Search Results

This system is intended to monitor physiological parameters of patients within any healthcare environment. The user, responsible to interpret the monitored data made available, will be a professional health care provider. Physiological data, system alarms and patient data analysis will be available to the care provider from the monitor.

The monitored parameters are:

1. ECG
2. Noninvasive Blood Pressure (NIBP)
3. Invasive Blood Pressure (IBP)
4. Temperature
5. Respiratory Gases
6. Anesthetic Agent Gases
7. Respiratory Rate
8. Pulse Oximetry (SpO2)
9. Arrhythmia and ST Analysis of the ECG waveforms

The 9100 monitor measures and displays real time physiological data of the patient, including a graphical plethysmogram and numerical data. The 9100 is a modular system and can be used to monitor one or more of the following parameters: ECG, Noninvasive BP (NIBP), Invasive BP, Temperature, Respiratory Gases, Anesthetic Agent Gases and SpO2. Arrhythmia and ST Segment analysis of the ECG waveforms is also offered. For all these vital parameters, the 9100 will be capable of limit alarms and alerts, printing of strip chart recordings and storing trends for retrospective review.

The provided text does not contain specific acceptance criteria or a study detailing the device's numerical performance against such criteria. The document is a 510(k) summary for the Criticare Systems Inc. Model 9100 Family Vital Signs Monitor, which primarily asserts substantial equivalence to predicate devices and compliance with various performance and safety standards.

Therefore, many of the requested details, such as specific performance metrics, sample sizes for test and training sets, expert qualifications, and adjudication methods, are not present in this document.

Here's an overview of what can be extracted and what is missing:

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

The document does not provide a table with specific numerical acceptance criteria and reported device performance. Instead, it broadly states: "The 9100 monitor performance for each monitoring modality has been confirmed to be equivalent to the predicate device." It also lists various performance standards that the device complies with, implying that meeting these standards constitutes the acceptance criteria.

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 filing focuses on substantial equivalence and standard compliance rather than detailed study results.

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 in the document. Given that the main claim is equivalence to predicate devices and compliance with engineering standards, direct human interpretation of a test set with expert ground truth establishment is not described.

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

This information is not provided in the document.

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

An MRMC comparative effectiveness study is not mentioned in the document. The device is a vital signs monitor, and the filing describes its standalone performance and equivalence, not its role in assisting human interpretation or diagnostic efficacy in a reader study. There is no AI component mentioned.

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

Yes, the filing implicitly describes a standalone performance evaluation by stating "The 9100 monitor performance for each monitoring modality has been confirmed to be equivalent to the predicate device" and listing compliance with various performance standards (e.g., for NIBP, oximetry, ECG, etc.). These standards typically involve objective testing of the device's accuracy and functionality without human intervention in the loop of the measurement and display process.

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

For the performance evaluations mentioned (compliance with standards like AAMI SP-10 for NIBP or ISO 9919 for Oximetry), the ground truth would typically be established through scientific reference methods, calibrated instruments, and standardized test protocols as defined by those specific engineering and performance standards. It is not expert consensus, pathology, or outcomes data in the clinical sense, but rather "technical ground truth" established by the standards themselves.

8. The sample size for the training set

This information is not provided in the document. The document references "existing core technologies from the predicate 8100 monitor" and "CSI's field experience with these modalities in the predicate devices has been satisfactory." This suggests that the development likely leveraged historical data and experience from previous products, but specific training set sizes are not disclosed.

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

This information is not explicitly provided. Given the reliance on "existing core technologies" and "field experience," the ground truth for any underlying algorithms (e.g., for arrhythmia detection or ST segment analysis) would have been established during the development and validation of those predicate technologies, likely through a combination of clinical data and expert review, but the specifics are not detailed here.

Ask a specific question about this device

This system is intended to monitor physiological parameters of patients within any healthcare environment. The user, responsible to interpret the monitored data made available, will be a professional health care provider. Physiological data, system alarms and patient data analysis will be available to the care provider from the monitor.

The 506CN monitor measures and displays real time physiological data of the patient, including a graphical plethysmogram and numerical data. The 506CN can be used to monitor one or more of the following parameters: Noninvasive BP (NIBP) and SpO2. For all these vital parameters, the 506CN will be capable of limit alarms and alerts, printing of strip chart recordings and storing trends for retrospective review.

The provided text describes a 510(k) premarket notification for the 506CN Patient Monitor. This type of submission relies on demonstrating substantial equivalence to a predicate device rather than conducting new clinical trials to establish acceptance criteria and device performance from scratch. Therefore, the information typically requested in a detailed AI device study report (like sample sizes, expert qualifications, and specific performance metrics vs. acceptance criteria tables) is not present in this document.

However, I can extract the information that is available and explain the context of why certain details are missing for this type of submission.

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

Since this is a 510(k) submission based on substantial equivalence, specific numerical acceptance criteria and a table directly reporting performance against those criteria are not provided in the same way as a de novo clinical study. Instead, the "acceptance criteria" are implied by compliance with recognized standards and equivalence to the predicate device.

2. Sample sized 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 510(k) summary. For a 510(k) based on substantial equivalence to a predicate device and compliance with standards, detailed clinical test set data (including sample size, provenance, or retrospective/prospective nature) is generally not required to be submitted or summarized. The equivalence is often demonstrated through bench testing, engineering comparisons, and adherence to established performance standards. The document mentions "equivalence testing" but does not detail its methodology or sample size.

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 in the 510(k) summary, as it is not a study requiring expert-established ground truth in the typical sense of AI/diagnostic device validation.

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

This information is not provided in the 510(k) summary.

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

An MRMC comparative effectiveness study was not conducted or reported in this 510(k) summary. This device is a patient monitor, not an AI-assisted diagnostic tool, and the focus of the submission is on demonstrating equivalence to an existing monitor, not on improving human reader performance with AI.

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

This device is a patient monitor that displays data for a healthcare professional to interpret ("The user, responsible to interpret the monitored data made available, will be a professional health care provider."). It is not an "algorithm only" device in the AI sense. Its "standalone" performance is assessed by its ability to accurately measure and display physiological parameters, which is affirmed by its compliance with performance standards and equivalence to the predicate device. However, a specific "standalone" study report in the context of AI performance validation is not provided.

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

For this type of device, "ground truth" for NIBP and SpO2 measurements typically refers to reference measurements from established, highly accurate (often invasive) methods against which the device's measurements are validated during standard compliance testing (e.g., AAMI SP-10 for NIBP, ISO 9919 for SpO2). However, the specific methods and sources of this ground truth are not detailed in this 510(k) summary. It only states compliance with the standards that prescribe how such ground truth is established and used for testing.

8. The sample size for the training set

This information is not applicable and not provided. This device is a physiological monitor, not an AI system that undergoes "training" in the machine learning sense. Its functionality is based on established signal processing and measurement algorithms, not learned from a training dataset.

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

This information is not applicable and not provided, as there is no "training set" for this device in the context of AI/machine learning.

Ask a specific question about this device

This system is intended to monitor physiological parameters of patients within any healthcare environment. The user, responsible to interpret the monitored data made available, will be a professional health care provider. Physiological data, system alarms and patient data analysis will be available to the care provider from the monitor.

The 8600 monitor measures and displays real time physiological data of the patient, including waveforms and numerical data. The 8600 can be configured to monitor one or more of the following parameters: ECG, Noninvasive BP (NIBP), Invasive BP (IBP), SpOz, Temperature, Respiration, CO2, Nominvasive BP (NIDF), Invasive BP Agenta, For all the samini, CO2, N2O, O2 and Halogenated Anesthetic Agents. For all these vital parameters, the 8600 will be capable of limit alams and alerts, printing of strip chart recordings and storing trends for retrospective review.

The provided document (K042569) is a 510(k) summary for the Criticare Systems, Inc. Model 8600 Vital Signs Monitor. It outlines the device description, intended use, comparison to a predicate device, and compliance with standards. However, it does not contain specific study results or detailed acceptance criteria with performance numbers for the device itself. Instead, it relies on demonstrating substantial equivalence to a predicate device and compliance with general performance standards.

Therefore, much of the requested information regarding detailed acceptance criteria, specific study results, sample sizes, expert involvement, and ground truth establishment cannot be extracted directly from this document.

Here's an attempt to answer based on the available information and recognizing the limitations:

1. Table of Acceptance Criteria and Reported Device Performance

Important Note: The document states that performance has been "confirmed to be equivalent" and "compliance has been completed." It does not provide the specific quantitative results from these compliance tests or detail what "equivalent" means in terms of a specific delta or accuracy range. The "acceptance criteria" are generally implied by the requirement to meet these recognized standards.

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

This information is not provided in the 510(k) summary. The document states "field experience" with the predicate device and "equivalence testing" and "applicable objective standards compliance." It does not describe specific clinical studies or test sets with sample sizes or data provenance (e.g., country of origin, retrospective/prospective).

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

This information is not provided in the 510(k) summary. The submission relies on compliance with established performance standards, which implicitly require certain testing methodologies, but the details of expert involvement are not disclosed.

4. Adjudication Method for the Test Set

This information is not provided in the 510(k) summary. Given the nature of a vital signs monitor and the reliance on performance standards, a formal adjudication process using multiple experts for a test set is unlikely to be described at this level of detail.

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

This information is not applicable and not provided. The 8600 Vital Signs Monitor is a device that provides physiological data; it is not an AI-powered diagnostic tool that assists human "readers" or interpreters in the way an imaging algorithm would. Therefore, an MRMC study related to AI assistance for human readers is not relevant in this context.

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

The device itself is a standalone monitor. Its performance is assessed against recognized standards for accuracy and reliability of physiological measurements. The document states its performance "has been confirmed to be equivalent to the predicate device" and that it "complies with applicable safety and performance standards." This implies standalone performance testing against those standards.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The "ground truth" for the performance of a vital signs monitor, as implied by compliance with standards like EN 1060-1 for NIBP or EN 865 for Oximetry, would typically involve:

• Reference Devices: Highly accurate, calibrated reference measurement devices (e.g., invasive arterial lines for IBP, calibrated gas analyzers for CO2/O2, etc.).
• Simulators/Phantoms: Calibrated simulators or phantoms for specific parameters (e.g., ECG simulators, NIBP cuffs with controlled pressure waveforms).
• Clinical Studies: For parameters like NIBP or SpO2, clinical studies comparing the device's readings to reference measurements in human subjects are often required by the standards.

However, the specific methods for establishing ground truth are not detailed in this 510(k) summary, beyond the mention of compliance with the listed standards.

8. The Sample Size for the Training Set

This information is not applicable and not provided. Vital signs monitors, especially from 2004, typically rely on established signal processing algorithms and hardware engineering rather than machine learning models that require "training sets" in the modern AI sense.

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

This information is not applicable and not provided for the same reasons as point 8. The device's underlying technology likely involves well-understood physiological sensing and signal processing, not a "training set" with associated ground truth as understood in contemporary AI/ML development.

Ask a specific question about this device

This system is intended to monitor physiological parameters of patients within any healthcare environment. The user, responsible to interpret the monitored data made available, will be a professional health care provider. Physiological data, system alarns and patient data analysis will be available to the care provider from the monitor.

The 8100 monitor interprets and displays real time physiological data of the patient including waveforms and numerical data. The 8100 can be custom configured to monitor ECG, Noninvasive BP (NIBP), Invasive BP (IBP), S.O2, Temperature, Respiration, CO2, N.O. O2 and Halogenated Anesthetic Agents. Arrhythmia Detection and ST Analysis software from Brentwood Medical has been incorporated into the 8100 system and uses the extant ECG hardware inputs and microprocessor to enable these capabilities. All user interface elements are provided by the existing 8100 monitor. For each patient vital parameter, the 8100 will be capable of providing limit alarms and alerts, printing of strip chart recordings and storing data trends for retrospective review.

The provided document is a 510(k) summary for the Criticare Systems Inc. 8100 Vital Signs Monitor with Arrhythmia Detection and ST Analysis. It describes the device, its intended use, and claims substantial equivalence to a predicate device.

However, the document does NOT contain specific acceptance criteria, detailed study design, or reported device performance metrics in the format requested. It mentions that AAMI EC-57 testing was performed by Brentwood Medical for a previous submittal (K013717) and that the device was tested with "a representative group of prerecorded ECG waveforms with abnormal beats" to document the performance of the integrated Brentwood algorithms. There is no table of acceptance criteria or reported device performance against such criteria in this document.

Therefore, many of the requested details cannot be extracted from the provided text.

Based on the information available:

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

• Not provided in the document. The document states "AAMI EC-57 testing was performed by Brentwood Medical in their previous submittal (K013717)", which is a standard for ambulatory electrocardiographs. While this implies performance against AAMI EC-57 standards, the specific acceptance criteria or how the 8100 monitor performed against them are not detailed here.

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

• Test Set Sample Size: "a representative group of prerecorded ECG waveforms with abnormal beats." No specific number is given.
• Data Provenance: Not specified.
• Retrospective or Prospective: "prerecorded ECG waveforms" suggests retrospective data.

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

• Not specified. The document does not describe how the ground truth for the "abnormal beats" in the prerecorded ECG waveforms was established or by whom.

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 vital signs monitor with arrhythmia and ST analysis, not an "AI" device as typically conceived for MRMC studies involving human readers' diagnostic performance. The document describes the integration of software algorithms into existing hardware.

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

• Yes, implicitly. The testing described: "To document the performance of the Brentwood algorithms when integrated into the 8100 and verify the timeliness of ECG morphology-related alarms, the 8100 was tested with a representative group of prerecorded ECG waveforms with abnormal beats." This refers to evaluating the algorithms' performance on predefined ECG data, which is a form of standalone testing.

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

• Implied ground truth: "abnormal beats" in prerecorded ECG waveforms. The basis for declaring these beats "abnormal" (e.g., expert interpretation, pre-labeled dataset) is not explicitly stated but is typically derived from expert-annotated databases for arrhythmia analysis.

8. The sample size for the training set:

• Not specified. The document mentions the integration of Brentwood Medical's software, which implies these algorithms were pre-developed. The training set size for those algorithms is not discussed.

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

• Not specified. This information would pertain to the development of Brentwood Medical's algorithms, which is not detailed in this 510(k) summary.

Ask a specific question about this device

This system is intended to monitor physiological parameters of patients within any healthcare environment. The user, responsible to interpret the monitored data made available, will be a professional health care provider. Physiological data, system alarms and patient data analysis will be available to the care provider from the monitor.

The 507EL monitor measures and displays real time physiological data of the patient, including waveforms and numerical data. The 507EL can be used to monitor one or more of the following parameters: ECG, Noninvasive BP (NIBP), SpO3, Temperature, and Respiration. For all these vital parameters, the 507EL will be capable of limit alarms and alerts, printing of strip chart recordings and storing trends for retrospective review.

The provided text is a 510(k) summary for the Criticare Systems, Inc. Model 507EL Vital Signs Monitor, submitted to the FDA in 2002. This document is a premarket notification asserting substantial equivalence to a predicate device, not a detailed study report on acceptance criteria and performance of a novel AI/ML device. Therefore, much of the requested information regarding AI/ML device studies (e.g., sample sizes for test/training sets, ground truth establishment for AI/ML, MRMC studies, standalone performance of an algorithm) is not applicable or available in this document.

However, based on the provided text, I can extract information related to the device's performance claims and how its equivalence was established.

Acceptance Criteria and Device Performance (as inferred from the document):

Study Information (Based on a 510(k) submission for a non-AI/ML device):

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

   • Test set size: Not specified. The document refers to "equivalence testing" and compliance with performance standards, which would involve testing the device against those standards and comparing its performance to the predicate. However, details on the patient numbers or specific data sets used for these tests are not provided in this summary.
   • Data provenance: Not explicitly stated as "data provenance." The document mentions that the patient monitoring technologies have been in "clinical use for at least six years in the predicate device," and CSI's "field experience with these modalities in the predicate device has been satisfactory." This suggests that the predicate device's performance (and by extension, the new device's claim of equivalence) is supported by retrospective clinical use and field data, but for the 507EL's specific testing, the provenance of the test data (e.g., country, retrospective/prospective) is not detailed.

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

   • Not applicable as this is a traditional medical device, not an AI/ML device requiring expert ground truth for interpretation. Ground truth for physiological measurements is typically established by reference instruments or established clinical methodologies.

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

   • Not applicable. This is not an AI/ML device relying on human expert adjudication for its output.

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. This is not an AI/ML device.

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

   • The device itself is a standalone vital signs monitor. Its "performance for each monitoring modality has been confirmed to be equivalent to the predicate device" through "equivalence testing" and "applicable objective standards compliance." This implies the device's output (ECG, NIBP, SpO2, Temp, Resp measurements) was evaluated directly against established methods and standards, without necessarily "human-in-the-loop performance" in the context of an AI/ML algorithm's output interpretation. The "user" is a "professional health care provider" responsible for interpreting the data, but this refers to the clinical use of the monitor's displayed data, not an evaluation of an AI algorithm's assistance.

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

   • For physiological measurements like NIBP, ECG, SpO2, and Temperature, ground truth is typically established by:
     • Reference standard measurements: e.g., invasive blood pressure for NIBP, a gold-standard ECG recording device for ECG, co-oximetry for SpO2, or a calibrated thermometer for temperature.
     • Clinical validation protocols: specific testing methodologies outlined in the referenced performance standards (e.g., AAMI SP-10 for NIBP, AAMI EC-13 for ECG, EN 865/ASTM F 1415 for Oximetry) dictate how ground truth is obtained and used for evaluating device accuracy. The document states compliance with these standards.

7. The sample size for the training set:

   • Not applicable. This device does not employ machine learning that would require a "training set." Its core technologies are established and were already in "clinical use for at least six years in the predicate device."

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

   • Not applicable, as there is no training set for an AI/ML algorithm.

Ask a specific question about this device

This system is intended to monitor physiological parameters of patients within any healthcare environment. The user, responsible to interpret the monitored data made available, will be a professional health care provider. Physiological data, system alarms and patient data analysis will be available to the care provider from the monitor.

The 8100 / 8500 monitor measures and displays real time physiological data of the patient, including waveforms and numerical data. The 8100 / 8500 can be configured to monitor one or more of the following parameters: ECG, Noninvasive BP (NIBP), Invasive BP (IBP), SpO2, Temperature, Respiration, CO2, N2O, O2 and Halogenated Anesthetic Agents. For all these vital parameters, the 8100 / 8500 will be capable of limit alarms and alerts, printing of strip chart recordings and storing trends for retrospective review.

The provided text is a 510(k) summary for the Criticare Systems, Inc. Model 8100/8500 Vital Signs Monitor. This document is a premarket notification for a medical device seeking clearance from the FDA, claiming substantial equivalence to previously cleared predicate devices. It describes the device's function, intended use, and its compliance with relevant standards. However, it does not contain the detailed study results, acceptance criteria, or specific performance metrics in the way that would typically be presented for a standalone AI/software-as-a-medical-device (SaMD) study.

Based on the provided text, here's what can be extracted and what cannot:

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

• Acceptance Criteria: The document states that the device's performance for each monitoring modality "has been confirmed to be equivalent to the predicate devices" and that it "complies with applicable safety and performance standards." It lists numerous specific standards (e.g., EN 60601-2-30 NIBP Safety, AAMI SP-10 NIBP Performance, EN 865 Oximetry Performance).
• Reported Device Performance: The document generally states that the performance has been confirmed and complied with standards, but it does not provide numerical results or specific performance metrics against those standards. For example, it doesn't say "NIBP accuracy was within X mmHg, meeting the AAMI SP-10 requirement of Y mmHg."

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

• Not provided. The document refers to "equivalence testing" and "field experience" but does not detail the methodology, sample sizes, or data provenance of any specific tests or studies.

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

• Not applicable/Not provided. This document describes a vital signs monitor, not a diagnostic AI device requiring expert ground truth for interpretation of images or complex data. The "ground truth" for vital signs monitoring typically comes from established reference methods (e.g., a known SpO2 calibration, a reference NIBP cuff, or an invasive arterial line for IBP comparison). The document mentions "CSI's field experience with these modalities in the predicate devices has been satisfactory," suggesting real-world data, but no specific expert panel for ground truth generation is indicated.

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

• Not applicable/Not provided. No adjudication method is mentioned as this is not a study involving expert interpretation of data.

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 vital signs monitor, not an AI-assisted diagnostic device. Therefore, no MRMC study or AI assistance effect size is discussed.

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

• Applicable in a different context. The device is a standalone monitoring system that measures physiological parameters. Its performance, in comparison to predicate devices and standards, would be considered its "standalone" performance for each parameter. However, the document doesn't detail the specifics of such testing beyond stating compliance. The "user... will be a professional health care provider," indicating that human interpretation is part of the overall clinical use, but the device itself performs the measurements independently.

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

• Implied by standards. For vital signs monitors, ground truth typically involves reference devices or established physiological measurement techniques. For instance:
  • NIBP: Likely compared against invasive arterial blood pressure measurements or a highly accurate reference NIBP device.
  • SpO2: Likely compared against co-oximetry blood gas analysis or a reference oximeter in controlled desaturation studies.
  • ECG: Compared against a reference ECG device/system that accurately captures cardiac electrical activity.
  • Gas analysis (CO2, O2, N2O, Anesthetics): Likely compared against calibrated gas analyzers.
• The document implies that the ground truth for its "equivalence testing" and "compliance to standards" would have been established according to the methodologies prescribed by the relevant performance standards (e.g., AAMI SP-10 for NIBP, EN 865 for Oximetry).

8. The sample size for the training set

• Not applicable/Not provided. This is a hardware-based vital signs monitor, not an AI/machine learning model that undergoes "training." Its performance is based on established physiological measurement principles embedded in its design.

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

• Not applicable/Not provided. As there is no "training set" in the context of an AI/ML algorithm, this question is not relevant to the information provided.

Ask a specific question about this device

Ask a specific question about this device

Ask a specific question about this device

Ask a specific question about this device