaluation is not the subject of this specific submission.

7. The type of ground truth used:

• For the liquid ingress test, the ground truth would be physical observation and measurement of liquid ingress during bench testing, as per relevant standards (e.g., IPX ratings).

8. The sample size for the training set:

• Not applicable. This document describes verification testing for a hardware change, not an AI model's training.

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

• Not applicable.

In summary, this 510(k) submission addresses a specific hardware modification for liquid ingress and demonstrates its safety and substantial equivalence through functional and bench studies. It does not contain the detailed clinical study information that would typically be provided for evaluating the performance of a diagnostic or predictive algorithm like the Acumen Hypotension Index. For such details, one would need to refer to separate 510(k)s or clinical trial reports specifically for those features.

Ask a specific question about this device

Hypotension Decision Assist is indicated to acquire, process and display arterial pressure and other key cardiovascular characteristics of adult patients who are at least eighteen years of age that are undergoing surgery where their arterial pressure is being continuously monitored by a vital-signs monitor. It is indicated for use to assist anesthesia healtheare professionals manage the blood pressure, hemodynamic stability and the cardiovascular system during such surgery.

Hypotension Decision Assist (HDA) is a clinical decision support Software as a Medical Device (SaMD) that is installed upon a medically-rated touch-screen computer. HDA connects to a multi-parameter patient monitor supplied by other manufacturers, from which it acquires vital signs data continuously including the arterial blood pressure waveform and cardiovascular-related numeric parameters.

HDA continually processes this data to display, in graphical charts and numeric format, vital signs data and derived variables including mean arterial pressure (MAP), heart rate, systolic and diastolic blood pressure, cardiac output and systemic vascular resistance. HDA compares MAP to user set targets to indicate when MAP is above or below the target range. It allows the user to mark the administration of vasopressors and volume challenges to the MAP trend.

Here's a breakdown of the requested information based on the provided text, focusing on the acceptance criteria and the study that proves the device meets them:

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

The document primarily focuses on demonstrating substantial equivalence to a predicate device and meeting various technical and safety standards, rather than defining specific numerical performance acceptance criteria for clinical outcomes. However, it does highlight areas of verification.

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

• Sample Size for Test Set: Not explicitly stated as a number of patients or cases for clinical performance assessment. The "test set" primarily refers to hardware and software testing.
• Data Provenance: "Patient data sets obtained from internationally recognized databases" were used for the original system verification and "bench testing performed to compare the performance of HDA to the predicate device." The data was "representative of the range of data input and signal quality that will be encountered in the intended use population and environment of use of the device." No specific countries of origin or whether the data was retrospective or prospective are mentioned beyond being from "internationally recognized databases."

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

Not applicable. The document states that "Clinical studies were not performed." Therefore, there was no expert consensus or ground truth established by human experts for a clinical test set in the traditional sense. The "ground truth" for the bench testing was derived from established standards (e.g., IEC 60601-2-34) and comparison to predicate/reference device measurements.

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

Not applicable. Since no clinical studies were performed, there was no adjudication of clinical outcomes by multiple experts.

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. A MRMC comparative effectiveness study was not performed. The device is a clinical decision support software, not an AI for image interpretation that would typically involve human readers. Clinical studies involving human users were not performed.

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

Yes, in a sense. The "Performance Data" section describes "Measurement accuracy verification," "Artefact Detection Verification," and "Predicate comparison testing" which evaluate the algorithm's direct output and processing capabilities against established standards or predicate device outputs. This represents a standalone performance evaluation of the algorithms and software functionality, rather than human-in-the-loop performance.

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

The ground truth for the device's technical performance verification (e.g., measurement accuracy) was established through:

• Bench testing methodologies derived from recognized standards (e.g., IEC 60601-2-34).
• Comparison to predicate or reference devices' established performance for specific parameters (e.g., cardiac output, SVR events, physiological parameter derivation).
• Pre-defined specifications for artifact detection and power interruption tolerance.

For claims of "clinical decision support" or "assisting healthcare professionals," the ground truth implicitly relies on the widely accepted understanding that accurate display and processing of vital signs aid clinical decision-making, rather than a specific clinical outcome study being performed with this device.

8. The sample size for the training set

The document does not explicitly mention a "training set" in the context of machine learning or AI model development. The device is described as "clinical decision support software" that "continually processes this data." If machine learning was used implicitly, no details are provided about its training data. The "patient data sets obtained from internationally recognized databases" were used for "original system verification" and "bench testing," which might imply they were used for validation or testing, but not necessarily for training a model.

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

Not applicable, as a clear "training set" and its ground truth establishment are not described in the provided text. The device's functionality appears to be primarily based on processing established physiological parameters and rules, rather than learning from a labeled training dataset in the AI sense.

Ask a specific question about this device

The Argos Cardiac Output monitoring device is intended for use on patients above the age of 18. It is intended to be used as a hemodynamic monitor for monitoring cardiac output and its derived parameters on patients in the intensive care unit or the operating room.

The Argos Monitor is a portable hemodynamic monitor that calculates Cardiac Output and other derived parameters, including cardiac index (CI), stroke volume (SV), stroke volume index (SVI), systemic vascular resistance (SVR), systemic vascular resistance index (SVRI), mean arterial pressure (MAP), heart rate (HR), and pulse pressure variation (PPV) based on a proprietary algorithm that analyzes the blood pressure waveform and user-entered patient demographic information (age, height weight and gender). The blood pressure waveform is input into the monitor via a connection with either a radial arterial catheter or the analog blood pressure signal output of a vital signs monitor. The scientific method that underlies the algorithm is based on a novel signal processing technique to determine the parameters of the well-established Windkessel model of the circulation in order to calculate cardiac output.

The Argos Monitor comes with a touchscreen monitor and computer system enclosed in a rigid plastic housing and a power cable. Cables to connect the monitor to a radial blood pressure transducer or to the analog blood pressure signal output of a vital signs monitor are also provided according to the setup and needs of the individual institution. The Monitor may be attached to a pole or a table stand via a standard screw interface pattern.

The requested information about the acceptance criteria and the study proving the device meets them is extracted from the provided text.

Based on the provided text, the device in question is the Retia Medical, LLC: Argos Monitor, which calculates Cardiac Output and other derived parameters.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of numerical acceptance criteria for specific performance metrics (e.g., accuracy thresholds for Cardiac Output). Instead, the acceptance is framed in terms of equivalence to a predicate device and meeting safety and performance standards.

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

• Sample Size for Clinical Performance Test Set: 40 patients (20 from the Operating Room (OR) and 20 from the Intensive Care Unit (ICU)).
• Data Provenance: The document does not explicitly state the country of origin. It describes the study as "clinical testing" and "clinical data," implying a prospective collection of data in a clinical setting for the purpose of this study. The timeframe is not specified beyond "No adverse effects or complications were noted during the study."

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

The document does not specify the number of experts or their qualifications for establishing the ground truth. The ground truth (reference standard) used was an invasive method: "the pulmonary artery catheter as the reference for all measurements." This is a direct measurement, and thus expert interpretation for ground truth establishment might not be applicable in the same way it would be for an image-based diagnostic study requiring consensus reads.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method for the test set, as the ground truth was established by direct measurement via a pulmonary artery catheter, not by expert consensus. The comparison was between the device's output, the predicate device's output, and the pulmonary artery catheter's output.

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

No, an MRMC study was not conducted. This study focused on device performance against a reference standard and comparison to a predicate device, not on the improvement of human reader performance with AI assistance. The device is a "Single-Function, Preprogrammed Diagnostic Computer" that measures physiological parameters.

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

Yes, a standalone performance assessment was conducted implicitly. The "accuracies of the Argos monitor and the predicate device were assessed using the pulmonary artery catheter as the reference." This directly measures the algorithm's output against the ground truth without human intervention in the loop of the measurement process. Human users were involved in setting up and interpreting the device, but the accuracy assessment was of the device's calculated parameters.

7. The Type of Ground Truth Used

The ground truth used for the clinical performance assessment was outcomes data in the form of direct measurements from a pulmonary artery catheter (PAC). The PAC is considered a gold standard for cardiac output measurement.

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set. It only mentions that the algorithm is "proprietary" and based on a "novel signal processing technique."

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

The document does not describe how the ground truth for the training set was established. It focuses on the validation of the device's performance against the predicate and a reference standard.

Ask a specific question about this device

The PulsioFlex Monitoring System is a diagnostic aid for the measurement and monitoring of blood pressure, cardiopulmonary, circulatory and organ function variables. The PulsioFlex Monitoring System is indicated in patients where cardiovascular and circulatory volume status monitoring is necessary. If a patient's data are entered, the PulsioFlex monitor presents the derived parameters indexed.

With the PiCCO Module cardiac output is determined both continuously through pulse contour analysis and intermittently through thermodilution technique. Both are used for the determination of other derived parameters.

With the CeVOX oximetry module connected to a compatible oximetry probe, the PulsioFlex Monitoring System measures continuous venous oxygen saturation to assess oxygen delivery and consumption.

The use of the PulsioFlex Monitoring System is indicated in patients where cardiovascular and organ monitoring is useful. This includes patients in surgical, medical, and other hospital units.

The PulsioFlex Monitoring System is a patient monitoring system that consists of the following components:
a) PulsioFlex Monitor
b) CeVOX Optical Module
c) PICCO Module

The PulsioFlex Monitor receives incoming signals from the patient through the connections with the modules and the accessories applied to the patient. The measurement hardware in the PulsioFlex Monitoring System provides the PulsioFlex host application (software) all data from the modules via USB protocol. The algorithms embedded in the monitor host application process the signals and provide parameter calculations. Based on the patient's biometric data, the PulsioFlex Monitor presents the derived parameters indexed.

The provided text is a 510(k) Premarket Notification for the PulsioFlex Monitoring System. This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving the device meets specific acceptance criteria through a clinical study or a study solely proving the algorithm's performance.

Therefore, the information required to answer the prompt cannot be fully extracted from the provided text. The document states: "Clinical data was not required for this device." and the "Performance Data" section primarily addresses system verification, electrical safety, software verification, cybersecurity, and usability testing, all aimed at demonstrating that updates do not adversely affect safety and effectiveness compared to the predicate device.

Here's a breakdown of why each section of your request cannot be fully answered and what little information is available:

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

• Cannot be provided. The document does not specify quantitative acceptance criteria for new derived parameters or overall device performance in the form of a table. Its focus is on showing equivalence for already cleared parameters and verifying the functionality of newly added derived parameters (GEF, CPO, PVPI, O2ER, and ITBV) which are calculated from previously cleared parameters. The performance data section refers to "measurements of Cardiac Output parameters and Oximetry parameters were performed with the subject device," but does not provide specific values or acceptance criteria for these measurements.

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

• Not applicable/Not provided. Since "Clinical data was not required," there isn't a test set of patient data in the typical sense for evaluating diagnostic accuracy or algorithm performance derived from patient outcomes. The "System Verification" describes testing "individual modules... at a system level," but this refers to technical verification, not a clinical data test set.

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/Not provided. As no clinical data test set was required or used for direct performance evaluation, there was no need for expert-established ground truth.

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

• Not applicable/Not provided. No clinical test set to adjudicate.

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/Not provided. This is not a study of AI assistance to human readers. It's a monitoring system that calculates physiological parameters.

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

• Partially applicable, but no detailed performance metrics. The document states that new derived parameters are "calculated by the PulsioFlex Monitors host application (software) based on the previous cleared parameters." This implies algorithm-only performance for these calculations. However, no specific performance metrics (e.g., accuracy against a gold standard for these calculated parameters) or a stand-alone study showing statistical results are provided. The "System Verification" section mentions "Measurements of Cardiac Output parameters and Oximetry parameters were performed with the subject device," but provides no details on the study design or results.

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

• Not explicitly stated for the "new derived parameters." Given that they are "calculated by the PulsioFlex Monitors host application (software) based on the previous cleared parameters," the implicit ground truth for the calculation logic would be physiological principles and mathematical correctness, likely verified through internal testing against known inputs and expected outputs, rather than clinical outcomes or expert consensus on raw patient data. For the original parameters, the ground truth would have been established during the predicate device's clearance.

8. The sample size for the training set:

• Not applicable/Not provided. This device is not described as being based on a machine learning model that requires a "training set" in the common sense (e.g., for image recognition). The "algorithms" mentioned process signals and calculate parameters, implying deterministic algorithms, not learned from a training dataset.

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

• Not applicable/Not provided. (See point 8).

In summary, the provided document is a regulatory submission for a device modification, demonstrating substantial equivalence. It does not contain the kind of detailed performance study data, acceptance criteria, ground truth establishment methods, or sample sizes related to clinical validation of AI algorithms or diagnostic accuracy that your prompt requests.

Ask a specific question about this device

The LiDCOunity Monitor is intended for use under the direct supervision of a licensed healthcare or by personnel trained in its proper use for:

1. The measurement of blood pressure, cardiac output and associated hemodynamic parameters in adult patients.

2. When connected to the BIS Module: monitoring the state of the brain by data acquisition of EEG signals and 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.

3. When connected to the LiDCO CNAP Module it may be used for the continuous, non-invasive monitoring of arterial blood pressure in adults and pediatric (>4yrs) patients by medical professionals. The LiDCO CNAP Module is intended for use with the LiDCOunity Monitor

4. The measurement of cardiac output via Lithium Indicator Dilution in adult patients (>40Kg/88lbs) with pre-inserted arterial and venous catheters, and for monitoring continuous blood pressure and cardiac output in patients with preexisting peripheral arterial line access

5. In addition to arterial blood pressure parameters and cardiac output, the LiDCOunty Monitor of derived parameters: Body Surface Area, Pulse Pressure Variation, Stroke Volume Variation, Cardiac Index, Stroke Volume, Stroke Volume Index, Systemic Vascular Resistance, Systemic Vascular Resistance Index, Oxygen Delivery/ Index

Location of Use: Suitable patients will be receiving treatment in the following areas: Medical and Surgical Intensive Care Units Operative Suites Step Down / High Dependency Units Trauma/Accident & Emergency Departments Coronary Intensive Care Units Cardiac Catheter Laboratories

Not Found

I am sorry, but the provided text from the FDA 510(k) K163334 document for the LiDCOunity v2 Hemodynamic Monitor does not contain any information regarding acceptance criteria or the study that proves the device meets acceptance criteria in the context of an AI/ML-based medical device.

The document is a clearance letter and the "Indications for Use" statement for a non-AI/ML medical device. It focuses on:

• Substantial Equivalence Determination: The FDA has determined the LiDCOunity v2 Monitor is substantially equivalent to legally marketed predicate devices.
• Regulatory Information: Details about its classification (Class II), product codes, and applicable regulations.
• Indications for Use: What the device is intended to measure (blood pressure, cardiac output, EEG signals with BIS Module, continuous non-invasive arterial blood pressure with CNAP Module, etc.) and where it is intended to be used.
• General Controls: Mentions general controls like annual registration, listing, good manufacturing practice, and labeling.

It does not describe:

• Acceptance criteria in a quantitative sense (e.g., specific metrics like accuracy, sensitivity, specificity, AUC).
• A "study" with a test set, training set, ground truth, experts, or statistical analysis.
• Any mention of AI, machine learning, or algorithms that would require such a study as per your request parameters.
• Any comparative effectiveness studies with or without human-in-the-loop for an AI component.

Therefore, I cannot fulfill your request using the provided text. To answer your questions, I would need a document that details the validation study of an AI/ML medical device.

Ask a specific question about this device

The LiDCOunity Monitor is intended for use under the direct supervision of a licensed healthcare practitioner or by personnel trained in its proper use for:

1. The measurement of blood pressure, cardiac output and associated hemodynamic parameters in adult patients.
2. When connected to the BIS Module: monitoring the state of the brain by data acquisition of EEG signals and 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.
3. When connected to the LiDCO CNAP Module it may be used for the continuous, non-invasive monitoring of arterial blood pressure in adults and pediatric (>4yrs) patients by medical professionals. The LiDCO CNAP Module is intended for use with the LiDCOunity Monitor
4. The measurement of cardiac output via Lithium Indicator Dilution in adult patients (>40Kg/88lbs) with pre-inserted arterial and venous catheters, and for monitoring continuous blood pressure and cardiac output in patients with pre-existing peripheral arterial line access
5. In addition to arterial blood pressure parameters and cardiac output, the LiDCOunity Monitor calculates a number of derived parameters: Body Surface Area, Pulse Pressure Variation, Stroke Volume Variation, Cardiac Index, Stroke Volume, Stroke Volume Index, Systemic Vascular Resistance, Systemic Vascular Resistance Index, Oxygen Delivery/Index

Not Found

The provided text is a 510(k) premarket notification approval letter for the "LiDCOunity Monitor." It details the device's intended uses and regulatory classification but does not contain information about acceptance criteria or a study proving the device meets these criteria in the context of an AI/ML medical device.

The document describes a traditional medical device (monitor for physiological parameters) and its substantial equivalence to previously marketed predicate devices. It focuses on regulatory approval based on the device's functional capabilities, not on performance metrics of an AI/ML algorithm against a ground truth.

Therefore, I cannot extract the requested information using the provided text. The questions assume the context of an AI/ML device study, which is not what this document describes.

Ask a specific question about this device

The intended use of the ELSA system is to provide clinically relevant data to healthcare providers treating neonatal, pediatric, adult patients with arterial and venous lines for routine monitoring of diagnostic parameters: Delivered Flow; Recirculation: Oxygenator Blood Volume and other associated hemodynamic parameters.

In accordance with section 510(k) for the Federal Food, Drug, and Cosmetic Act, Transonic Systems Inc. intends to introduce into interstate commerce the Transonic ELSA system, which is an apparatus based on transit time ultrasound indicator dilution techniques that provides clinically relevant data to healthcare providers treating patients undergoing Extracorporeal Life Support Procedures. The clinically relevant data (such as delivered flow, recirculation, oxygenator blood volume and other related hemodynamic parameters), shall indicate the efficacy of such procedures and quantify the patient's hemodynamic status. These patients could be in the intensive care units (ICU), operating room (OR) or other such environments.

The provided text includes a 510(k) summary for the Transonic ELSA System, outlining its substantial equivalence to predicate devices and detailing bench testing. However, it does not contain the specific acceptance criteria or the full study details to definitively answer all parts of your request.

Here's what can be extracted and what information is missing:

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

The document states: "The ELSA system (HCE101) is deemed to be safe and effective based on the safety testing conducted in accordance with the IEC 60601-1 standard and the electromagnetic compatibility test report." and "Prior to shipment, the finished product will be tested and must meet all required release specifications before distribution."

• Acceptance Criteria (General): Safe and effective; compliance with IEC 60601-1 standard; electromagnetic compatibility test report; meeting all required release specifications (physical testing and visual examination).
• Reported Device Performance: No specific numerical performance metrics (e.g., accuracy, precision, sensitivity, specificity) against defined acceptance criteria are provided in this summary. It states "These tests are established testing procedures that ensure the product's performance parameters conform to the product design specifications," but doesn't list the parameters or their achieved values.

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

• Sample Size: Not specified in the provided text.
• Data Provenance: Not specified in the provided text. The testing mentioned is "bench testing," meaning it was likely conducted in a laboratory setting. No patient data provenance is mentioned.

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)

• Number of Experts: Not applicable/not specified. The testing described is bench testing, not a clinical study involving experts establishing ground truth from patient data.
• Qualifications of Experts: Not applicable/not specified.

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

• Adjudication Method: Not applicable/not specified. This is typically relevant for clinical studies involving multiple readers, which is not described 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

• No MRMC study is mentioned. This device is described as a diagnostic monitor, not an AI-assisted diagnostic tool for human readers.

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

• The testing described is "bench testing" focusing on safety, electromagnetic compatibility, and conformity to product design specifications. This implies standalone device performance testing, but the specific metrics are not detailed.

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

• For the bench testing, the "ground truth" would likely be instrument calibration standards, reference measurements (e.g., using established flow meters), or predefined physical standards for visual and physical examinations. No patient-derived ground truth (like expert consensus or pathology) is mentioned because this was bench testing, not a clinical study.

8. The sample size for the training set

• Sample Size: Not applicable. The document describes a medical device, not a machine learning or AI model that requires a "training set."

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

• Ground Truth Establishment: Not applicable, as there is no mention of a training set for a machine learning model.

Ask a specific question about this device