Search Results

• HemoSphere Advanced Monitor with HemoSphere Swan-Ganz Module: The HemoSphere advanced monitor when used with the HemoSphere Swan-Ganz module and Edwards Swan-Ganz catheters is indicated for use in adult and pediatric critical care patients requiring monitoring of cardiac output (continuous [CO] and intermittent [iCO]) and derived hemodynamic parameters in a hospital environment. Pulmonary artery blood temperature monitoring is used to compute continuous and intermittent CO with thermodilution technologies. It may also be used for monitoring hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol in a hospital environment. Refer to the Edwards Swan-Ganz catheter and Swan-Ganz Jr catheter indications for use statements for information on target patient population specific to the catheter being used. Refer to the Intended Use statement for a complete list of measured and derived parameters available for each patient population.

• HemoSphere Advanced Monitor with HemoSphere Oximetry Cable: The HemoSphere Advanced Monitor when used with the HemoSphere Oximetry Cable and Edwards oximetry catheters is indicated for use in adult and pediatric critical care patients requiring monitoring of venous oxygen saturation (SvO2 and ScvO2) and derived hemodynamic parameters in a hospital environment. Refer to the Edwards oximetry catheter indications for use statement for information on target patient population specific to the catheter being used. Refer to the Intended Use statement for a complete list of measured and derived parameters available for each patient population.

• HemoSphere Advanced Monitor with HemoSphere Pressure Cable: The HemoSphere advanced monitor when used with the HemoSphere pressure cable is indicated for use in adult and pediatric critical care patients in which the balance between cardiac function, fluid status, vascular resistance and pressure needs continuous assessment. It may be used for monitoring of hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol in a hospital environment. Refer to the Edwards FloTrac sensor, FloTrac Jr sensor, Acumen IQ sensor, and TruWave disposable pressure transducer indications for use statements for information on target patient populations specific to the sensor/transducer being used. The Edwards Acumen Hypotension Prediction Index software feature provides the clinician with physiological insight into a patient's likelihood of future hypotensive events and the associated hemodynamics. The Acumen HPI feature is intended for use in surgical or non-surgical patients receiving advanced hemodynamic monitoring. The Acumen HPI feature is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Acumen Hypotension Prediction Index (HPI) parameter. Refer to the Intended Use statement for a complete list of measured and derived parameters available for each patient population.

• HemoSphere Advanced Monitor with Acumen Assisted Fluid Management Feature and Acumen IQ Sensor: The Acumen Assisted Fluid Management (AFM) software feature provides the clinician with physiological insight into a patient's estimated response to fluid therapy and the associated hemodynamics. The Acumen AFM software feature is intended for use in surgical patients >=18 years of age, that require advanced hemodynamic monitoring. The Acumen AFM software feature offers suggestions regarding the patient's physiological condition and estimated response to fluid therapy. Acumen AFM fluid administration suggestions are offered to the clinician; the decision to administer a fluid bolus is made by the clinician, based upon review of the patient's hemodynamics. No therapeutic decisions should be made based solely on the Assisted Fluid Management suggestions. The Acumen Assisted Fluid Management software feature may be used with the Acumen AFM Cable and Acumen IQ fluid meter.

• HemoSphere Advanced Monitor with HemoSphere Technology Module and ForeSight Oximeter Cable: The non-invasive ForeSight oximeter cable is intended for use as an adjunct monitor of absolute regional hemoglobin oxygen saturation of blood under the sensors in individuals at risk for reduced-flow or no flow ischemic states. The ForeSight Oximeter Cable is also intended to monitor relative changes of total hemoglobin of blood under the sensors. The ForeSight Oximeter Cable is intended to allow for the display of StO2 and relative change in total hemoglobin on the HemoSphere advanced monitor.

  • When used with large sensors, the ForeSight Oximeter Cable is indicated for use on adults and transitional adolescents >=40 kg.
  • When used with medium sensors, the ForeSight Oximeter Cable is indicated for use on pediatric subjects >=3 kg.
  • When used with small sensors, the ForeSight Oximeter Cable is indicated for cerebral use on pediatric subjects

The HemoSphere Advanced Monitor was designed to simplify the customer experience by providing one platform with modular solutions for all hemodynamic monitoring needs. The user can choose from available optional sub-system modules or use multiple sub-system modules at the same time. This modular approach provides the customer with the choice of purchasing and/or using specific monitoring applications based on their needs. Users are not required to have all of the modules installed at the same time for the platform to function.

The provided FDA 510(k) clearance letter and summary for the Edwards Lifesciences HemoSphere Advanced Monitor (HEM1) and associated components outlines the device's indications for use and the testing performed to demonstrate substantial equivalence to predicate devices. However, it does not contain the detailed acceptance criteria or the specific study results (performance data) in the format typically required to answer your request fully, especially for acceptance criteria and performance of an AI/algorithm-based feature like the Hypotension Prediction Index (HPI) or Assisted Fluid Management (AFM).

The document states:

• "Completion of all verification and validation activities demonstrated that the subject devices meet their predetermined design and performance specifications."
• "Measured and derived parameters were tested using a bench simulation. Additionally, system integration and mechanical testing was successfully conducted to verify the safety and effectiveness of the device. All tests passed."
• "Software verification testing was conducted, and documentation was provided per FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices". All tests passed."

This indicates that internal performance specifications were met, but the specific metrics, thresholds, and study designs for achieving those specifications are not detailed in this public summary.

Therefore, I cannot populate the table with specific numerical performance data against acceptance criteria for the HPI or AFM features, nor can I provide details on sample size, expert ground truth establishment, or MRMC studies, as this information is not present in the provided text.

The text primarily focuses on:

• Substantial equivalence to predicate devices.
• Indications for Use for various HemoSphere configurations and modules.
• Description of software and hardware modifications (e.g., integration of HPI algorithm, new finger cuffs).
• General categories of testing performed (Usability, System Verification, Electrical Safety/EMC, Software Verification) with a blanket statement that "All tests passed."

Based on the provided document, here's what can and cannot be stated:

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

Cannot be provided with specific numerical data or thresholds from the given text. The document only states that "all verification and validation activities demonstrated that the subject devices meet their predetermined design and performance specifications." No specific acceptance criteria values (e.g., "Accuracy > X%", "Sensitivity > Y%", "Mean Absolute Error

Ask a specific question about this device

HemoSphere Alta™ Advanced Monitor with Swan-Ganz Technology
The HemoSphere Alta monitor when used with the HemoSphere Alta Swan-Ganz patient cable and Edwards Swan-Ganz catheters is indicated for use in adult and petical care patients requiring monitoring of cardiac output (continuous [CO] and intermittent [iCO]) and derived hemodynamic parameters in a hospital environment. Pulmonary artery blood temperature monitoring is used to compute continuous and intermittent CO with thermodilution technologies. It may be used for monitoring hemodynamic parameters in conjunction with a perioperative goal directed in a hospital environment. Refer to the Edwards Swan-Ganz Ir catheter indications for use statement for information on target patient population specific to the catheter being used.

The Global Hypoperfusion Index (GHI) algorithm provides the clinician with physiological insight into a patient's likelihood of future hemodynamic instability. The GHI algorithm is intended for use in surgical or non-surgical patients receiving advanced hemodynamic monitoring with the Swan-Ganz catheter. The GHI algorithm is considered to provide additional information regarding the patient's predicted future risk for clinical deterioration, as well as identifying patients at low risk for deterioration. The product predictions are for reference only and no therapeutic decisions should be made based solely on the GHI algorithm predictions.

When used in combination with a Swan-Ganz catheter connected to a pressure transducer, the Edwards Lifesciences Smart Wedge algorithm measures and provides pulmonary artery occlusion pressure and assesses the quality of the pulmonary artery occlusion pressurement. The Smart Wedge algorithm is indicated for use in critical care patients over 18 years of age receiving advanced hemodynamic monitoring. The Smart Wedge algorithm is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Smart Wedge algorithm parameters.

HemoSphere Alta Advanced Monitor with HemoSphere Oximetry Cable
The HemoSphere Alta monitor when used with the HemoSphere oximetry cable and Edwards oximetry catheters is indicated for use in adult and pediatric critical care patients requiring of venous oxygen saturation (SvO2 and ScvO2) and derived hemodynamic parameters in a hospital environment. Refer to the Edwards oximetry catheter indications for use statement for information on target patient population specific to the catheter being used.

HemoSphere Alta Advanced Monitor with HemoSphere Pressure Cable or HemoSphere Alta Monitor Pressure Cable
The HemoSphere Alta monitor when used with the HemoSphere Pressure Cable or HemoSphere Alta monitor Pressure cable is indicated for use in adult and pediatric critical care patients in which the balance between cardiac fluid status, vascular resistance and pressure needs continuous assessment. It may be used for monitoring hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol in a hospital environment. Refer to the Edwards FloTrac, FloTrac Jr, Acumen IQ, and TruWave DPT sensor indications for use statement for information on target patient population specific to the sensor being used.

The Edwards Lifesciences Acumen Hypotension Prediction Index software feature provides the clinician with physiological insight into a patient's likelihood of future hypotensive events and the associated hemodynamics. The Acumen HPI feature is intended for use in surgical patients receiving advanced hemodynamic monitoring. The Acumen HPI feature is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Hypotension Prediction Index (HPI) parameter.

When used in combination with the Swan-Ganz technology connected to a compatible Swan-Ganz catheter, the Edward Lifesciences Right Ventricular Pressure (RVP) algorithm provides the clinician with physiological insight into the hemodynamic status of the right ventricle of the heart. The RVP algorithm is indicated for critically ill patients over 18 years of age receiving advanced hemodynamic monitoring in the operating room (OR) and intensive care unit (ICU). The RVP algorithm is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Right Ventricular Pressure (RVP) parameters.

When used in combination with the HemoSphere Pressure Cable connected to a compatible Swan-Ganz catheter, the Right Ventricular Cardiac Output (RVCO) feature provides the clinician with physiological insight into the hemodynamic status of the right ventricle of the heart. The RVCO algorithm is intended for use in surgical patients over 18 years of age that require advanced hemodynamic monitoring. The Right Ventricular Cardiac a continuous cardiac output and derived parameters.

The Cerebral Adaptive Index (CAI) Algorithm is an informational index to help assess the level of coherence or lack thereof between Mean Arterial Pressure (MAP) and the Absolute Levels of Blood Oxygenation Saturation (StO2) in patient's cerebral tissue. MAP is acquired by the HemoSphere pressure cable or HemoSphere Alta Pressure Cable and StO2 is acquired by the ForeSight oximeter cable. CAI is intended for use in patients over 18 years of age receiving advanced hemodynamic monitoring. CAI is not indicated to be used for treatment of any disease or condition and no therapeutic decisions should be made based solely on the Cerebral Adaptive Index (CAI) Algorithm.

HemoSphere Alta Advanced Monitor with Acumen Assisted Fluid Management Feature and Acumen IQ Sensor
The Acumen assisted fluid management (AFM) software feature provides the clinician with physiological insight into a patient's estimated response to fluid therapy and the associated hemodynamics. The Acumen AFM software feature is intended for use in surgical patients ≥18 years of age, that require advanced hemodynamic monitoring. The Acumen AFM software feature offers suggestions regarding the patient's physiological condition and estimated response to fluid therapy.

Acumen AFM fluid administration suggestions are offered to the clinician; the decision to administer a fluid bolus is made by the clinician, based upon review of the patient's hemodynamics. No therapeutic decisions should be made based solely on the assisted fluid management suggestions.

Acumen IQ Fluid Meter
The Acumen IQ fluid meter is a sterile single use device that is intended to be used with the HemoSphere Alta AFM cable and AFM software feature to inform the user of the rate of flow. The device is intended to be used by qualified personnel or clinicians in a clinical setting for up to 24 hours.

HemoSphere Alta Advanced Monitor with ForeSight Oximeter Cable
The non-invasive ForeSight oximeter cable is intended for use as an adjunct monitor of absolute regional hemoglobin oxygen saturation of blood under the sensors in individuals at risk for reduced flow or no-flow ischemic states. The ForeSight oximeter cable is also intended to monitor relative changes of total hemoglobin of blood under the sensors. The ForeSight oximeter cable is intended to allow for the display of StO2 and relative change in total hemoglobin on the HemoSphere Alta monitor.

• When used with large sensors, the ForeSight Oximeter Cable is indicated for use on adults and transitional adolescents ≥40 kg.
· When used with Medium Sensors, the ForeSight Oximeter Cable is indicated for use on pediatric subjects ≥3 kg.
· When used with Small Sensors, the ForeSight Oximeter Cable is indicated for cerebral use on pediatric subjects

The HemoSphere Alta Advanced Monitoring Platform is Edwards' next-generation platform that provides a means to interact with and visualize hemodynamic and volumetric data on a screen. It incorporates a comprehensive view of patient hemodynamic parameters with an intuitive and easy user interface. The HemoSphere Alta Advanced Monitoring Platform is designed to provide monitoring of cardiac flow with various core technologies coupled with other technologies-based features such as Algorithms and Interactions. It integrates Edwards existing Critical Care technologies into a unified platform.

The Right Ventricular Cardiac Output (RVCO) feature is a machinelearning algorithm that calculates and displays continuous cardiac output (CORV) from the right ventricle using as inputs the right ventricular pressure waveform and derived right ventricular pressure parameters such as SYSRVF, DIARVP, MRVP, RVEDP, PRRV and Max RV dP/dt from the existing Right Ventricular Pressure (RVP) algorithm and if available, intermittent cardiac output (iCO).

The provided text describes the HemoSphere Alta Advanced Monitoring Platform and its various features, as well as the testing conducted to support its 510(k) clearance. However, it does not contain specific acceptance criteria and detailed device performance data in the format of a table, nor does it provide a detailed study that proves the device meets specific acceptance criteria for any of its algorithms.

The document makes general statements about testing, such as:

• "Completion of all verification and validation activities demonstrated that the subject devices meet their predetermined design and performance specifications."
• "Measured and derived parameters were tested using a bench simulation."
• "All tests passed."
• "Software verification testing were conducted, and documentation was provided per FDA's Guidance..." "All tests passed."
• "Usability study was conducted per FDA's guidance document... The usability study demonstrated that the intended users can perform primary operating functions and critical tasks of the system without any usability issues that may lead to patient or user harm."

While it mentions the Right Ventricular Cardiac Output (RVCO) algorithm as a new algorithm and states that "clinical data (waveforms) were collected in support of the design and validation of the RVCO algorithm," it does not present the detailed results of this validation study, nor does it define specific acceptance criteria for the RVCO algorithm and its performance against those criteria.

Therefore,Based on the provided text, I cannot provide the requested information in the form of a table of acceptance criteria and reported device performance for any specific algorithm, nor can I describe a detailed study that proves the device meets these criteria. The document contains general statements about testing and compliance but lacks the specific quantitative data and study design details needed to answer all aspects of your request.

To provide a complete answer, specific study reports and performance data would be required, which are not present in the provided FDA 510(k) summary.

Ask a specific question about this device

The Edwards Lifesciences Acumen Assisted Fluid Management (AFM) Software Feature provides the clinician with physiological insight into a patient's estimated response to fluid therapy and the associated hemodynamics. The Acumen AFM Software Feature is intended for use in surgical patients ≥18 years of age, that require advanced hemodynamic monitoring. The Acumen AFM Software Feature offers suggestions regarding the patient's physiological condition and estimated response to fluid therapy. Acumen AFM fluid administration suggestions are offered to the clinician; the decision to administer a fluid bolus is made by the clinician, based upon review of the patient's hemodynamics. No therapeutic decisions should be made based solely on the Assisted Fluid Management suggestions.

The Acumen AFM Software Feature (core AFM algorithm + AFM Graphical User Interface) was originally granted in De Novo, DEN190029, on November 13, 2020, to inform clinicians about a patient's fluid responsiveness. The performance of the AFM Software Feature in predicting a patient's fluid responsiveness is measured using response rate and is calculated by reporting the percentage of followed AFM recommendations ("Fluid Bolus Suggested" and "Test Bolus Suggested" prompts) that have the desired change in stroke volume (SV), divided by the total number of AFM recommendations.

With this submission, Edwards is seeking clearance for the AFM Prompt Reclassifier algorithm (AFM PR algorithm) to the Acumen AFM Software Feature. The AFM Prompt Reclassifier algorithm is intended to be used in conjunction with the core AFM algorithm to re-assess the fluid bolus recommendations provided by the core alqorithm. It analyzes the patient's current hemodynamics for either confirming (corroborating) the original prompt or reclassifying the prompts (i.e., reclassify a "Test Bolus Suggested" prompt to a "Fluid Bolus Suggested" prompt or vice versa). In doing so, it acts as a secondary check for the fluid bolus prompts such that a greater number of the "Fluid Bolus Suggested" prompts lead to the desired change in stroke volume. Through refined prompt adjustments informed by real-time hemodynamic data, the AFM PR algorithm aims to improve patient responsiveness, thereby optimizing the impact of the AFM Software Feature on patient hemodynamics.

The FDA 510(k) summary for the Acumen Assisted Fluid Management (AFM) Software Feature describes the acceptance criteria and the study conducted to demonstrate the device meets these criteria.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The algorithm performance was analyzed on an archived dataset consisting of 1229 data points from 307 patients.
• Data Provenance: The data came from the US IDE Study, G170204. The study involved 9 independent U.S. sites. The data is retrospective as it was an "archived dataset."

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

• This information is not provided in the document. The study uses physiological response (change in stroke volume) as the outcome measure, implying a physiological ground truth rather than expert interpretation of images or other data.

4. Adjudication Method for the Test Set

• This information is not provided in the document. Given the nature of the ground truth (physiological response), a traditional adjudication method for subjective assessments might not be directly applicable.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• A MRMC comparative effectiveness study was not explicitly mentioned or described.
• The study focuses on the algorithm's performance in improving the response rate of its suggestions, rather than comparing human reader performance with and without AI assistance. The device offers "suggestions" and the "decision to administer a fluid bolus is made by the clinician."

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

• Yes, a standalone algorithm performance study was done. The document states, "Algorithm performance was analyzed on the archived dataset... The validation was to demonstrate the impact on the response rate of the AFM Software Feature's fluid bolus prompts due to the addition of AFM Prompt Reclassifier algorithm." This implies evaluating the algorithm's predictions against the measured physiological outcomes.

7. The Type of Ground Truth Used

• The ground truth used is physiological response/outcomes data. Specifically, the "desired change in stroke volume (SV)" following AFM recommendations was used to measure the "response rate."

8. The Sample Size for the Training Set

• The document does not explicitly state the sample size for the training set. It only mentions the "archived dataset from the US IDE Study, G170204" used for algorithm performance analysis/validation.

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

• The document does not explicitly describe how the ground truth for the training set was established. It focuses on the validation of the AFM Prompt Reclassifier algorithm using an existing dataset. Given that the core AFM algorithm was granted in De Novo DEN190029, the ground truth for its original training would likely have involved similar physiological outcome data from clinical studies where fluid administration decisions were made and subsequent stroke volume changes were observed.

Ask a specific question about this device

The HemoSphere Alta monitor when used with the HemoSphere Alta Swan-Ganz patient cable and Edwards Swan-Ganz catheters is indicated for use in adult and pediatic critical care patients requiring of cardiac output (continuous [CO] and intermittent [CO]) and derived hemodynamic parameters in a hospital environment. Pulmonary artery blood temperature monitoring is used to compute continuous and intermittent CO with thermodilution technologies. It may be used for monitoring hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol in a hospital environment. Refer to the Edwards Swan-Ganz catheter indications for use statement for information on target patient population specific to the catheter being used.

The Global Hypoperfusion Index (GHI) algorithm provides the clinician with physiological insight into a patient's likelihood of future hemodynamic instability. The GHI algorithm provides the risk of a global hypoperfusion event (defined as SvO2 ≤ 60% for at least 1 minute) occurring in the next 10-15 minutes. The GHI algorithm is intended for use in surgical or non-surgical patients receiving advanced hemodynamic monitoring with the Swan-Ganz catheter. The GHI algorithm is considered to provide additional information regarding the patient's predicted future risk for clinical deterioration, as well as identifying patients at low risk for deterioration. The product predictions are for reference only and no therapeutic decisions should be made based solely on the GHI algorithm predictions.

HemoSphere Alta monitor with HemoSphere Oximetry Cable

The HemoSphere Alta monitor when used with the HemoSphere oximetry cable and Edwards oximetry catheters is indicated for use in adult and pediatric crtical care patients requring of venous oxygen saturation (SvO2 and ScvO2) and derived hemodynamic parameters in a hospital environment. Refer to the Edwards oximetry catheter indications for use statement for information on target patient population specific to the catheter being used. Refer to the Intended Use statement for a complete list of measured and derived parameters available for each patient population.

HemoSphere Alta Monitor with HemoSphere Pressure Cable

The HemoSphere Alta monitor when used with the HemoSphere pressure cable is indicated for use in critical care patients in which the balance between cardiac function, fluid status, vascular resistance and pressure needs continuous assessment. It may be used for monitoring of hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol in a hospital environment. Refer to the Edwards FloTrac sensor, Acumen IQ sensor, and TruWave DPT indications for use statements for information on target patient populations specific to the sensor/transducer being used.

The Edwards 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 HemoSphere Alta™ Advanced Monitoring Platform is Edwards' next-Device generation platform that provides a means to interact with and visualize Description: hemodynamic and volumetric data on a screen. The HemoSphere Alta™ Monitoring Platform provides an improved user interface utilizing the existing Edwards technologies and algorithms commercially available in the HemoSphere Advanced Monitoring Platform.

This FDA 510(k) summary for the Edwards Lifesciences HemoSphere Alta Advanced Monitoring Platform (K232294) primarily focuses on demonstrating substantial equivalence to predicate devices through technical comparisons and non-clinical performance validation. It explicitly states that "No new clinical testing was performed in support of the subject 510(k)." As such, the document does not provide specific acceptance criteria for AI/algorithm performance or details of a study proving the device meets such criteria through clinical data.

Instead, the submission emphasizes the device's functional and safety aspects, along with the integration of existing, previously cleared technologies and algorithms into a new hardware and software platform with an improved user interface.

Therefore, many of the requested sections below cannot be fully answered based on the provided text, as the focus was on non-clinical verification and substantial equivalence rather than new clinical performance studies for AI/algorithm features.

1. Table of Acceptance Criteria and Reported Device Performance

As per the provided document, specific acceptance criteria and detailed device performance metrics for individual AI/algorithm features (like HPI, GHI, AFM, RVP) are not detailed as part of a new clinical study for this 510(k) submission. The submission states, "No new clinical testing was performed in support of the subject 510(k)." The "Performance Data" section primarily discusses non-clinical verification.

The document states:

• "Completion of all verification and validation activities demonstrated that the subject devices meet their predetermined design and performance specifications."
• "Measured and derived parameters were tested using a bench simulation."
• "System integration and mechanical testing was successfully conducted to verify the safety and effectiveness of the device. All tests passed."
• "Software verification testing were conducted... All tests passed."

This indicates that internal performance specifications were met, but these specifications themselves are not provided, nor is the performance against them quantified in this public summary.

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

No test set for clinical performance of AI/algorithm features is described, as "No new clinical testing was performed." The device leverages existing, previously cleared algorithms.

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

Not applicable, as no new clinical test set for AI/algorithm performance is described. The AI/algorithm features leverage ground truth established in prior clearances for the predicate devices.

4. Adjudication Method for the Test Set

Not applicable, as no new clinical test set for AI/algorithm performance is described.

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

No MRMC comparative effectiveness study is mentioned, as "No new clinical testing was performed." The submission focuses on the HemoSphere Alta platform being a new generation integrating existing Edwards technologies and algorithms with an improved user interface and hardware.

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

The document does not describe new standalone performance studies for the AI/algorithm features. The AI/algorithm features (HPI, GHI, AFM, RVP) themselves were likely evaluated in standalone fashion during their original predicate clearances (e.g., K231038 for GHI). This 510(k) integrates these existing algorithms into a new platform.

7. Type of Ground Truth Used

The type of ground truth for the AI/algorithm features (HPI, GHI, AFM, RVP) would have been established during their original clearances. For this 510(k) submission, this information is not provided. Typically, hemodynamic algorithms like HPI or GHI rely on physiological measurements (e.g., direct arterial pressure, SvO2 from Swan-Ganz catheter, outcomes data related to hypotension or hypoperfusion events) as ground truth.

8. Sample Size for the Training Set

No details regarding training set sample sizes for the AI/algorithm features are provided in this 510(k) summary, as it covers the integration of existing algorithms. The training data would have been described in the original 510(k) submissions for those predicate algorithms (e.g., for Acumen HPI feature, Global Hypoperfusion Index, Right Ventricular Pressure algorithm, Acumen Assisted Fluid Management).

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

As with the training set size, the method for establishing ground truth for the training set of the AI/algorithm features is not detailed in this 510(k) summary because it pertains to existing algorithms. This would have been covered in their individual predicate 510(k) submissions.

Ask a specific question about this device

HemoSphere Advanced Monitor with HemoSphere Swan-Ganz Module:
The HemoSphere Advanced Monitor when used with the HemoSphere Swan-Ganz Module and Edwards Swan-Ganz Catheters is indicated for use in adult and pediatric critical care patients requiring monitoring of cardiac output [continuous (CO) and intermittent (iCO)] and derived hemodynamic parameters. Pulmonary artery blood temperature monitoring is used to compute continuous and intermittent CO with thermodilution technologies. It may also be used for monitoring hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol in a hospital environment. Refer to the Edwards Swan-Ganz catheter indications for use statement for information on target patient population specific to the catheter being used. Refer to the Edwards Swan-Ganz catheter indications for use statement for information on target patient population specific to the catheter being used.
Refer to the Intended Use statement for a complete list of measured and derived parameters available for each patient population.

HemoSphere Advanced Monitor with HemoSphere Oximetry Cable:
The HemoSphere Advanced Monitor when used with the HemoSphere Oximetry catheters is indicated for use in adult and pediatric critical care patients requiring of venous oxygen saturation (SvO2 and ScvO2) and derived hemodynamic parameters in a hospital environment. Refer to the Edwards oximetry catheter indications for use statement for information on target patient population specific to the catheter being used.
Refer to the Intended Use statement for a complete list of measured and derived parameters available for each patient population.

HemoSphere Advanced Monitor with HemoSphere Pressure Cable:
The HemoSphere Advanced Monitor when used with the HemoSphere Pressure Cable is indicated for use in critical care patients in which the balance between cardiac function, fluid status, vascular resistance and pressure needs continuous assessment. It may be used for monitoring hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol in a hospital environment. Refer to the Edwards FloTrac, Acumen IQ and TruWave DPT sensor indications for use statement for information on target patient population specific to the sensor being used. The Edwards Acumen Hypotension Index feature provides the clinician with physiological insight into a patient's likelihood of future hypotensive events (defined as mean arterial pressure 40 kg.
• When used with Medium Sensors, the ForeSight Oximeter Cable is indicated for use on pediatric subjects ≥3 kg.
• When used with Small Sensors, the ForeSight Oximeter Cable is indicated for cerebral use on pediatric subjects

The HemoSphere Advanced Monitoring platform was designed to simplify the customer experience by providing one platform with modular solutions for their hemodynamic monitoring needs. The user can choose from the available optional sub-system modules or use multiple sub-system modules at the same time. This modular approach provides the customer with the choice of purchasing and/or using specific monitoring applications based on their needs. Users are not required to have all of the modules installed at the same time for the platform to function.
HemoSphere Advanced Monitoring Platform, subject of this submission, consists of the HemoSphere Advanced Monitor that provides a means to interact with and visualize hemodynamic and volumetric data on the monitor screen and its five (5) optional external modules: the HemoSphere Swan-Ganz Module (K163381 cleared, April 14, 2017), the HemoSphere Oximetry Cable (K163381 cleared, April 14, 2017), HemoSphere Pressure Cable (K180881 Cleared, November 16, 2018), HemoSphere Technology Module (K213682 cleared, June 22, 2022), HemoSphere ForeSight Module (K213682, June 22, 2022), and the HemoSphere ClearSight Module (K203687 cleared, May 28, 2021). Additionally, the HemoSphere Advanced Monitoring Platform includes the Acumen Hypotension Prediction Index software feature (DEN160044 granted March 16, 2018) and the Acumen Assisted Fluid Management software feature (DEN190029 granted November 13, 2020). The HemoSphere Advanced Monitor also has wired and wireless capabilities, which was originally used only for connecting to a Hospital Information System (HIS) for data charting purposes. This capability is now used to allow it to stream continuously monitored data to the Viewfinder Remote, a mobile device-based application, for remote viewing the information (K211465, cleared July 8, 2021). The remotely transmitted data from the patient monitoring sessions include all hemodynamic parameter data and the associated physiological alarm notifications, historical trend data, and parameter waveform data.

HemoSphere Advanced Monitoring platform as cleared in K213682 cleared June 22, 2022, is being modified as follows:

1. Acumen Assisted Fluid Management Automated Fluid Tracking Mode:
   The AFM software feature (AFM algorithm + AFM GUI), which informs clinicians of patient fluid responsiveness (K213682, cleared June 22, 2022), allows for manual fluid tracking, and resides on the HemoSphere Advanced Monitor.
   The AFM software feature is being modified to allow for an automated fluid tracking mode as the default mode. Users can switch to the optional manual fluid tracking mode through the advanced settings menu. This automated fluid tracking mode for the AFM software feature is achieved via two components namely, the Acumen AFM Cable and the Acumen IQ fluid meter (both devices subject of this 510(k)). No modifications have been made to the previously cleared AFM algorithm. AFM GUI screens have been updated to account for the automated fluid tracking mode via the Acumen AFM cable and Acumen IO fluid meter.
   The Acumen AFM Cable is a reusable cable that connects the Acumen IO fluid meter to the HemoSphere Advanced Monitoring Platform and converts the flow rate received from the Acumen IQ fluid meter to total volume for the HemoSphere monitor to be used by AFM software feature. No modifications have been made to the previously cleared AFM algorithm. AFM GUI screens have been updated to account for the automatic fluid tracking mode. The Acumen IQ fluid meter is a sterile, single use device that measures the flow of fluid delivered to a patient through the intravenous line to which it is connected.
   When used together, the Acumen IQ fluid meter with the Acumen AFM Cable connected to a HemoSphere monitor, the fluid volume can be automatically tracked and displayed on the monitor as part of the AFM software feature screens.

2. Automatic Zeroing of the Heart Reference Sensor (HRS)
   The ClearSight Module (CSM), initially cleared in K201446 on October 1, 2020, is a non-invasive monitoring platform that includes a Pressure Controller (PC2) that is worn on the wrist, a Heart Reference Sensor (HRS), and the ClearSight/Acumen IQ Finger Cuffs.
   The Pressure Controller (also referred to as 'Wrist unit' or PC2) is connected to the patient via a wrist band. The Pressure Controller connects to the ClearSight Module (CSM) on one end and with the Heart Reference Sensor (HRS) and the finger cuff on the other. The connection to the CSM provides power and serial communication. The Pressure Controller is designed to control the blood pressure measurement process and send the finger arterial pressure waveform to the CSM. The CSM software transforms the finger level blood pressure measurements into the conventional radial blood pressure.
   In the predicate HemoSphere (K213682, cleared on June 22, 2022), as part of the ClearSight workflow, the user was required to zero the HRS prior to monitoring by aligning both ends of the HRS, the heart end and the finger end, and pressing the "0" button on the HemoSphere Graphical User Interface (GUI). After zeroing the HRS, the user is required to place both ends of the HRS in the appropriate location and then they can begin monitoring.
   For the subject device, the Pressure Controller (PC2) firmware has been updated to include a mathematical model that automatically calculates the zero offset of the HRS based on the age of the specific HRS at the time of use. With the addition of the mathematical model, the user is no longer required to zero the HRS prior to start of monitoring since the system now has the zero-offset calculated. As such, the HemoSphere Advanced Monitor graphical user interface (GUI) was updated to remove the Zero HRS step as part of the Zero & Waveform screen and ClearSight setup.
   The ClearSight Module firmware was also updated as part of support for the Automatic Zeroing of HRS feature. The firmware update included additional logging to support HRS calibration, bug fixes and updates to communication to the pressure controller to support display of proper HRS calibration information.

3. Patient Query
   As cleared in K213682, when the user queried for patient information, all patient records that match the search criteria were sent to the HemoSphere platform (from the Viewfinder Hub) for the user to review. With this update, only 30 records are shared at a time between the Viewfinder Hub and HemoSphere monitor.

4. Miscellaneous Updates
   Miscellaneous updates include:

• Bug fixes -
• Cybersecurity updates -
• Operator's manual updates -
• Heart Reference Sensor Instructions for Use update -

Based on the provided text, the document is a 510(k) Premarket Notification from the FDA to Edwards Lifesciences, LLC, regarding the HemoSphere Advanced Monitor and related components. It does not contain the detailed acceptance criteria and study proving device performance in the way typically required for AI/ML-driven diagnostic devices. This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving a new clinical claim with a standalone performance study.

Therefore, many of the requested details about acceptance criteria, human expert involvement, ground truth, and training set information are not available in this specific regulatory document, as they are not typically required for a 510(k) submission for device modifications like those described here. The "Acumen Assisted Fluid Management software feature" is mentioned, and an "AFM algorithm" is referenced, but detailed studies on its performance metrics are not included in this summary.

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

Acceptance Criteria and Device Performance Study (Partial Information)

This 510(k) notification describes modifications to an existing device (HemoSphere Advanced Monitoring Platform) and new components (Acumen AFM Cable, Acumen IQ fluid meter). The primary goal is to demonstrate substantial equivalence to a previously cleared predicate device (K213682). As such, the performance data presented is focused on verifying that the modifications do not adversely affect safety and effectiveness, rather than establishing new clinical performance metrics or comparing AI performance against human readers.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of predetermined acceptance criteria for AI performance in the way one would for a new AI diagnostic claim (e.g., sensitivity, specificity, AUC). Instead, it lists various verification and validation activities performed to ensure the modified device functions as intended and remains safe and effective.

Summary of Performance Data Presented:

2. Sample Size and Data Provenance for Test Set

• Sample Size: Not specified for any quantitative testing that would typically involve a "test set" in the context of AI model validation (e.g., number of patient cases, number of images). The performance data cited are primarily bench simulations and system-level verification, not a clinical study with a patient test set.
• Data Provenance: Not specified, as no new clinical data or specific patient test sets are described. The reference to "bench simulation" suggests data generated in a lab environment.

3. Number of Experts and Qualifications for Ground Truth

• Not Applicable/Not Provided: Since "No new clinical testing was performed" for this 510(k), there is no mention of expert involvement for establishing ground truth on a clinical test set. The original AFM algorithm clearance (DEN190029) might contain this information, but it's not in this document.

4. Adjudication Method for Test Set

• Not Applicable/Not Provided: No clinical test set described.

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

• No: The document explicitly states, "No new clinical testing was performed." Therefore, no MRMC study was conducted or reported in this submission.

6. Standalone (Algorithm Only) Performance Study

• Partial/Limited: While the document mentions "AFM outputs when the fluid meter mode was unlocked... were tested using a bench simulation," it does not provide quantitative results (e.g., accuracy, precision) for the algorithm's performance in a standalone setting. The focus is on the functionality and safety of the hardware additions (cable, meter) and the automation of fluid tracking for an existing algorithm. The "core predictive algorithm for the Assisted Fluid Management software feature" is stated to be from the predicate device (K213682), which itself refers back to DEN190029.

7. Type of Ground Truth Used

• Not explicitly stated for AI performance: For the "bench simulation" of AFM outputs, the "ground truth" would likely be the known, controlled fluid flow rates programmed into the simulation. No external clinical ground truth (e.g., pathology, long-term outcomes) is described in relation to the AI/AFM performance in this document.

8. Sample Size for Training Set

• Not Provided: The document focuses on demonstrating substantial equivalence of modifications. Information about the training set size for the AI algorithm (Acumen Assisted Fluid Management software feature) would have been part of its original clearance (DEN190029), not this subsequent 510(k) for modifications and new hardware. It mentions: "No modifications have been made to the previously cleared AFM algorithm."

9. How Ground Truth for Training Set Was Established

• Not Provided: Similar to point 8, this information would pertain to the original clearance of the AFM algorithm (DEN190029) and is not detailed in this document.

Ask a specific question about this device

The HemoSphere Advanced Monitoring Platform is intended to be used by qualified personnel or trained clinicians in a critical care environment in a hospital setting. The Viewfinder Remote mobile application can be used for supplemental near real-time remote display of monitored hemodynamic parameter data as well as Faults, Alerts and Notifications generated by the HemoSphere Advanced Monitoring Platform.

The HemoSphere Advanced Monitoring Platform is intended for use with compatible Edwards Swan-Ganz and Oximetry Catheters, FloTrac sensors, Acumen IQ sensors, TruWave DPT sensors, ForeSight sensors, and ClearSight/Acumen IQ finger cuffs.

The HemoSphere Advanced Monitoring platform was designed to simplify the customer experience by providing one platform with modular solutions for their hemodynamic monitoring needs. The user can choose from the available optional sub-system modules or use multiple sub-system modules at the same time. This modular approach provides the customer with the choice of purchasing and/or using specific monitoring applications based on their needs. Users are not required to have all of the modules installed at the same time for the platform to function.

HemoSphere Advanced Monitoring Platform, subject of this submission, consists of the HemoSphere Advanced Monitor that provides a means to interact with and visualize hemodynamic and volumetric data on the monitor screen and its five (5) optional external modules: the HemoSphere Swan-Ganz Module (K163381 Cleared, April 14, 2017), the HemoSphere Oximetry Cable (K163381 Cleared, April 14, 2017), HemoSphere Pressure Cable (K180881 Cleared, November 16, 2018), HemoSphere Technology Module (previously referred to as "Tissue Oximetry Module"; K190305 cleared, August 29, 2019), HemoSphere ForeSight Module (K180003, May 10, 2018), and the HemoSphere ClearSight Module (K203687 cleared, May 28, 2021). The HemoSphere Advanced Monitor also has wired and wireless capabilities which was originally used only for connecting to a Hospital Information System (HIS) for data charting purposes. This capability is now used to allow it to stream continuously monitored data to the Viewfinder Remote, a mobile device-based application, for remote viewing the information (K211465 cleared July 8, 2021). The remotely transmitted data from the patient monitoring sessions include all hemodynamic parameter data and the associated physiological alarm notifications, historical trend data, and parameter waveform data.

The provided text describes several features and modifications to the HemoSphere Advanced Monitoring Platform, but it does not contain a specific table of acceptance criteria and reported device performance, nor does it detail a standalone AI algorithm study or an MRMC comparative effectiveness study for the machine learning features (like HPI or AFM).

The document primarily focuses on demonstrating substantial equivalence to predicate devices, and the performance data mentioned is generally high-level "All tests passed" rather than specific quantitative results against defined acceptance criteria for AI model performance.

Therefore, many of the requested details about the study that proves the device meets the acceptance criteria (especially for the AI/ML features) are not available in this document. The information that can be extracted relates more to the overall device functionality and compliance than to a detailed AI performance validation.

Based on the provided text, here's what can be extracted and what information is missing:

Information NOT available in the document regarding acceptance criteria and AI study specifics:

• 1. A table of acceptance criteria and the reported device performance for AI features: This level of detail is not provided. The document states that "Completion of all performance verification and validation activities demonstrated that the subject devices meet their predetermined design and performance specifications," and "Measured and derived parameters were tested using a bench simulation. Additionally, individual modules were tested at a system level to verify the safety of these modules." However, it does not enumerate specific acceptance criteria (e.g., accuracy, sensitivity, specificity thresholds) or quantitative performance results for the AI algorithms (HPI, AFM).
• 2. Sample size used for the test set and the data provenance, whether retrospective or prospective: This information is not provided. The document mentions "bench simulation" and "system level" testing but does not quantify the dataset size or its nature.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified.
• 4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not specified.
• 5. If a multi reader multi case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance: Not mentioned. The document states, "No new clinical testing was performed in support of the subject 510(k)," indicating that specific MRMC studies for this submission were not conducted.
• 6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The document states that the "Acumen Hypotension Prediction Index feature is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Acumen Hypotension Prediction Index (HPI) parameter," and similarly for AFM, "No therapeutic decisions should be made based solely on the Assisted Fluid Management suggestions." This implies the AI features are intended for human-in-the-loop use, but it doesn't explicitly refer to a "standalone" performance study in the context of a typical AI performance evaluation. It does mention "Measured and derived parameters were tested using a bench simulation," which could include algorithm-only testing, but specific metrics are absent.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not specified.
• 8. The sample size for the training set: Not specified.
• 9. How the ground truth for the training set was established: Not specified.

Information that CAN be inferred or extracted (though limited for AI-specific performance):

• Regarding "Acumen Hypotension Prediction Index Feature" and "Acumen Assisted Fluid Management Feature":
  • The document explicitly states that for the Acumen HPI feature, "No modifications have been made to the previously granted AFM algorithm" (referring to the core algorithm, K203687), and for HPI Smart Alerts/Trends modifications, "There are no changes to the core HPI algorithm, the behavior of the HPI parameter display, nor the indications for use and intended use of the HPI parameter due to this Smart Trends/ Smart Alerts modification." This suggests that the core algorithms for HPI and AFM were previously cleared (DEN190029 for AFM and K203687 for HPI), and this submission focuses on incorporating and updating the display and connectivity of these features rather than re-validating the core algorithms themselves. This means the detailed AI performance validation, if done, would have been part of the previous submissions (DEN190029 and K203687).
  • The HPI feature defines hypotensive events as "mean arterial pressure

Ask a specific question about this device

The Edwards Lifesciences Acumen Assisted Fluid Management (AFM) software feature provides the clinician with physiological insight into a patient's estimated response to fluid therapy and the associated hemodynamics. The Acumen AFM software feature is intended for use in surgical patients ≥18 years of age, that require advanced hemodynamic monitoring. The Acumen AFM software feature offers suggestions regarding the patient's physiological condition and estimated response to fluid therapy. Acumen AFM fluid administration suggestions are offered to the clinician; the decision to administer a fluid bolus is made by the clinician, based upon review of the patient's hemodynamics. No therapeutic decisions should be made based solely on the Assisted Fluid Management suggestions.

The Acumen™ Assisted Fluid Management (AFM) Software Feature ("the device") consists of software running on the Edwards Lifesciences EV1000 Clinical Platform (K160552 cleared on June 1, 2016) coupled with an Acumen 10 sensor (which was called FloTrac IO sensor in K152980 cleared on January 19, 2016) connected to a radial arterial catheter. The goal of AFM is to reduce the barriers slowing the utilization of perioperative goal directed therapy (PGDT) during surgical procedures by easing the implementation of PGDT, recognizing patterns of fluid responsiveness (i.e. hemodynamic data and past responses to fluid), and suggesting when fluid administration may improve the patient's hemodynamic state. The clinician is responsible for reviewing the AFM software suggestion in addition to a patient's current hemodynamic state and, if the clinician agrees, the clinician can deliver fluid in the standard-of-care fashion. Alternatively, if the clinician disagrees with the fluid suggestion, it can be rejected as the clinician chooses to not deliver any fluid.

The AFM algorithm can be used on the EV1000 Clinical Platform to help maintain patient fluid balance throughout a surgery. The AFM algorithm continuously estimates patient fluid responsiveness (percent increase in Stroke Volume, A SV%) using current hemodynamic parameters and past responses to fluid boluses. The Acumen AFM software feature is intended to simplify the implementation of fluid management protocols/perioperative goal directed therapy (PGDT).

When an Acumen IO sensor is connected and the AFM algorithm is initialized. the EV1000 Clinical Platform will provide notifications to the user when fluid is recommended by the AFM algorithm. The AFM algorithm learns from the stroke volume response to each fluid bolus to determine if a patient is in a fluid responsive or pre-load dependent state. The patient's tidal volume must be ≥ 8 mL/kg while using the AFM software feature. Throughout the case. the algorithm tracks and records bolus and patient response information to adapt its suggestions based off of the individual patient. In order for the algorithm to analyze each fluid bolus, the start and stop time of each infusion must be entered in the system, as well as the volume of the fluid bolus. The algorithm uses data from the current patient in order to predict their fluid responsiveness; this data is not used by the algorithm to determine fluid responsiveness in future patients.

Each bolus can be administered with the fluid, rate, and volume at the discretion of the clinician. Additionally, any fluid bolus can be declined or discarded as deemed appropriate by the clinician. The AFM algorithm will analyze fluid boluses within the following range: Volume: 100 - 500 mL: Rate: 1 - 10 L / hr.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The primary effectiveness endpoint for the Acumen AFM feature was its ability to predict a patient's fluid responsiveness. The acceptance criterion was based on exceeding a historical performance criterion of 30% fluid responsiveness, derived from the OPTIMISE study.

Table 1: Acceptance Criteria and Reported Device Performance

Other relevant performance data:

• User Boluses (Clinician-initiated boluses outside AFM recommendations): 40.9% [37.4, 44.1] of the time, user-administered boluses resulted in an increase in stroke volume. However, the study explicitly states that "it is not appropriate to compare AFM boluses against user boluses," as the study was not designed for this comparison.

Study Proving Device Meets Acceptance Criteria

The study used to prove the device meets acceptance criteria is the Assisted Fluid Management IDE study (AFM IDE study), identified by ClinicalTrials.gov identifier NCT03469570.

1. Sample Size and Data Provenance:

• Test Set Sample Size:
  • 330 subjects were initially enrolled.
  • 307 subjects were assigned to the per-protocol pivotal cohort and included in the effectiveness evaluation for the primary endpoint.
  • The primary effectiveness endpoint was based on the 54% (165/307) of subjects who received and followed AFM Recommended suggestions.
• Data Provenance: Retrospective and prospective. The AFM IDE study was a prospective, multi-center, single-arm clinical study. Data for comparison (historical control) was from a retrospective sub-analysis of the OPTIMISE trial. The AFM IDE study was conducted at study sites in the United States (US).

2. Number of Experts and Qualifications for Ground Truth (Test Set):

• The document does not explicitly state the number of experts used to establish ground truth or their specific qualifications for the test set.
• The ground truth for effectiveness (fluid responsiveness) was determined by measuring the percent increase in stroke volume (SV%) following a bolus and comparing it to the selected fluid strategy threshold (e.g., 15% increase for a 15% strategy). This is a physiological measurement, not directly an expert interpretation of an image or signal. Clinical decisions were made by the clinicians in charge during the study, and their actions (administering fluid after an AFM recommendation) were then assessed for outcomes.

3. Adjudication Method for the Test Set:

• For safety events, a Clinical Events Committee (CEC) reviewed and adjudicated events for anticipation, severity, and relatedness to fluid management.
• For effectiveness, the assessment was based on whether the measured physiological response (stroke volume increase) met the predefined fluid strategy threshold. There is no explicit mention of an adjudication method (like 2+1 or 3+1) for the primary effectiveness endpoint, as it relies on objective physiological measurements monitored by the device.

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

• No, an MRMC comparative effectiveness study was not done in the conventional sense of human readers interpreting data with and without AI assistance to assess diagnostic improvement.
• This device is an "adjunctive open loop fluid therapy recommender," meaning it provides suggestions to clinicians who then make the final decision and administer fluid. The study evaluated the outcome of following the device's recommendations (i.e., did the patient become fluid responsive as predicted?).
• The comparison was against a historical performance criterion (30% fluid responsiveness) rather than a direct comparison of human performance with and without AI assistance in real-time decision-making scenarios where human performance itself is being measured and improved. The text states: "The AFM IDE study was not designed to compare against manually administered fluid management protocols."

5. Standalone Performance (Algorithm Only without Human-in-the-Loop Performance):

• The primary effectiveness endpoint was not purely standalone. It evaluated the performance of the device's recommendations followed by clinician action. The outcome measured was the percentage of times an AFM recommendation that was followed by a clinician-accepted and clinician-delivered bolus resulted in the desired physiological change.
• The algorithm generates the recommendations (standalone function), but the ultimate "performance" (i.e., whether the patient responded as predicted by the recommendation) is assessed in the context of it being a decision support tool where the human makes the final decision. The study notes that a "major study limitation" was that decline rates were high for AFM recommendations (~50%), and the outcome for these declined interventions is unknown.

6. Type of Ground Truth Used:

• The ground truth for the effectiveness endpoint was based on physiological outcomes data: specifically, the percent increase in stroke volume (SV%) after a fluid bolus, compared against a pre-selected fluid strategy threshold (e.g., 10%, 15%, 20%). This is an objective, measured physiological response.
• The historical control for comparison was also derived from clinical study data (OPTIMISE trial).

7. Sample Size for the Training Set:

• The document does not explicitly state the sample size for the training set used to develop the AFM algorithm.
• It mentions that "Algorithm unit testing was performed using privately collected patient data."
• "The AFM algorithm learns from the stroke volume response to each fluid bolus to determine if a patient is in a fluid responsive or pre-load dependent state. The algorithm uses data from the current patient in order to predict their fluid responsiveness; this data is not used by the algorithm to determine fluid responsiveness in future patients." This suggests a patient-specific learning component rather than a large, fixed, pre-trained model for all patients.

8. How Ground Truth for Training Set was Established:

• The document describes the algorithm's learning process: "The AFM algorithm learns from the stroke volume response to each fluid bolus to determine if a patient is in a fluid responsive or pre-load dependent state." This implies that the ground truth for training (or rather, for its adaptive learning) is the actual measured physiological response (stroke volume change) of a patient to administered fluid boluses.
• The animal study also provided "non-clinical justification for the basic validity of the AFM algorithm" by showing more fluid suggestions in hypovolemic states compared to hypervolemic states. This could be considered a form of "validation data" or coarse "ground truth" for the algorithm's underlying physiological model, but it's not described as the primary training data.

Ask a specific question about this device