Search Results

The LuMon™ System is a noninvasive, non-radiation device that provides information on regional impedance variation within a cross-section of a patient's thorax. Graphical and numerical information is presented to the user as an adjunctive tool to other clinical information to support the user to assess a patient's respiratory condition.

The LuMon™ System is indicated for neonatal and infant patients with chest circumferences between 16.5 - 50 cm and adolescent through adult patients with chest circumferences between 76 - 128 cm who are breathing spontaneously or require mechanical ventilation in professional healthcare facilities.

Impedance-based respiratory rate monitoring is indicated for adults 22 years and older whose chest circumference is above 76 cm only.

The LuMon™ System also displays selected physiological and respiratory parameters from supported bedside devices.

The LuMon™ System does not measure regional ventilation of the lungs.

The LuMon™ System is a compact and lightweight Electrical Impedance Tomography (EIT) system that provides noninvasive monitoring of variations of regional air content/volume within a cross-section of the patient's thorax and patient respiration. It displays the results as real-time EIT images, waveforms, and derived parameters.

The system consists of a controller display unit, signal acquisition connector cable, and patient-applied conductive textile electrode belts. The system can connect to external bedside devices such as ventilators and monitoring devices to display contextual information for interpretation of EIT measurements.

The provided FDA 510(k) clearance letter and summary for the LuMon™ System contains information regarding its acceptance criteria and the studies conducted to demonstrate its performance. However, some specific details commonly found in a comprehensive study report (e.g., exact sample size for each clinical study, number of experts for ground truth, adjudication methods beyond "clinician-scored") are not explicitly stated in this high-level summary.

Based on the provided text, here's a structured response addressing your request:

Acceptance Criteria and Device Performance for LuMon™ System

The LuMon™ System underwent extensive non-clinical (bench and pre-clinical) and clinical testing to demonstrate its safety and effectiveness. The acceptance criteria are implicitly defined by the performance characteristics presented in the comparison tables and the successful attainment of stated accuracies and correlations.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally established as equivalent to or better than the predicate/reference devices, or as meeting pre-defined tolerances for specific parameters.

• Data Provenance: Not explicitly stated regarding country of origin for clinical data. The studies are described as "pre-clinical" and "clinical," with no indication of being retrospective. "Clinical testing was performed to support safety and effectiveness" generally implies prospective data collection for regulatory purposes.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Not specified.
• Qualifications of Experts: For the Respiration Rate study, the reference standard was "Clinician-scored EtCO2 capnogram." This implies medical professionals were involved in establishing the ground truth, but their specific qualifications (e.g., types of physicians, years of experience) are not detailed.

4. Adjudication Method for the Test Set

• For Respiration Rate Ground Truth: "Clinician-scored EtCO2 capnogram" implies expert review. However, the exact adjudication method (e.g., 2+1, 3+1, majority vote, independent reads with reconciliation) is not specified.

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

• It is not explicitly stated that a specific MRMC study was conducted to compare human readers with and without AI assistance.
• The device is presented as an "adjunctive tool to other clinical information to support the user," meaning it assists clinicians rather than replacing them. Its effectiveness is shown through its ability to provide accurate EIT data and respiratory rate, which clinicians would then integrate into their assessment. The summary focuses on the device's accuracy relative to reference standards or predicate devices, not on direct human-AI performance comparison studies.

6. Standalone (Algorithm Only) Performance

• Yes, the performance characteristics listed in the tables (e.g., R-squared correlations for EIT-CT, accuracy for RRi against reference standards, SNR, voltage accuracy) represent the standalone performance of the algorithm and the device. The clinical studies compare the device's output itself to established medical standards or other modalities, distinct from how a human user might interpret or use that output.

7. Type of Ground Truth Used

• Pre-clinical (Regional Impedance Distribution): Differential CT changes in aeration (healthy and injured lungs, one- and two-sided intubation) and "established physiological changes" were used as ground truth.
• Clinical (Global Volume Changes): Body plethysmograph traces and Ventilator flow-sensed volumes were used as ground truth.
• Clinical (Regional Impedance Distribution): The Timpel Enlight 2100 predicate comparison was used for ground truth.
• Clinical (Respiration Rate): Clinician-scored EtCO2 capnogram was used as ground truth.

8. Sample Size for the Training Set

• The information provided is a 510(k) summary, which typically focuses on validation. The sample size for the training set is not provided in this document. Training data details are usually proprietary and not disclosed in 510(k) summaries unless directly relevant to the regulatory pathway or substantial equivalence claim.

9. How Ground Truth for the Training Set Was Established

• The document does not specify how ground truth was established for the training set. Similar to the training set size, details about the training data and its ground truth establishment are generally considered proprietary and are not typically included in a public 510(k) summary. The summary focuses on the independent test data performance.

Ask a specific question about this device

Indications for Use for CARESCAPE Canvas 1000:

CARESCAPE Canvas 1000 is a multi-parameter patient monitor intended for use in multiple areas within a professional healthcare facility.

CARESCAPE Canvas 1000 is intended for use on adult, pediatric, and neonatal patients one patient at a time.

CARESCAPE Canvas 1000 is indicated for monitoring of:

· hemodynamic (including ECG, ST segment, arrhythmia detection, ECG diagnostic analysis and measurement, invasive pressure, non-invasive blood pressure, pulse oximetry, regional oxygen saturation, total hemoglobin concentration, cardiac output (thermodilution and pulse contour), temperature, mixed venous oxygen saturation, and central venous oxygen saturation),

· respiratory (impedance respiration, airway gases (CO2, O2, N2O, and anesthetic agents), spirometry, gas exchange), and

· neurophysiological status (including electroencephalography, Entropy, Bispectral Index (BIS), and neuromuscular transmission).

CARESCAPE Canvas 1000 is able to detect and generate alarms for ECG arrhythmias: atrial fibrillation, accelerated ventricular rhythm, asystole, bigeminy, bradycardia, ventricular couplet, irregular, missing beat, multifocal premature ventricular contractions (PVCs), pause, R on T, supra ventricular tachycardia, trigeminy, ventricular bradycardia, ventricular fibrillation/ ventricular tachycardia, ventricular tachycardia, and VT>2. CARESCAPE Canvas 1000 also shows alarms from other ECG sources.

CARESCAPE Canvas 1000 also provides other alarms, trends, snapshots and events, and calculations and can be connected to displays, printers and recording devices.

CARESCAPE Canvas 1000 can interface to other devices. It can also be connected to other monitors for remote viewing and to data management software devices via a network.

CARESCAPE Canvas 1000 is intended for use under the direct supervision of a licensed healthcare practitioner, or by personnel trained in proper use of the equipment in a professional healthcare facility.

CARESCAPE Canvas 1000 is not intended for use in an MRI environment.

Indications for Use for CARESCAPE Canvas Smart Display:

CARESCAPE Canvas Smart Display is a multi-parameter patient monitor intended for use in multiple areas within a professional healthcare facility.

CARESCAPE Canvas Smart Display is intended for use on adult, pediatric, and neonatal patients one patient at a time.

CARESCAPE Canvas Smart Display is indicated for monitoring of:

· hemodynamic (including ECG, ST segment, arrhythmia detection, ECG diagnostic analysis and measurement, invasive pressure, non-invasive blood pressure, pulse oximetry, regional oxygen saturation, total hemoglobin concentration, cardiac output (thermodilution), and temperature, and · respiratory (impedance respiration, airway gases (CO2)

CARESCAPE Canvas Smart Display is able to detect and generate alarms for ECG arrhythmias: atrial fibrillation, accelerated ventricular rhythm, asystole, bigeminy, bradycardia, ventricular couplet, irregular, missing beat, multifocal premature ventricular contractions (PVCs), pause, R on T, supra ventricular tachycardia, trigeminy, ventricular bradycardia, ventricular fibrillation/ ventricular tachycardia, ventricular tachycardia, and VT>2. CARESCAPE Canvas Smart Display also shows alarms from other ECG sources.

CARESCAPE Canvas Smart Display also provides other alarms, trends, snapshots and events. CARESCAPE Canvas Smart Display can use CARESCAPE ONE or CARESCAPE Patient Data Module (PDM) as patient data acquisition devices. It can also be connected to other monitors for remote viewing and to data management software devices via a network.

CARESCAPE Canvas Smart Display is intended for use under the direct supervision of a licensed healthcare practitioner, or by personnel trained in proper use of the equipment in a professional healthcare facility.

CARESCAPE Canvas Smart Display is not intended for use in an MRI environment.

Indications for Use for CARESCAPE Canvas D19:

CARESCAPE Canvas D19 is intended for use as a secondary display with a compatible host device. It is intended for displaying measurement and parametric data from the host device and providing visual and audible alarms generated by the host device.

CARESCAPE Canvas D19 enables controlling the host device, including starting and discharging a patient case, changing parametric measurement settings, changing alarm limits and disabling alarms.

Using CARESCAPE Canvas D19 with a compatible host device enables real-time multi-parameter patient monitoring and continuous evaluation of the patient's ventilation, oxygenation, hemodynamic, circulation, temperature, and neurophysiological status.

Indications for Use for F2 Frame; F2-01:

The F2 Frame, module frame with two slots, is intended to be used with compatible GE multiparameter patient monitors to interface with two single width parameter modules, CARESCAPE ONE with a slide mount, and recorder.

The F2 Frame is intended for use in multiple areas within a professional healthcare facility. The F2 Frame is intended for use under the direct supervision of a licensed healthcare practitioner, or by person trained in proper use of the equipment in a professional healthcare facility.

The F2 Frame is intended for use on adult, pediatric, and neonatal patients and on one patient at a time.

Hardware and software modifications carried out on the legally marketed predicate device CARESCAPE B850 V3.2, resulted in new products CARESCAPE Canvas 1000 and CARESCAPE Canvas Smart Display, along with the CARESCAPE Canvas D19 and F2 Frame (F2-01) all of which are the subject of this submission.

CARESCAPE Canvas 1000 and CARESCAPE Canvas Smart Display are new modular multi-parameter patient monitoring systems. In addition, the new devices CARESCAPE Canvas D19 and F2 Frame (F2-01) are a new secondary display and new module frame respectively.

The CARESCAPE Canvas 1000 and CARESCAPE Canvas Smart Display patient monitors incorporates a 19-inch display with a capacitive touch screen and the screen content is user-configurable. They have an integrated alarm light and USB connectivity for other user input devices. The user interface is touchscreen-based and can be used also with a mouse and a keyboard or a remote controller. The system also includes the medical application software (CARESCAPE Software version 3.3). The CARESCAPE Canvas 1000 and CARESCAPE Canvas Smart Display include features and subsystems that are optional or configurable.

The CARESCAPE Canvas 1000 and CARESCAPE Canvas Smart Display are compatible with the CARESCAPE Patient Data Module and CARESCAPE ONE acquisition device via F0 docking station (cleared separately).

For the CARESCAPE Canvas 1000 patient monitor, the other type of acquisition modules, E-modules (cleared separately) can be chosen based on care requirements and patient needs. Interfacing subsystems that can be used to connect the E-modules to the CARESCAPE Canvas 1000 include a new two-slot parameter module F2 frame (F2-01), a five-slot parameter module F5 frame (F5-01), and a seven-slot parameter module F7 frame (F7-01).

The CARESCAPE Canvas 1000 can also be used together with the new secondary CARESCAPE Canvas D19 display. The CARESCAPE Canvas D19 display provides a capacitive touch screen, and the screen content is user configurable. The CARESCAPE Canvas D19 display integrates audible and visual alarms and provides USB connectivity for other user input devices.

Please note that the provided text is a 510(k) summary for a medical device and primarily focuses on demonstrating substantial equivalence to a predicate device through non-clinical bench testing and adherence to various standards. It explicitly states that clinical studies were not required to support substantial equivalence. Therefore, some of the requested information regarding clinical studies, human expert involvement, and ground truth establishment from patient data will likely not be present.

Based on the provided text, here's the information regarding acceptance criteria and device performance:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present a formal table of specific, quantifiable acceptance criteria alongside reported performance data. Instead, it states that various tests were conducted to demonstrate that the design meets specifications and complies with consensus standards. The performance is generally reported as "meets the specifications," "meets the EMC requirements," "meets the electrical safety requirements," and "fulfilled through compliance."

However, we can infer some "acceptance criteria" based on the standards and tests mentioned:

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

• Test Set Sample Size: The document implies that the "test set" for performance evaluation was the device itself and its components as described ("CARESCAPE Canvas 1000, CARESCAPE Canvas Smart Display, CARESCAPE Canvas D19 and F2 Frame (F2-01)").
  • For usability testing, "16 US Clinical, 16 US Technical and 15 US Cleaning users" were involved.
• Data Provenance: The testing described is non-clinical bench testing.
  • For usability testing, the users were located in the US.
  • No direct patient data or retrospective/prospective study data is mentioned beyond the device's inherent functional characteristics being tested according to standards.

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

• Number of Experts: Not applicable in the context of establishing "ground truth" for patient data, as no clinical studies with patient data requiring expert adjudication were conducted or reported to establish substantial equivalence.
• For usability testing, "16 US Clinical, 16 US Technical and 15 US Cleaning users" participated. Their specific qualifications (e.g., years of experience, types of healthcare professionals) are not detailed in this summary.

4. Adjudication Method for the Test Set

• Not applicable, as no clinical studies with patient data requiring adjudication were conducted or reported.

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

• No MRMC study was done, as the document explicitly states: "The subjects of this premarket submission... did not require clinical studies to support substantial equivalence." The device is a patient monitor, not an AI-assisted diagnostic tool for image interpretation or similar.

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

• The performance evaluations mentioned (e.g., for general device functionality, electrical safety, EMC, specific parameter measurements like ECG/arrhythmia detection) represent the device's standalone performance in a bench setting, demonstrating its adherence to established standards and specifications. There is no separate "algorithm only" performance study reported distinctly from integrated device testing. The EK-Pro V14 algorithm, which is part of the device, is noted as "identical" to the predicate, implying its performance characteristics are maintained.

7. The Type of Ground Truth Used

• For the non-clinical bench testing, the "ground truth" was established by conformance to internationally recognized performance and safety standards (e.g., IEC, ISO, AAMI/ANSI) and the engineering specifications of the device/predicate. These standards define the acceptable range of performance for various parameters.
• For usability testing, the "ground truth" was the successful completion of tasks and overall user feedback/satisfaction as assessed by human factors evaluation methods.
• No ground truth from expert consensus on patient data, pathology, or outcomes data was used, as clinical studies were not required.

8. The Sample Size for the Training Set

• Not applicable. This document describes a 510(k) submission for a patient monitor, not a machine learning or AI model trained on a dataset. The device contains "Platform Software that has been updated from version 3.2 to version 3.3," but this refers to traditional software development and not a machine learning model requiring a "training set" in the AI sense.

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

• Not applicable, as there is no mention of a "training set" in the context of machine learning. The software development likely followed conventional software engineering practices, with ground truth established through design specifications, requirements, and verification/validation testing.

Ask a specific question about this device

EOlife is intended for use with emergency manual resuscitation devices to measure ventilatory flows and display visual guide on the insufflated volume, and ventilation frequency to ensure adequate ventilation of adult cardiopulmonary arrest patient during cardiopulmonary resuscitation (CPR) performed by healthcare professionals.

EOlife is a medical device dedicated to healthcare professionals to help them providing manual ventilation during cardiopulmonary resuscitation (CPR). EOlife is intended to be connected to any standard manual resuscitator for adults including a bag and a mask or endotracheal tube (ET tube) and supraglottic airway (SGA) device and to be used during manual ventilation of an adult cardiopulmonary arrest patient. EOlife is a portable device composed of an electronic control unit including an embedded software, a removable and rechargeable battery pack and of a single use flow sensor: FlowSense. EOlife does not present direct contact with the patient. Only the ventilation air flow is in contact with the internal part of FlowSense (indirect contact with the patient). During manual ventilation, EOlife measures the ventilation parameters (insufflated volumes, tidal volumes, ventilation frequencies, ) and gives real-time feedback to the user about the quality of the ventilation provided to the patient compared to the 2020 AHA (American Heart Association) Guidelines for Cardiopulmonary Resuscitation and Emergency Cardiovascular Care, Part 3: Adult Basic and Advanced Life Support. The aim is to help the user ventilate according to the recommended frequencies (10 cycles per minute) and volumes (6-8 ml/kg of ideal body weight).

The provided text describes the EOlife device, a medical device intended to assist healthcare professionals in manual ventilation during cardiopulmonary resuscitation (CPR) by measuring ventilatory flows and displaying visual guides on insufflated volume and ventilation frequency. The document is a 510(k) premarket notification by Archeon Medical to the FDA, asserting substantial equivalence to a predicate device.

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document includes a "Comparison of Technological Characteristics with Predicate Device" (Table 1) and a "Summary of Performance Testing" (Table 2). The most relevant section for acceptance criteria related to product performance is the "Measuring range and accuracy of ventilation values" and "Measuring range and accuracy of ventilation frequencies" within Table 1.

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

The document explicitly states: "The subject EOlife did not require clinical studies to support substantial equivalence." Instead, it relies on non-clinical (bench) testing, usability testing, and comparison to a predicate device.

• Test Set Description: The "test set" in this context refers primarily to the testing conducted on the physical device and its software, rather than a dataset of patient cases.
• Sample Size:
  • For the performance metrics (Vi, Vt, Freq), the specific number of tests or samples used to derive the RMSE values is not provided.
  • For biocompatibility, electrical safety, EMC, battery, power supply, mechanical, and software testing, the sample size is also not explicitly stated. These types of tests typically involve a limited number of devices to demonstrate compliance with standards.
  • For usability testing, "rounds of formative and summative testing" were performed, but the number of participants or test scenarios is not specified.
• Data Provenance: The testing was related to the device itself (hardware, software). No patient data is mentioned as being used for testing. The manufacturer, Archeon Medical, is based in Besançon, France. Therefore, the testing would presumably have been conducted there or by affiliated labs.

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

This information is not provided as the submission focuses on non-clinical testing and comparison to a predicate device, not on diagnostic performance against human expert-established ground truth on a patient dataset. The "ground truth" for the device's measurements (volume, frequency) would be established by calibrated measurement equipment used in the bench testing.

4. Adjudication Method for the Test Set:

This information is not applicable as there is no human expert-based ground truth or adjudication process described for clinical effectiveness. The assessment is against technical specifications and established standards through bench testing.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done. The submission explicitly states: "The subject EOlife did not require clinical studies to support substantial equivalence." The device is positioned as an "adjunct tool" providing real-time feedback, not as an AI diagnostic tool that human readers would interpret. Therefore, there is no discussion of human reader improvement with or without AI assistance.

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

The performance testing (bench testing) described in Table 2, specifically the "Accuracy assessment of the values measured and displayed by EOlife," can be considered a form of standalone performance assessment of the device's measurement capabilities. The software within the device operates autonomously to measure and display parameters ("algorithm only"). However, this is for measurement accuracy, not for a diagnostic or interpretive task that would typically be associated with "standalone AI performance" in imaging or other clinical decision support contexts. The device's primary function is to provide real-time guidance to a human user, making it inherently "human-in-the-loop" in its intended use.

7. The Type of Ground Truth Used:

• For the measurement accuracy of volume and frequency values during bench testing, the ground truth would be established by precision laboratory instruments and simulated ventilation profiles (e.g., using a test lung and a ventilator simulator with known, calibrated outputs).
• For biocompatibility, electrical safety, EMC, mechanical, and software validation, the ground truth is compliance with international consensus standards (e.g., ISO, IEC, UN).
• For usability, the ground truth is the successful and safe completion of critical tasks by users as assessed in human factors testing.

8. The Sample Size for the Training Set:

This information is not applicable/not provided. The EOlife device is described as having "an embedded software that contains algorithms," but the document does not indicate that these algorithms (for measuring ventilatory flows and providing guidance) were developed using machine learning or required a "training set" of data in the typical sense. It appears to be based on programmed logic and physics models rather than statistical learning from a large dataset.

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

This information is not applicable/not provided for the same reasons as point 8.

Ask a specific question about this device

ENLIGHT 2100 is a non-invasive, radiation free medical device that provides information from impedance variation from a cross-section of a patient's thorax. This information is presented to the clinician user as an adjunctive tool to other clinical information in order to support the user's assessment of variations in regional air content within a cross section of a patient's thorax.

ENLIGHT 2100 also provides respiratory parameters based on spirometric monitoring.

It is intended for mechanically ventilated adult and pediatric patients in a hospital setting, whose thorax perimeter is within the range of 37.5 - 134 cm.

ENLIGHT 2100 does not measure regional ventilation of the lungs

ENLIGHT 2100 is a Ventilatory electrical impedance tomograph that uses several electrodes (usually between 16 and 32) placed around the patient's thorax to assess regional impedance variation in a lung slice (tomography). It provides a relative measurement, so it only provides information on variations in local impedance. ENLIGHT 2100 estimates Local Impedance Variation, occurring in a cross section of the thorax during a respiratory cycle, and which are linearly related to Variations in Regional Air Content within the lung.

The ENLIGHT 2100 is a ventilatory electrical impedance tomograph that also provides respiratory parameters based on spirometric monitoring. It is intended for mechanically ventilated adult and pediatric patients in a hospital setting. The device provides information on impedance variation from a cross-section of a patient's thorax as an adjunctive tool to support the user's assessment of variations in regional air content. It does not measure regional ventilation of the lungs. The device relies on a primary predicate (ENLIGHT 2100 - K211135) for its Electrical Impedance Tomography (EIT) data and a secondary predicate (Philips NM3 Respiratory Profile Monitor with VentAssist – K103578) for its spirometric monitoring capabilities. The data provided focuses on non-clinical/bench testing to demonstrate substantial equivalence to these predicates.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for the ENLIGHT 2100 are based on its performance characteristics in comparison to its predicate devices for both EIT parameters and spirometric parameters. The study conducted was non-clinical bench testing.

Table 1: Acceptance Criteria and Reported Device Performance

The "Explanation of Differences" column in the provided tables typically serves as the primary source for the reported device performance and the proof that it meets the acceptance criteria (i.e., demonstrating substantial equivalence to the predicates based on the non-clinical testing). For the EIT parameters, the performance is reported as "Same" as the predicate, with the rationale that the hardware and EIT algorithm are identical. For the spirometric parameters, specific accuracy metrics are provided for the subject device and its accuracy relative to the secondary predicate (NM3).

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

The document explicitly states that "Bench Testing - We have performance tests to check the automatic calculation of the parameters shown at the Trend Screen." and lists "Non-clinical testing" and "Bench Test" as the method. Therefore, the data provenance is bench test data. No information is provided regarding the specific sample size (e.g., number of test points, simulated cases, or repetitions) used for this bench testing. The data does not specify the country of origin, but given the sponsor's location (Brazil) and the nature of bench testing, it would likely be laboratory/engineering data. It is inherently prospective as it involves controlled testing to confirm performance.

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

The study described is non-clinical bench testing. It involves evaluating the device's numerical calculations and performance against specified ranges and accuracy criteria, likely using simulated physiological signals or validated reference equipment. Therefore, no human experts were used to establish ground truth in the way they would be for image interpretation or diagnosis. The ground truth for this type of testing is established by the specifications of the signals generated or the reference standards of the testing equipment.

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

Given that this was a non-clinical bench study focused on numerical calculation accuracy and signal acquisition performance, no human adjudication method was employed. The "ground truth" was inherently defined by the test setup and reference measurements, not by human interpretation or consensus.

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

No MRMC comparative effectiveness study was done. The device (ENLIGHT 2100) functions as a sensor and data display unit for physiological parameters, not an AI-assisted diagnostic tool that would directly assist human readers in interpreting complex medical images or data where a reader study would be applicable. The document describes it as an "adjunctive tool to other clinical information," implying it provides data for clinicians to interpret, but not in a way that necessitates an AI-assistance reader study.

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

Yes, a standalone (algorithm only) performance evaluation was implicitly done through the bench testing. The document states, "We have performance tests to check the automatic calculation of the parameters shown at the Trend Screen." This testing evaluates the device's ability to accurately measure and calculate the specified EIT and spirometric parameters within defined ranges and accuracies, independent of human interaction or interpretation beyond setting up the test and recording results.

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

The ground truth used for this non-clinical bench testing was established through engineered inputs/simulations and/or comparisons to a validated reference standard. For example, for spirometric parameters like Tidal Volume or Respiratory Rate, the system would be fed precisely controlled and measured airflow/pressure signals, and the device's output would be compared to the known input values of these signals. For EIT parameters, the ground truth would similarly come from controlled electrical impedance variations generated under laboratory conditions.

8. The sample size for the training set

The document describes non-clinical bench testing for the purpose of demonstrating substantial equivalence. It does not mention any machine learning or AI components that would require a separate training set. Therefore, information regarding a training set sample size is not applicable or provided in this context. The device's algorithms are likely based on established physiological and electrical impedance principles, not trained on a large dataset of patient measurements requiring specific "training set" ground truth establishment.

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

As there is no mention of a training set or machine learning/AI model training, the question of how its ground truth was established is not applicable based on the provided information.

Ask a specific question about this device

The monitors are intended to be used for monitoring, storing, and to generate alarms for, multiple physiological parameters of adults and pediatrics. The monitors are intended for use by trained healthcare professionals in hospital environments.

The LM-8 monitor monitors parameters such as ECG (3-lead, 12-lead selectable), Respiration (RESP), Functional arterial oxygen saturation (SpO2), Invasive or noninvasive blood pressure (dual-IBP, NIBP), Temperature (dual-TEMP), Expired CO2 and Quick Temperature (Quick TEMP).

The LM-10 monitor monitors parameters such as ECG (3-lead, 12-lead selectable), Respiration (RESP), Functional arterial oxygen saturation (SpO2), Invasive or noninvasive blood pressure (2/4 channels IBP, NIBP), Cardiac Output (C.O.), Temperature (dual-TEMP) and Expired CO2.

The LM-12 monitor monitors parameters such as ECG (3-lead, 12-lead selectable), Respiration (RESP), Functional arterial oxygen saturation (SpO2), Invasive or noninvasive blood pressure (2/4 chamels IBP, NIBP), Cardiac Output (C.O.), Temperature (dual-TEMP), Expired CO2 and Anesthetic gas (AG).

The LM-15 monitors parameters such as ECG (3-lead, 5-lead, 12-lead selectable), Respiration (RESP), Functional arterial oxygen saturation (SpO2), Invasive or noninvasive blood pressure (2/4 channels IBP, NIBP), Cardiac Output (C.O.), Temperature (dual-TEMP), Expired CO2 and Anesthetic gas (AG).

The arrhythmia detection and ST Segment analysis are intended for adult and pediatric patients.

The monitors are not intended for MRI environments.

LM-8, LM-10, LM-12 and LM-15, patient monitor integrates parameter measuring modules, display and recorder in one device, featuring in compactness, lightweight and portability. Replaceable built-in battery facilitates patient transport. Large high-resolution display provides clear view of 10 waveforms and full monitoring parameters. Patient Monitor can monitor vital signal such as ECG, respiration (RESP), non-invasive blood pressure (NIBP), oxygen saturation of the blood (SpO2), temperature (TEMP), invasive blood pressure (IBP), cardiac output (C.O.), CO2 and anesthetic gas (AG). Those signals are digitized, processed and examined for alarm conditions, after that presents all those information on the color TFT display. The monitor also provides advantageous operating control for the user.

The provided text is an FDA 510(k) summary for a Patient Monitor (models LM-8, LM-10, LM-12, LM-15). It primarily focuses on demonstrating substantial equivalence to predicate devices through technical comparisons and compliance with general performance standards.

However, the document does not contain the detailed information necessary to answer all aspects of your request regarding acceptance criteria and a study proving the device meets those criteria in the context of an AI/algorithm-driven medical device performance study.

Specifically, the document lacks:

• A explicit table of acceptance criteria for algorithm performance (e.g., sensitivity, specificity, F1-score for arrhythmia detection).
• Detailed results of a study demonstrating the device meets specific performance criteria for arrhythmia detection or ST-segment analysis (beyond basic functional checks).
• Information on sample size for test sets directly related to algorithm performance (as opposed to overall device safety/functionality).
• Data provenance, number of experts for ground truth, adjudication methods, or MRMC studies, which are typical for AI/ML device evaluations.
• Training set details for any AI/ML components.

The "Performance data" section refers to "Clinical data" for validation, but these appear to be general functional validation tests on physiological parameters (ECG, RESP, SpO2, NIBP, etc.) to ensure the monitors function as intended, rather than a specific study to validate the performance of the arrhythmia detection and ST Segment analysis algorithm against clinical ground truth. The statement "The clinical data demonstrate that the subject devices perform comparably to the predicate device that is currently marketed for the same intended use" is a high-level conclusion without supporting details beyond the comparative features table.

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

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

The document doesn't provide a specific table of quantitative acceptance criteria for the arrhythmia detection and ST segment analysis algorithm (e.g., sensitivity, specificity thresholds) and corresponding reported performance metrics. It lists general parameters and their measurement ranges, which are functional specifications, not performance criteria for an arrhythmia detection algorithm.

General device functional specifications (from comparison table, not acceptance criteria for algorithm):

The document notes that "The arrhythmia detection and ST Segment analysis are intended for adult and pediatric patients" and that "Clinical tests were performed on the LM-8, LM-12 and LM-15 monitors to validate their performance in terms of ECG...". However, it does not specify what constituted "validation" for these particular algorithmic features or what the performance metrics were. The "Conclusion" states: "The clinical data demonstrate that the subject devices perform comparably to the predicate device that is currently marketed for the same intended use." This is the reported device performance for these features: "comparable to predicate."

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

• Sample Size for Test Set: Not specified for the "Clinical data" related to ECG/arrhythmia/ST validation. The statement is general: "Clinical tests were performed on the LM-8, LM-12 and LM-15 monitors..."
• Data Provenance: Not specified (e.g., country of origin, retrospective or prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

• Not specified. The document does not describe how ground truth for arrhythmia or ST segment analysis was established for clinical testing.

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, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No, an MRMC study is not mentioned. This device is a monitor, not an AI-assisted diagnostic tool for interpretation by a human reader in the typical sense of an MRMC study for imaging. It provides "arrhythmia detection and ST Segment analysis" algorithms directly to the user.

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

• The "Clinical data" statement indicates the monitors' performance was validated. Given the nature of a patient monitor, the arrhythmia and ST segment analysis would inherently be "standalone" algorithmic functions integrated into the device, providing automated analysis. However, specific performance metrics (like sensitivity/specificity of the algorithm itself) from this standalone evaluation are not presented.

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

• Not specified. It is generally implied that such devices are validated against accepted physiological measurement standards and potentially manually confirmed ECG interpretations, but the document does not detail this for the arrhythmia/ST segment analysis.

8. The sample size for the training set:

• Not applicable/Not specified. The document does not indicate that the arrhythmia detection or ST segment analysis algorithms utilize machine learning or require a "training set" in the sense of AI/ML development. It's likely these are based on established rule-based or signal processing algorithms, not learned from data.

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

• Not applicable. (See #8)

In summary, this 510(k) submission successfully demonstrates substantial equivalence through technical specifications, comparisons to predicate devices, and compliance with general safety and performance standards (e.g., electrical safety, EMC, biocompatibility, software verification/validation). However, it does not detail a specific performance study for its arrhythmia detection and ST segment analysis algorithms in a way that typically applies to AI/ML clearance, which would include explicit acceptance criteria, detailed test set characteristics, and ground truth methodologies. The "clinical data" section is very high-level and only states comparability to predicate devices.

Ask a specific question about this device

The monitors are intended to be used for monitoring, storing, and to generate alarms for, multiple physiological parameters of adults, pediatrics and neonates. The monitors are intended for use by trained healthcare professionals in hospital environments.

The monitored physiological parameters include: ECG, respiration (RESP), temperature (TEMP), oxygen saturation of arterial blood (SpO2), pulse rate (PR), non-invasive blood pressure (NIBP), invasive blood pressure (IBP), carbon dioxide (CO2), cardiac output (C.O.), anesthetic gas (AG), bispectral index (BIS), respiration mechanice cardiography (ICG).

BIS is intended for use on adult and pediatric patients.

ICG monitoring is intended for use on adults only.

The arrhythmia detection and ST Segment analysis are intended for adult patients.

The monitors are additionally intended for use during patient transport inside hospitals.

The monitors are not intended for MRI environments.

LMPLUS series Patient Monitor including LMPLUS-12, LMPLUS-15 and LMPLUS-17 which can perform long-time continuous monitoring of multiple physiological parameters. Also, it is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormity so that doctors and nurses can deal with them in time.

The LMPLUS series Patient Monitor realize the monitoring of physiological parameters by configuration with different parameter modules which include SpO2 (pulse oxygen saturation, pulse rate and SpO2 plethysmogram) with EDAN SpO2 module or Nellcor SPO2 module, NIBP (systolic pressure, diastolic pressure and pulse rate), TEMP, ECG, RESP (respiration), CO2, IBP, C.O. and AG (anesthetic gas), RM (respiratory mechanics), BIS (bispectral index) and ICG (impedance cardiography).

The above is the maximum configuration for LMPLUS series Patient Monitor, the user may select different monitoring parameters in according with their requirements.

LMPLUS-12 configures with 12.1-inch color TFT touch screen, LMPLUS-15 and LMPLUS-17 with same screen except different sizes 15-inch and 17-inch separately. Three models are all build-in Lithium-ion battery, support software upgrade online and networking.

The provided document focuses on the 510(k) summary for the CAF Medical Solutions Inc. Patient Monitor (models LMPLUS-12, LMPLUS-15, and LMPLUS-17), demonstrating its substantial equivalence to a predicate device (Edan Instruments, Inc. Patient Monitor, models elite V5, elite V6, and elite V8). The document primarily presents a feature-by-feature comparison and non-clinical performance data, with a brief mention of clinical tests.

Therefore, the information regarding acceptance criteria and the study proving the device meets them will be limited to what is explicitly stated in the document or can be inferred from the provided test types and standards. A full, detailed study proving acceptance criteria for specific performance metrics (like sensitivity, specificity, or inter-reader variability for an AI model) is not present in this type of regulatory submission document, which focuses on substantial equivalence to a predicate rather than a novel AI algorithm.

Based on the provided document, here's what can be extracted and inferred regarding performance and validation:

The document indicates that the device's performance was evaluated against various recognized standards for patient monitors, which inherently define acceptable performance ranges for each physiological parameter. The study primarily aims to show that the new device meets these established standards and performs comparably to the predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a "table of acceptance criteria" in the format of a pre-defined threshold that the device must meet for a specific study's outcome (e.g., "sensitivity > X%"). Instead, it shows a feature-by-feature comparison to a predicate device, including various performance specifications (e.g., accuracy, measurement range) that are in line with industry standards for patient monitors. The "Acceptance Criteria" are implicitly defined by the parameters and accuracy/range specifications of the predicate device and the relevant IEC/ISO standards the device claims compliance with. The "Reported Device Performance" for the subject device (LMPLUS models) is stated to be "Same" as the predicate device across all listed specifications.

Here's an illustrative table based on the provided comparison, highlighting key physiological parameters:

Note: The table above is a summary of just a few representative parameters from the much larger comparison table (Table 1) in the document. The general "Acceptance Criteria" for all listed parameters are the identical specifications of the predicate device.

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

The document states: "Clinical tests were performed on the LMPLUS 12, LMPLUS 15 and LMPLUS 17 monitors to validate their performance in terms of noninvasive blood pressure (NIBP) and SpO2 accuracy."

However, the specific sample sizes for these clinical tests (number of patients, number of measurements) and the data provenance (e.g., country of origin, retrospective or prospective nature) are not detailed in this 510(k) summary. This level of detail would typically be found in the full test report, which is referenced but not included.

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

The document mentions "clinical tests" for NIBP and SpO2 accuracy. For these types of physiological measurements, the ground truth is typically established by:

• Reference Devices: Using highly accurate, calibrated reference measurement devices.
• Clinical Protocols: Adhering to established clinical protocols for data collection (e.g., for NIBP, a protocol like ISO 81060-2 which often involves comparisons to invasive arterial measurements or calibrated sphygmomanometers by trained healthcare professionals).

There is no mention of human experts being used to establish "ground truth" in the context of interpretation (e.g., radiologists for imaging, unlike an AI algorithm for image analysis). The device measures physiological parameters, and accuracy is validated against established, objective measurement techniques, not expert consensus on qualitative data. Therefore, the concept of "experts establishing ground truth" as it applies to subjective judgments or interpretations (which is common for AI/ML in imaging) is not directly applicable here.

4. Adjudication Method for the Test Set

Given that the clinical tests mentioned are for quantitative physiological parameter accuracy (NIBP and SpO2), adjudication methods like 2+1 or 3+1 (common in studies involving multiple readers for subjective assessments) are not applicable. Accuracy is determined by comparing device readings to a reference standard, not by expert consensus on interpretations.

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

No MRMC study was mentioned or implied.
This device is a patient monitor, not an AI-assisted diagnostic tool that would involve human readers interpreting cases. Therefore, a study to measure how much human readers improve with AI assistance is not relevant to this type of device and was not performed.

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

The document does not describe the device as having a distinct "algorithm" component for analysis that would be evaluated in isolation. It's a physiological monitoring device. Its accuracy in measuring parameters like NIBP and SpO2 is its "standalone performance." The clinical tests mentioned (for NIBP and SpO2 accuracy) would indeed be an assessment of the device's ability to accurately measure these parameters independently, which is effectively its standalone performance. The results are implied by the statement "the subject devices perform comparably to the predicate device."

7. Type of Ground Truth Used

For the clinical tests (NIBP and SpO2 accuracy), the ground truth would be established through:

• Reference Standard Measurements: Using a highly accurate and validated reference device (e.g., an invasive arterial line for NIBP, or a co-oximeter for SpO2) or an established standardized method as per relevant ISO standards (e.g., ISO 81060-2 for NIBP).
• Physiological Data: Direct physiological measurements, not pathology, outcomes data, or expert consensus on subjective interpretations.

8. Sample Size for the Training Set

This document describes a conventional patient monitor, not a medical device that utilizes AI/ML requiring a distinct "training set" of data to learn from. Therefore, there is no mention of a training set or its sample size. The device's algorithms for processing physiological signals are based on established engineering principles and signal processing, not machine learning from a large training dataset.

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

As there is no training set for this type of device, this question is not applicable.

Ask a specific question about this device

The CARESCAPE B650 is a multi-parameter patient monitor intended for use in multiple areas and intrahospital transport within a professional healthcare facility.

The CARESCAPE B650 is intended for use on adult, pediatric, and neonatal patients and on one patient at a time. The CARESCAPE B650 is indicated for monitoring of:

· hemodynamic (including ECG, ST segment, arrhythmia detection, ECG diagnostic and measurement, invasive pressure, non-invasive blood pressure, pulse oximetry, regional oxygen saturation, total hemoglobin concentration, cardiac output (thermodilution and pulse contour), temperature, mixed venous oxygen saturation, and central venous oxygen saturation),

· respiratory (impedance respiration, airway gases (CO2, O2, N2O, and anesthetic agents), spirometry, gas exchange), and

· neurophysiological status (including electroencephalography, Entropy, Bispectral Index (BIS), and neuromuscular transmission).

The CARESCAPE B650 can be a stand-alone monitor or interfaced to other devices. It can also be connected to other monitors for remote viewing and to data management software devices via a network.

The CARESCAPE B650 is able to detect and generate alarms for ECG arrhythmias: atrial fibrillation, accelerated ventricular rhythm, asystole, bigeminy, bradycardia, ventricular couplet, missing beat, multifocal premature ventricular contractions (PVCs), pause, R on T, supra ventricular tachycardia, trigeminy, ventricular bradycardia, ventricular fibrillation/ventricular tachycardia, ventricular tachycardia, and VT>2. The CARESCAPE B650 also shows alarms from other ECG sources.

The CARESCAPE B650 also provides other alarms, trends, snapshots and calculations, and can be connected to displays, printers and recording devices.

The CARESCAPE B650 is intended for use under the direct supervision of a licensed healthcare practitioner, or by personnel trained in proper use of the equipment in a professional healthcare facility.

Contraindications for using CARESCAPE B650:

The CARESCAPE B650 is not intended for use in a controlled MR environment.

CARESCAPE B650 is a new version of a portable multi-parameter patient monitoring system. The CARESCAPE B650 includes the monitor with built-in CPU, power unit, a 15 inch touch display, the CARESCAPE Software and the battery. CARESCAPE B650 is equipped with two module slots where patient data acquisition modules (E-Module type) can be connected to perform patient monitoring. CARESCAPE B650 is equipped with the ePort interface that supports use of PDM or CARESCAPE ONE patient data acquisition devices. In addition to the ePort interface the PDM module can be also connected directly to the CARESCAPE B650 via special slide mount connector which is in the back of the monitor. The CARESCAPE B650 includes features and subsystems that are optional or configurable.

The provided text is a 510(k) Summary for the GE Healthcare CARESCAPE B650 patient monitor. It focuses on demonstrating substantial equivalence to a predicate device, rather than presenting a detailed study of acceptance criteria and device performance. Therefore, the information requested in your prompt is largely not available within this document.

Here's a breakdown of what can and cannot be extracted based on the provided text:

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

The document does not provide a specific table of acceptance criteria with corresponding reported device performance values in the format you requested. It states: "Bench testing related to software, hardware and performance including applicable consensus standards was conducted on the CARESCAPE B650, demonstrating the design meets the specifications." This is a general statement about testing without specific criteria or performance metrics.

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

This information is not provided in the document. The document mentions "Bench testing related to software, hardware and performance," but does not detail the nature of the test sets, their size, or their origin.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not provided. As this is a 510(k) submission for a patient monitor, the primary evidence relies on engineering and performance testing against established standards, not typically on expert consensus for "ground truth" in the way it might be for an AI diagnostic device.

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

This information is not provided. Adjudication methods are typically relevant for studies involving human interpretation or subjective assessments, which are not detailed here.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done, and it is not applicable to this submission. The device is a patient monitor, not an AI-assisted diagnostic tool that would involve human readers. The document explicitly states: "The subject of this premarket submission, CARESCAPE B650 did not require clinical studies to support substantial equivalence."

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

The document describes "Bench testing related to software, hardware and performance" and "Software testing included software design, development, verification, validation and traceability." This implies standalone testing of the device's algorithms and functionality. However, specific details about the results of such standalone performance are not provided in a quantifiable manner against acceptance criteria.

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

Given the nature of the device (a multi-parameter patient monitor), "ground truth" would likely be established through:

• Reference measurement devices/standards: For parameters like ECG, blood pressure, oxygen saturation, temperature, etc., the device's measurements would be compared against validated reference devices or established physical standards.
• Simulated physiological signals: For arrhythmia detection, the device would be tested with simulated ECG waveforms containing known arrhythmias.

However, the specific types of "ground truth" used are not explicitly elaborated beyond "bench testing" and "applicable consensus standards."

8. The sample size for the training set

This information is not provided and is generally not applicable in the context of a patient monitor's 510(k) submission unless specific machine learning algorithms requiring training data were a novel aspect of the submission, which is not indicated here. The document describes modifications to software and hardware, implying updates to existing functionalities rather than the introduction of new, data-trained AI models.

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

This information is not provided and is not applicable for the reasons stated in point 8.

Ask a specific question about this device

The CARESCAPE B850 is a multi-parameter patient monitor intended for use in multiple areas within a professional healthcare facility.

The CARESCAPE B850 is intended for use on adult, pediatric, and neonatal patients and on one patient at a time. The CARESCAPE B850 is indicated for monitoring of:

• · hemodynamic (including ECG, ST segment, arthythmia detection, ECG diagnostic analysis and measurement, invasive pressure, non-invasive blood pressure, pulse oximetry, regional oxygen saturation, total hemoglobin concentration, cardiac output (thermodilution and pulse contour), temperature, mixed venous oxygen saturation, and central venous oxygen saturation),
• · respiratory (impedance respiration, airway gases (CO2, O2, N2O, and anesthetic agents), spirometry, gas exchange), and
• · neurophysiological status (including electroencephalography, Entropy, Bispectral Index (BIS), and neuromuscular transmission).

The CARESCAPE B850 can be a stand-alone monitor or interfaced to other devices. It can also be connected to other monitors for remote viewing and to data management software devices via a network.

The CARESCAPE B850 is able to detect and generate alarms for ECG arrhythmias: atrial fibrillation, accelerated ventricular rhythm, asystole, bigeminy, bradycardia, ventricular couplet, missing beat, multifocal premature ventricular contractions (PVCs), pause, R on T, supra ventricular tachycardia, trigeminy, ventricular bradycardia, ventricular fibrillation/ventricular tachycardia, ventricular tachycardia, and VT>2. The CARESCAPE B850 also shows alarms from other ECG sources.

The CARESCAPE B850 also provides other alarms, trends, snapshots and calculations, and can be connected to displays, printers and recording devices.

The CARESCAPE B850 is intended for use under the direct supervision of a licensed healthcare practitioner, or by personnel trained in proper use of the equipment in a professional healthcare facility.

Contraindications for using the monitor

The CARESCAPE B850 is not intended for use in a controlled MR environment.

CARESCAPE B850 is a new version of a modular multi- parameter patient monitoring system. The monitor includes a separate 19-inch touchscreen display, the central processing unit (also called CPU), the CARESCAPE Software, and a module frame F5 or F7. CARESCAPE B850 is equipped with the ePort interface that supports use of PDM or CARESCAPE ONE patient data acquisition modules for patient monitoring. In addition, the F5 module frame has five module slots, and the F7 module frame has seven module slots where patient data acquisition modules (E-Module type), can be connected to perform patient monitoring. The CARESCAPE B850 includes features and subsystems that are optional or configurable.

This looks like a 510(k) summary for the GE Healthcare CARESCAPE B850 patient monitor. I will extract information related to the acceptance criteria and study that proves the device meets them.

Based on the provided text, the CARESCAPE B850 is a multi-parameter patient monitor. The 510(k) submission is for a new version with updated software and minor hardware modifications. The submission refers to a primary predicate device, also named CARESCAPE B850 (K191323), and additional predicate/reference devices for specific parameters (INVOS PM7100 and MASIMO RADICAL Y PULSE CO-OXIMETER).

The key takeaway is that the device did not require clinical studies to support substantial equivalence because it is a modified version of an already cleared device and incorporates previously cleared parameters. Therefore, the "study that proves the device meets the acceptance criteria" primarily refers to non-clinical bench testing.

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 explicitly present a table of acceptance criteria with corresponding performance metrics for the new CARESCAPE B850 compared to a specific threshold. Instead, it relies on the concept of substantial equivalence to a predicate device.

The "acceptance criteria" are implied to be that the performance of the new device is "as safe, as effective, and the performance to be substantially equivalent to the predicate device." The reported "device performance" is primarily that it passed various non-clinical tests.

Implied Acceptance Criteria (based on substantial equivalence concept):

Note: The document states that the fundamental function and operation of the proposed CARESCAPE B850 monitor are unchanged compared to its predicate (K191323), except for the addition of an E-musb Interface module and the capability to display previously cleared hemodynamic parameters from OEM devices (regional oxygen saturation and total hemoglobin concentration).

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

• Sample Size for Test Set: Not explicitly stated. The document refers to "bench testing related to software, hardware and performance." This typically involves testing prototypes or production units, but a "sample size" in the context of patient data is not applicable here as no clinical studies were performed for this submission.
• Data Provenance: Not applicable, as no external data (e.g., patient data from a specific country, retrospective or prospective) was used for this 510(k) submission to demonstrate substantial equivalence. The testing was internal bench testing.

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

• Number of Experts: Not applicable. For bench testing of hardware and software, "ground truth" is typically established by engineering specifications, validated test protocols, and adherence to consensus standards, rather than expert clinical consensus on patient data.
• Qualifications of Experts: Not applicable.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. This concept applies to clinical studies where discrepancies in observations or diagnoses need to be resolved. For bench testing, test results are typically compared against predefined specifications.

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

• MRMC Study: No. The device is a multi-parameter patient monitor, not an AI-assisted diagnostic tool that would typically involve human readers. The new version mostly focuses on software updates, minor hardware changes, and display of previously cleared parameters from other OEM devices.

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

• Standalone Performance: The core functionality of the device (e.g., ECG, arrhythmia detection, various physiological measurements) operates in a "standalone" fashion in that the algorithms process patient data collected by the sensors. The document doesn't detail specific "algorithm-only" performance metrics as would be seen for a novel AI algorithm. Instead, it relies on the previous clearance of the predicate device and the fact that the algorithms (like EK-Pro arrhythmia detection algorithm V14) are identical. The newly added parameters (regional oxygen saturation and total hemoglobin concentration) are sourced from OEM devices that would have their own standalone performance data from their original clearances.

7. The Type of Ground Truth Used

• Type of Ground Truth: For the non-clinical bench testing, the ground truth would be the engineering specifications of the device and adherence to relevant consensus standards (e.g., for electromagnetic compatibility, electrical safety, environmental performance). For the physiological parameters, the "ground truth" for the algorithms (e.g., arrhythmia detection) was established during the development and clearance of the predicate device (K191323) and the OEM devices for rSO2 and SpHb.

8. The Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. As this is not an AI/ML device that requires a distinct "training set" for model development for this 510(k) submission, this information is not relevant here. The update involves existing algorithms and integration of existing cleared parameters.

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

• How Ground Truth for Training Set Was Established: Not applicable, for the same reason as point 8.

Ask a specific question about this device

The CARESCAPE B450 is a multi-parameter patient monitor intended for use in multiple areas and intrahospital transport within a professional healthcare facility.
The CARESCAPE B450 is intended for use on adult, pediatric, and neonatal patients and on one patient at a time. The CARESCAPE B450 is indicated for monitoring of:
· hemodynamic (including ECG, ST segment, arrhythmia detection, ECG diagnostic and measurement, invasive pressure, non-invasive blood pressure, pulse oximetry, regional oxygen saturation, total hemoglobin concentration, cardiac output (thermodilution and pulse contour), temperature, mixed venous oxygen saturation, and central venous oxygen saturation),
· respiratory (impedance respiration, airway gases (CO2, O2, N2O, and anesthetic agents), spirometry, gas exchange), and
· neurophysiological status (including electroencephalography, Entropy, Bispectral Index (BIS), and neuromuscular transmission).
The CARESCAPE B450 can be a stand-alone monitor or interfaced to other devices. It can also be connected to other monitors for remote viewing and to data management software devices via a network.
The CARESCAPE B450 is able to detect and generate alarms for ECG arrhythmias: atrial fibrillation, accelerated ventricular rhythm, asystole, bigeminy, bradycardia, ventricular couplet, missing beat, multifocal premature ventricular contractions (PVCs), pause, R on T, supra ventricular tachycardia, trigeminy, ventricular bradycardia, ventricular fibrillation/ventricular tachycardia, ventricular tachycardia, and VT>2. The CARESCAPE B450 also shows alarms from other ECG sources.
The CARESCAPE B450 also provides other alarms, trends, snapshots and calculations, and can be connected to displays, printers and recording devices.
The CARESCAPE B450 is intended for use under the direct supervision of a licensed healthcare practitioner, or by personnel trained in proper use of the equipment in a professional healthcare facility

CARESCAPE B450 is a new version of a portable multiparameter patient monitoring system. The CARESCAPE B450 includes the monitor itself with built-in CPU, power unit, a 12 inch touch display, the CARESCAPE Software and one or two batteries. CARESCAPE B450 is equipped with an ePort interface that supports use of PDM or CARESCAPE ONE patient data acquisition modules for patient monitoring. CARESCAPE B450 is also equipped with one module slot where patient data acquisition modules (E-Modules), can be connected to perform patient monitoring. The CARESCAPE B450 includes features and subsystems that are optional or configurable.

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

The document describes the CARESCAPE B450, a multiparameter patient monitor. This submission is for a new version of the device, primarily focusing on updated software and minor hardware modifications.

The document does not contain details about specific acceptance criteria for performance metrics (e.g., sensitivity, specificity, accuracy for arrhythmia detection) or a study proving the device meets those criteria with statistical significance. Instead, it primarily focuses on demonstrating substantial equivalence to a predicate device (K191249 CARESCAPE B450) and compliance with general safety and performance standards through non-clinical testing.

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

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

   This information is not explicitly provided in the document. The submission aims to show that the new CARESCAPE B450, with its updated software and minor hardware, is "substantially equivalent" to its predicate device. This implies that its performance is expected to meet the same standards as the predicate, but specific performance metrics and acceptance thresholds for those metrics are not detailed.

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

   This information is not provided. The document states that "Bench testing related to software, hardware and performance including applicable consensus standards was conducted on the CARESCAPE B450, demonstrating the design meets the specifications." It also notes that "The subject of this premarket submission, CARESCAPE B450 did not require clinical studies to support substantial equivalence." This indicates that the primary validation was through non-clinical bench testing, not through studies on patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

   This information is not provided. As clinical studies were not required and the validation was primarily non-clinical bench testing, the concept of "ground truth" derived from expert consensus on patient data (as would be typical for AI/ML performance studies) is not applicable or described in this document.

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

   This information is not provided. Since no clinical studies or evaluations of diagnostic performance against a "ground truth" established by experts on a test set are detailed, adjudication methods are not mentioned.

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

   No MRMC comparative effectiveness study was done or reported. The device is a patient monitor with arrhythmia detection, not an AI-assisted diagnostic tool for human readers in the context of an MRMC study.

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

   The document states that "Bench testing related to software, hardware and performance... was conducted," implying that the device's inherent functional performance was tested. The phrase "algorithm only" isn't explicitly used, but the testing would effectively assess the device's standalone operation. However, no specific performance metrics (like those one would expect for an AI algorithm, e.g., sensitivity/specificity for specific arrhythmias) are reported. The device features "EK-Pro arrhythmia detection algorithm EK-Pro V14", and its performance is assumed to be equivalent to the predicate using the same algorithm version.

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

   For the non-clinical bench testing, the "ground truth" would likely be based on established engineering specifications, simulated physiological signals, and validated test protocols inherent to medical device performance testing, rather than expert consensus, pathology, or outcomes data from human subjects. This type of detail is not further elaborated in the document.

8. The sample size for the training set

   This information is not provided. As the submission is for a new version of an existing device primarily involving software updates and minor hardware changes, and the algorithm (EK-Pro V14) itself is listed as "Identical" to the predicate, details about a training set for a new or significantly retrained algorithm are not discussed.

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

   This information is not provided, for the same reasons as point 8.

Ask a specific question about this device

The CARESCAPE Respiratory Modules, (E-sCO, E-sCOV, E-sCAiO, E-sCAiOV, E-sCAiOVX, E-sCAiOVX, E-sCAiOE, E-sCAiOVE) are indicated for use with a host device for monitoring respiratory parameters (CO2, O2, N2O, anesthetic agents, anesthetic agent identification and respiratory rate) and ventilatory parameters (airway pressure, flow and volume) of adult, pediatric and neonatal patients and gas exchange parameters (VCO2, VO2) of adult and pediatric patients.

When monitoring neonatal or other patients that have high respiration rate or low tidal volume these modules shall be used within the limits of respiration rates and tidal volumes to ensure specified measurement accuracy.

These modules are intended for use by qualified medical personnel only.

The CARESCAPE Respiratory Modules E-sCO, E-sCOV, E-sCOVX, E-sCAiO, E-sCAiOV, E-sCAiOVX, E-sCAiOE, E-sCAiOVE and accessories measure respiratory parameters (concentrations of Carbon Dioxide, Oxygen, Nitrous Oxide and anesthetic agents in the patient's breath, as well as the patient's respiration rate), ventilatory parameters (airway pressure, flow and breathing volumes) and gas exchange parameters (oxygen consumption and carbon dioxide production) of hospital patients.

Parameters measured by the CARESCAPE Respiratory Modules are CO2, N2O, O2, Anesthetic agents, Agent ID, Spirometry, oxygen consumption (VO2) and carbon dioxide production (VCO2) depending on the model used. The CARESCAPE Respiratory Modules is a family of single-width plug-in parameter modules for modular monitoring systems. The CARESCAPE Respiratory Modules are of the diverting type, which means that a small continuous flow of gas is sampled from the patient's breath to the module for measuring the gas concentrations. The CARESCAPE Respiratory Modules acquire the signals detected by the module sensors, calculate the parameter values and communicate them to the host device. The CARESCAPE Respiratory Modules measure the patient's respiration rate and activate a status signal if no breaths are detected in 20 second time and the modules activate relevant status signals upon detecting failures or anomalies in the operation of the module hardware, software or gas sampling system.

The CARESCAPE Respiratory Modules do not trigger or issue any physiological or technical alarms by themselves. All management of alarms is entirely performed by the host devices based on parameter and status data received from the modules, as well as on the alarm condition data stored in the host device.

This 510(k) introduces two new module models in the CARESCAPE Respiratory Modules family: E-sCAiOE and E-sCAiOVE. These new module models include added hardware compared to the modules cleared in K183394. The operation, measured parameters and performance specifications of the E-sCAiOE and E-sCAiOVE is identical to E-sCAiO and E-sCAiOV when used with the current module host devices cleared in the USA. The added modules E-sCAiOE and E-sCAiOVE have the same software as CARESCAPE Respiratory Modules cleared in K183394.

The provided text is a 510(k) Summary for the GE Healthcare CARESCAPE Respiratory Modules. This document describes the device and its claimed substantial equivalence to a predicate device. It does not contain information about an AI/ML-driven device or a study involving human readers or expert ground truth adjudication for image analysis. Therefore, based on the provided text, I cannot answer the questions related to AI/ML device acceptance criteria and study details.

The document focuses on:

• Device Description: Respiratory modules that measure various parameters like CO2, O2, N2O, anesthetic agents, and ventilatory parameters.
• Predicate Device: K183394 CARESCAPE Respiratory Modules.
• Key Change: Introduction of two new module models (E-sCAiOE and E-sCAiOVE) with added hardware (fresh gas sample connector) but identical operation, measured parameters, and performance specifications when used with current host devices.
• Non-Clinical Tests: Bench testing related to software, hardware, and performance, including compliance with various IEC and ISO standards (e.g., IEC 60601-1, IEC 60601-1-2, IEC 60601-2-49, ISO 80601-2-55). Biocompatibility and environmental testing were also conducted. Software was considered "Major" level of concern.
• Clinical Tests: The document explicitly states: "The subject of this premarket submission... did not require clinical studies to support substantial equivalence."

Therefore, I cannot extract the following information that would be relevant to an AI/ML device study:

• Table of acceptance criteria and reported device performance for an AI/ML model.
• Sample size for a test set or data provenance for AI/ML validation.
• Number of experts and their qualifications for establishing ground truth.
• Adjudication method for a test set.
• MRMC comparative effectiveness study results or effect size of AI assistance.
• Standalone performance of an algorithm.
• Type of ground truth used (expert consensus, pathology, outcome data).
• Sample size for the training set.
• How ground truth for the training set was established.

This document pertains to traditional medical device clearance, not an AI/ML device.

Ask a specific question about this device