Search Results

The EV1000 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. Monitoring of hemodynamic parameters in conjunction with a perioperative goal directed therapy protocol enables consistent in the intended patient populations. 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

EV1000A:
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 Index (HPI) feature, which is an index related to the likelihood of a patient experiencing a hypotensive event (defined as mean arterial pressure (MAP)

The provided text does not contain specific acceptance criteria with numerical thresholds or detailed study results for device performance related to specific clinical metrics. Instead, it describes general verification and validation activities conducted for software modifications and system functionality.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not provide a table of acceptance criteria with specific performance metrics and their corresponding reported values. It generally states that "All tests passed" and that the device "meet their predetermined design and performance specifications."

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

The document mentions "retrospective data analysis for algorithm and performance verification" but does not specify the sample size for this analysis nor the country of origin. It also does not explicitly state whether the test set was retrospective or prospective, though the mention of "retrospective data analysis" suggests a retrospective component.

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

The document mentions "an assessment by clinicians of its usability and human factors considerations" for usability testing. However, it does not specify the number of experts used to establish ground truth for any of the performance verification, nor their qualifications.

4. Adjudication Method for the Test Set:

The document does not describe any adjudication method (e.g., 2+1, 3+1, none) for the test set.

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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance. This type of study seems irrelevant given the device's function as a monitoring platform rather than an AI-assisted diagnostic tool for image interpretation.

6. Standalone (Algorithm Only) Performance Study:

The document mentions that "Measured and derived parameters were tested using a bench simulation" and "individual components were tested at a sub-system level" and "integrated as a system and verified for their safety and effectiveness." This implicitly describes standalone (algorithm-only) performance testing against simulations and individual component verification. However, it does not provide detailed numerical results or specific performance metrics from these standalone tests.

7. Type of Ground Truth Used:

The ground truth for the verification activities appears to be based on:

• Predetermined design and performance specifications: The document states that the device "meet their predetermined design and performance specifications."
• Bench simulation: Used for testing "measured and derived parameters."
• Comparison to predicate devices: The submission aims to demonstrate substantial equivalence to predicate devices.

8. Sample Size for the Training Set:

The document does not mention a training set or its sample size. The submission focuses on software modifications and verification, and if any machine learning algorithms were involved (e.g., for the Acumen HPI feature which was previously cleared), the details of their training are not part of this specific submission summary. The Acumen HPI feature itself was cleared in a separate submission (K183646), and this submission for K203131 only notes minor updates to its display.

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

Since a training set is not mentioned in this document, the method for establishing its ground truth is not provided.

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

The CNAP® Monitor 500 HD is intended for the non-invasive continuous monitoring of blood pressure, and the determination of associated derived hemodynamic parameters including cardiac output within hospitals. The device displays the blood pressure waveform, trends, and numeric for blood pressure, pulse rate, and associated derived hemodynamic parameters. Alarms are generated for blood pressure parameters and pulse rate. The CNAP® Monitor 500 HD is to be used for adults and is to be operated by healthcare professionals.

The CNAP® Monitor 500 HD is a stand-alone device for continuous non-invasive blood pressure and hemodynamic monitoring with alarming functionality. The continuous non-invasive blood pressure is measured on the patient's finger using a double finger cuff, the oscillometric blood pressure measurement function (Advantage 2.0 OEM module by SunTech Inc.) is used for intermittent calibration of the continuous blood pressure curve. Medium priority alarming can be set for blood pressure beat values and pulse rate.

Based on the provided text, the CNAP® Monitor 500 HD is a blood pressure and hemodynamic monitoring system. The acceptance criteria and the study proving it meets these criteria are primarily focused on its substantial equivalence to predicate devices rather than independent performance metrics against a defined standard.

Here's the breakdown of the information provided, or lack thereof, regarding a detailed AI/algorithm study:

Key Observation: The document describes a medical device, not an AI/ML algorithm. The performance data section focuses on electrical safety, electromagnetic compatibility, mechanical and acoustical testing, and software verification/validation, along with a claim of substantial equivalence to predicate devices based on clinical testing using "measurement data from different sources." There is no indication of an AI/ML algorithm being developed or studied for this device, nor is there a study described that would fit the typical criteria for AI/ML performance evaluation (e.g., sensitivity, specificity, AUC, human reader improvement studies).

Therefore, I will answer the questions based on the closest relevant information provided, while highlighting where the requested details for an AI/ML study are not applicable or not present in the document.

Acceptance Criteria and Device Performance (based on provided text)

The document focuses on demonstrating substantial equivalence to predicate devices. This is the primary "acceptance criterion" from a regulatory perspective. The performance data presented are primarily related to safety, electromagnetic compatibility, and software verification rather than specific diagnostic accuracy metrics for an AI.

Given the nature of the device (a non-invasive blood pressure and hemodynamic monitor), the key performance "acceptance" would be its accuracy in measuring blood pressure and derived hemodynamic parameters, and its safety. However, the document does not provide a table of precise acceptance criteria with numeric targets (e.g., ±5 mmHg for BP accuracy) or how the specific device performance was measured against such targets for the new device. Instead, it relies on demonstrating comparable performance to predicate devices.

Table of Acceptance "Criteria" (based on regulatory submission principles for this device type) and Reported Device "Performance":

Details Specific to AI/ML Studies (Not Applicable or Not Provided)

1. Sample sizes used for the test set and the data provenance:

   • The document states "For clinical testing and evaluation measurement data from different sources was used to demonstrate that the device is substantially equivalent to the predicate devices."
   • No specific sample size for a "test set" (as understood in AI/ML validation) is provided.
   • No data provenance (e.g., country of origin, retrospective/prospective) is specified for this "measurement data." This is typical for a traditional medical device submission focused on equivalence, rather than a novel AI algorithm.

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

   • Not applicable / Not provided. The device is a monitor that directly measures/derives physiological parameters, not an diagnostic imaging AI that requires expert labeling for ground truth. Ground truth for blood pressure and hemodynamic parameters in a device like this would typically involve invasive measurements (e.g., arterial line for BP) or established reference methods, not expert consensus on image labels. The document does not describe how this "measurement data" was validated against a gold standard.

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

   • Not applicable / Not provided. This method is relevant for studies involving human interpretation or labeling of data, especially in AI development for image analysis or diagnostics. It does not apply to a physiological monitoring device undergoing substantial equivalence testing.

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

   • Not applicable / Not done. An MRMC study is specific to AI-assisted diagnostic tools where human interpretation is part of the workflow. This device is a physiological monitor, not an AI that assists human readers.

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

   • Not applicable / Not explicitly detailed as an AI algorithm study. The device itself is a "standalone" monitor that performs continuous non-invasive blood pressure and hemodynamic monitoring. The "performance data" section broadly covers its functional performance, but not in the context of an isolated AI algorithm. The device's "algorithms" are for signal processing and calculation of physiological parameters, which are validated as part of the overall device functionality, not typically as distinct "standalone AI" studies in the regulatory sense described.

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

   • Not explicitly stated in detail. For a non-invasive blood pressure device, the gold standard (ground truth) is typically invasive arterial blood pressure monitoring. For hemodynamic parameters, it would be direct measurement methods like thermodilution (e.g., using a Swan-Ganz catheter). The document only generically refers to "measurement data from different sources."

7. The sample size for the training set:

   • Not applicable / Not provided. This device is not described as involving a machine learning model that would require a distinct "training set" for its primary function. While there might be internal development data used to optimize signal processing algorithms, it is not presented as an AI/ML training regimen.

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

   • Not applicable / Not provided. As no AI/ML training set is described, this question is not relevant to the provided text.

Ask a specific question about this device

The BeneVision N12/N15/N17/N19/N22 patient monitors are intended for monitoring, displaying, reviewing, storing, and transferring of multiple physiological parameters including ECG (3-lead, 5-lead, 6-lead or 12-lead selectable, Arrhythmia Detection, ST Segment Analysis, QT Analysis, and Heart Rate (HR)), Respiration Rate (Resp), Temperature (Temp), Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure(IBP), Pulmonary Artery Wedge Pressure (PAWP), Cardiac Output (C.O.), Continuous Cardiac Output (CCO), Mixed/Central Venous Oxygen Saturation (SvO2/ScvO2), Carbon Dioxide (CO2), Oxygen (O2), Anesthetic Gas (AG), Impedance Cardiograph (ICG), Respiration Mechanics (RM), Neuromuscular Transmission Monitoring (NMT), Electroencephalograph (EEG), and Regional Oxygen Saturation (rSO2). The system also provides an interpretation of resting 12-lead ECG.

All the parameters can be monitored on single adult, pediatric, and neonatal patients except for the following:

• The arrhythmia detection, RM, CCO, SvO2/ScvO2, PAWP, and NMT monitoring are intended for adult and pediatric patients only;
• C.O. monitoring is intended for adult patients only;
• ICG monitoring is intended for only adult patients who meet the following requirements: height: 122 to 229cm, weight: 30 to 155kg.
• rSO2 monitoring is intended for use in individuals greater than 2.5kg.

The monitors are to be used in healthcare facilities by clinical professionals or under their guidance. They should only be used by persons who have received adequate training in their use. The BeneVision N12/N15/N17/N19/N22 monitors are not intended for helicopter transport, hospital ambulance, or home use.

The BeneVision N1 Patient Monitor is intended for monitoring, displaying, storing, alarming, and transferring of multiple physiological parameters including ECG (3-lead, 5-lead, 6-lead or 12-lead selectable, Arrhythmia Detection, ST Segment Analysis, QT Analysis, and Heart Rate (HR)), Respiration (Resp), Temperature (Temp), Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure (IBP) , Pulmonary Artery Wedge Pressure (PAWP), Carbon Dioxide (CO2) and Oxygen (O2). The system also provides an interpretation of resting 12-lead ECG.

All the parameters can be monitored on single adult, pediatric, and neonatal patients except for the following:

• The arrhythmia detection and PAWP is intended for adult and pediatric patients only
  The BeneVision N1 monitor is to be used in healthcare facilities. It can also be used during patient transport inside and outside of the hospital environment. It should be used by clinical professionals or under their guidance. It should only be used by persons who have received adequate training in its use. It is not intended for home use.

The subject BeneVision N Series Patient Monitors includes six monitors:

• BeneVision N12 Patient Monitor
• BeneVision N15 Patient Monitor
• BeneVision N17 Patient Monitor
• BeneVision N19 Patient Monitor
• BeneVision N22 Patient Monitor
• BeneVision N1 Patient Monitor

The BeneVision N Series Patient Monitors are Mindray's new generation monitoring product family with ergonomic and flexible design in platform of both software and hardware to meet the clinical needs of monitoring.

The provided document is a 510(k) Summary for the Mindray BeneVision N Series Patient Monitors. It focuses on demonstrating substantial equivalence to predicate devices rather than proving the device meets specific acceptance criteria through a dedicated study with statistical endpoints.

Therefore, many of the requested elements for a detailed study description (e.g., sample size for test/training sets, data provenance, number/qualifications of experts, adjudication methods, MRMC studies, standalone performance with specific metrics, and ground truth establishment for training data) are not present in the provided text.

The document primarily highlights changes from predicate devices and states that functional and system-level testing, along with compliance with consensus standards, demonstrate equivalence.

Here's a summary of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding device performance metrics in the format typically seen for a new device's efficacy study. Instead, it compares the specifications of the subject device with those of predicate devices, implicitly indicating that the subject device's performance meets or exceeds the predicate's established performance or relevant cleared standards.

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

The document does not specify sample sizes for test sets. The testing mentioned is referred to as "functional and system level testing" and "bench testing." It also states Mindray conducted "clinical testing to demonstrate that the Mindray and Nellcor SpO2 modules meet relevant consensus standards."
There is no mention of data provenance (e.g., country of origin of data, retrospective or prospective).

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

Not applicable. The document does not describe the use of experts to establish ground truth for testing. The evaluation focused on meeting specifications and consensus standards, and demonstrating equivalence to predicate devices.

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

Not applicable. There is no mention of adjudication methods.

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

Not applicable. This is a patient monitor, not an AI-assisted diagnostic device, and no MRMC studies are mentioned.

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

The document describes performance in terms of functionality and adherence to technical specifications and consensus standards, not in terms of "algorithm-only" performance as would be relevant for an AI device. The tests performed are for the integrated device.

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

The term "ground truth" is not used. The performance evaluation is based on meeting engineering specifications, comparing against predicate device performance, and compliance with recognized consensus standards (e.g., IEC, ISO, AAMI standards for physiological measurement accuracy).

8. The sample size for the training set

Not applicable. A "training set" is relevant for machine learning algorithms. This document describes a patient monitor, and no machine learning model training is discussed.

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

Not applicable, as no training set for a machine learning model is mentioned.

Ask a specific question about this device

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

The Acumen Hypotension Prediction Index Feature ("the device") consists of software running on the Edwards Lifesciences EV1000 Platform (previously cleared under K100709, K110597, K131892. K140312, and K160552) paired with the FloTrac IQ extravascular blood pressure transducer (K152980) and a radial arterial catheter. The device includes the Hypotension Prediction Index (HPI), the Dynamic Arterial Elastance Parameter (Eagyn), the Left Ventricular Contractility Parameter (dP/dt), and additional graphical user interface features.

HPI is an index related to the likelihood of a patient experiencing a hypotensive event (defined as mean arterial pressure (MAP)

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document does not explicitly state numerical acceptance criteria for sensitivity, specificity, and AUC. However, the reported performance metrics from the clinical validation studies demonstrate a level of accuracy deemed acceptable by the FDA for de novo classification. The high specificities and AUC values, along with the detailed performance table for different HPI ranges, suggest that the device's ability to predict hypotension within the 15-minute timeframe was considered sufficient. The acceptance criteria for usability testing (at least 80% of participants agree or strongly agree) are explicitly stated in the Usability Testing section.

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

The "test set" for the HPI algorithm's performance evaluation was derived from two retrospective patient databases:

• First Database (Edwards Lifesciences):
  • Sample Size: 52 subjects (OR patients)
  • Data Provenance: Global clinical sites, collected via prospective, IRB/EC approved clinical protocols with informed consent for each patient. (Retrospective analysis of prospectively collected data).
• Second Database (University Hospital):
  • Sample Size: 204 subjects (OR patients)
  • Data Provenance: From a university hospital, includes OR patients. (Retrospective analysis of an arterial waveform database).

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

The document does not specify the "number of experts" or their "qualifications" used to establish the ground truth for the test set.

Instead, the ground truth for hypotensive events was defined objectively: "mean arterial pressure (MAP)

Ask a specific question about this device