Search Results

The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-lead ECG, heart rate, respiratory rate, pulse rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure, and patient posture and activity. VMS allows for the input of body temperature, and can display data from peripheral devices. VMS can generate alerts when rate-based carthythmias are detected and when physiological vital signs fall outside of selected parameters.

The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals. VMS includes Vios-proprietary monitoring software and a Vios-proprietary vitals sensor with two Vios-proprietary adapters. It is compatible with a medical grade, Bluetooth™-enabled NIBP cuff. The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices. The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile, multiple use, and rechargeable sensor that acquires 3-channel ECG, bioimpedance, 2-channel pulse oximetry, and tri-axial accelerometer data. The sensor contains signal acquisition firmware (embedded software) and wirelessly communicates acquired data via standard communication protocols (Bluetooth™) to the BSM SW for analysis and display. The Chest Sensor has a button that, when pressed, sends a patient call alert to the BSM SW. VMS Chest Sensor Adapter Models L2050E (Pulse Ox Ear Adapter) and L2050F (Pulse Ox Finger Adapter) are plastic, non-sterile, patient-worn, multiple use pulse oxygenation sensors that connect to the Vios Chest Sensor and are secured to the patient via medical grade ECG electrodes.

The provided text is a 510(k) Summary for the Vios Monitoring System™ Model 2050. This document outlines the device's intended use, regulatory information, and a summary of the testing performed to demonstrate substantial equivalence to predicate devices.

However, the document does not contain specific details about acceptance criteria, reported device performance metrics (e.g., sensitivity, specificity, accuracy for arrhythmia detection), the sample size of a test set, the number and qualifications of experts for ground truth establishment, adjudication methods, or effects of AI assistance on human readers.

The text focuses on hardware and software description, regulatory compliance, and general types of testing conducted (electrical safety, biocompatibility, usability, software development lifecycle, specific clinical testing for pulse oximetry and respiratory rate). It mentions that "VMS can generate alerts when rate-based cardiac arrhythmias are detected," but does not provide performance metrics for this specific function in the context of acceptance criteria.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them based solely on the provided text. The information required for your questions (especially points 1-7, and 9) is not present in this 510(k) Summary.

Here's an overview of what is mentioned in relation to testing, which is very high-level:

Summary of Non-Clinical, Clinical, and Conformance Testing:
The document states that "The safety, effectiveness, and substantial equivalency of the VMS Model 2050 have been confirmed through the following non-clinical, clinical, and conformance testing:"

• Non-clinical:

  • Electrical safety, EMC, and vitals sign monitoring standards (IEC 60601-1, IEC 60601-1-2, IEC 60601-1-8, IEC 60601-2-27, IEC 60601-2-49, EC53)
  • Biocompatibility standards (ISO 10993)
  • Usability and human factors standards (EN 62366)
  • Transportation Simulation testing (ASTM D4169-16)
  • Software development life cycle (EN 62304)
  • Risk Management (ISO 14971)

• Clinical:

  • Pulse oximetry clinical testing (IEC 80601-2-61)
  • Respiratory Rate clinical testing

Missing Information:

• Acceptance Criteria Table & Reported Performance: Not provided for any specific vital sign or arrhythmia detection.
• Sample size (test set) & Data Provenance: Not detailed. It only mentions "clinical testing."
• Number & Qualifications of Experts, Adjudication Method: Not specified for any ground truth establishment.
• MRMC Study / AI Assistance: Not mentioned. The device generates alerts for rate-based arrhythmias, but there's no comparative study with human readers described or any 'AI' effect size.
• Standalone Performance: While the device has an algorithm for arrhythmia detection, the specific performance metrics (sensitivity, specificity) are not reported here.
• Type of Ground Truth: For pulse oximetry and respiratory rate clinical testing, it's implied that a reference standard was used as per relevant IEC standards, but the exact method (e.g., expert consensus on ECG, pathology) for arrhythmia detection is not disclosed.
• Training Set Sample Size: Not mentioned, as this document focuses on substantial equivalence testing rather than algorithm development.
• Ground Truth for Training Set: Not mentioned.

In summary, while the document indicates that various tests were performed to support substantial equivalence, it does not provide the granular detail needed to answer your questions regarding acceptance criteria and performance metrics for the device's diagnostic or alerting capabilities.

Ask a specific question about this device

The Sienna Ultimate EEG amplifier is intended to be used as a front end amplifier to acquire, store and transmit electrophysiological signals in a wired or wireless mode for the EMS Neurodiagnostic system.

The Sienna Ultimate is a small portable device which is capable of acquiring a variety of electrophysiological signals at variable sampling frequencies and can be used in a wide variety of EEG applications. The proposed device consists of two models designated as the 32 channel and the 64 channel amplifier in a wireless or wired mode, passive headboxes, medical grade power supply, WLAN access point (for wireless models) or medical grade isolated LAN cable (for wired models), Sienna EEG software. The following accessories can be connected to the passive headboxes: EEG electrodes, EEG headcaps and pulse oximeter sensors.

The provided text describes the safety and performance testing for the "Sienna Ultimate Wireless Amplifier" (EEG Amplifier), but it does not present acceptance criteria in a quantitative table or a study proving that the device meets those criteria with performance metrics. The information focuses on demonstrating substantial equivalence to a predicate device through adherence to recognized standards.

Therefore, many of the requested details about acceptance criteria, reported performance, sample sizes, expert involvement, and ground truth are not explicitly available in the provided text.

Here's an analysis based on the information that is available:

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

The document doesn't provide a table of quantitative acceptance criteria with corresponding device performance metrics. Instead, it relies on demonstrating compliance with recognized safety and performance standards. The "Results" column in the "Safety Testing" table primarily states "There were no deviations from the standard and the proposed device passed the applicable tests and requirements."

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

The document does not specify the sample size used for any of the tests. It refers to "the subject device" or "the sample of the proposed device" passing tests, implying at least one device was tested. There is no information about 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 (e.g. radiologist with 10 years of experience):

This information is not applicable and not provided. The testing described is primarily engineering and regulatory compliance testing against defined standards, not a clinical study requiring expert ground truth for interpretation of observational data.

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

This is not applicable as there's no diagnostic or interpretive task described that would require an adjudication method.

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 is not applicable. The device is a physiological signal amplifier (EEG amplifier), not an AI-assisted diagnostic tool for human readers. No MRMC study was conducted or mentioned.

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

This is not applicable. The device is hardware (an EEG amplifier), not software or an algorithm.

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

This is not applicable directly in the way it's usually considered for diagnostic devices. The "ground truth" for the tests performed was compliance with the technical specifications and requirements outlined in the referenced international standards (e.g., IEC 60601-1, IEC 60601-2-26).

8. The sample size for the training set:

This is not applicable as the device is a hardware amplifier and not a machine learning model that requires a training set.

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

This is not applicable for the same reason as above.

Summary of available information regarding compliance with standards:

The study proving the device meets its requirements is a series of engineering and regulatory compliance tests against recognized international standards.

Conclusion from the document: "The Sienna Ultimate EEG amplifier meets the functional claims and intended use as described in the product labeling. The safety and effectiveness are substantially equivalent to the predicate device, Nicolet Wireless EEG Amplifier."

Ask a specific question about this device

The Dyna-Vision Telemontoring System is a wreless monitoring system intended for use by healthcare professionals for continuous collection of physiological data in home and healthcare settings and for normal daily activities. Physiological data recorded include: Electrocardiography (EGG), Heart Rate variability (R-R interval), Peripheral capillary Oxygen saturation (SpO2), Skin Temperature and respiration effort Data is transmitted wirelessly in near real time to a central location where it is stored for analysis. The Dyna-Vision™ system can be configured by Authorized Persons to notify healthcare professionals when physiological data falls outside selected parameters. Data from the Dyna-Vision™ system is intended to be used by healthcare professionals as an aid to diagnosis and treatment.

The device is intended for use on general care patients aged 18 years or more, as a general patient monitor, to provide physiological information. It is not intended for use on critical care patients.

The Dyna-Vision system is a wireless multi-parameter data collection systems that monitors physiological data such as: Electrocardiography (EGG), Heart Rate, Heart Rate variability (R-R interval), Peripheral capillary Oxygen saturation (SpO2), Skin Temperature and Rate of respiratory effort.
The system consist of:
• A body-worn unit with sensor input modules for the near real time acquisition of the physiological data with built-in wireless communication for data transmission.
• A telemetry server to receive the physiological data and transmit the physiological data to
• A workstation installed on a central server (or PC) equipped with software with which the physician can process the physiological data and create reports regarding the transmitted data, and read and configure alerts/notifications when a threshold value is exceeded. The alert function is an adjunct to and not intended to replace vital sign monitoring.
The software includes algorithms for Heart Rate, Heart Rate variability (R-R interval) and rate of respiratory effort.
The device is intended to be used by clinicians and medically qualified personnel in healthcare facilities. The body-worn unit for data acquisition, is a transportable battery-operated unit to record Electrocardiograph (ECG), Heart Rate variability (R-R interval), Peripheral capillary Oxygen saturation (SpO2), Skin Temperature and Rate of respiratory effort to be also used by the patient in the home setting and anywhere where WIFI or cell communication is available.
The Dyna-Vision system works with 3rd party 510(k) cleared SpO2 module (Nonin OEM III, K092101), and ECG patient lead (Scottcare K092947).
The device is intended for use on general care patients aged 18 years or more.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Dyna-Vision Telemonitoring System:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present acceptance criteria in a quantitative table format with corresponding performance metrics like a typical validation study report. Instead, the "Substantial Equivalence Comparison Table" (Pages 7-10) compares the Dyna-Vision system's features and specifications against multiple predicate devices. The "acceptance criteria" are implied by the features and performance characteristics of the predicate devices. The non-clinical tests section (Page 5) lists the characteristics tested.

Based on the provided information, I can infer the "acceptance criteria" through the comparison with predicate devices and the performance "reported" by the Dyna-Vision system's specifications.

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

The document explicitly states: "No clinical studies were utilized for the purpose of obtaining safety and Clinical Performance effectiveness data." This indicates that no patient-based "test set" in the traditional sense was used for clinical performance evaluation. The evaluation was based on non-clinical (bench) testing and substantial equivalence to predicate devices. Therefore, sample size and data provenance (country of origin, retrospective/prospective) for a test set of patient data are not applicable here.

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

Since no clinical studies or patient-based test sets were used, there were no experts establishing ground truth for such a set. The "ground truth" for the non-clinical tests would have been established by the standards and methodologies used in the bench testing.

4. Adjudication Method for the Test Set

As no clinical test set was used, no adjudication method was employed.

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

The document does not mention any MRMC comparative effectiveness study. The device is a "Telemonitoring System," not an AI diagnostic tool designed to assist human readers in interpreting medical images or complex data in an MRMC study context. Its purpose is continuous collection of physiological data and alerting based on parameters.

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

The document details extensive standalone (algorithm only/device only) performance testing through "Bench testing" and adherence to "Referenced Standards and Performance Testing." This includes:

• Electrocardiograph (ECG)
• Heart rate variability (R-R interval)
• Heart rate
• SpO2
• Skin Temperature
• ECG impedance for Rate of respiratory effort
• Notification (alert function)
• Measurement accuracy
• Communication, data transmission and storage
• Reliability (QoS) Wireless Quality of Service
• Electromagnetic compatibility (EMC)
• Electrical safety testing
• Wireless Coexistence Wi-Fi testing
• Software verification and validation testing
• Biocompatibility verification

The device's algorithms for Heart Rate, Heart Rate variability (R-R interval), and rate of respiratory effort were also implicitly tested in this standalone context against the performance claims.

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

For the non-clinical bench testing, the ground truth would have been established by:

• Reference measurement equipment/systems: Calibrated medical devices or simulators that provide known, accurate physiological signals for comparison.
• Established engineering and medical standards: The device was tested against standards such as IEC 60601-1, IEC 60601-1-2, IEC 60601-1-11, IEC 60601-2-47, AAMI/ANSI EC38, AAMI/ANSI EC57, ISO 80601-2-61, and IEC 80601-2-59. These standards define the acceptable performance limits and test methodologies for medical electrical equipment, including physiological monitors.

8. The sample size for the training set

The document explicitly states "No clinical studies were utilized for the purpose of obtaining safety and Clinical Performance effectiveness data." This implies that patient data was likely not used for training any machine learning or AI models in a traditional sense. The device appears to rely on established signal processing algorithms for its physiological measurements rather than complex, data-trained AI. Therefore, a "training set" in the context of machine learning is not discussed or implied.

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

Since no clinical training set is mentioned or implied, the question of how its ground truth was established is not applicable. The algorithms for Heart Rate, Heart Rate variability, and respiratory effort are likely based on well-understood physiological principles and signal processing techniques, rather than being "trained" on a large dataset with annotated ground truth.

Ask a specific question about this device

The Natus Quantum Amplifier is intended to be used as an electroencephalograph: to acquire, display, store and archive electrophysiological signals. The amplifier should be used in conjunction with Natus NeuroWorks™/SleepWorks™ software to acquire scalp and intracranial electroencephalographic (EEG) signals as well as polysomnographic (PSG) signals. The amplifier is designed to facilitate functional mapping using a Digital Switch Matrix. The Digital Switch Matrix portion of the headbox is a combination of hardware relays and software controls allowing the user (physician or technologist) to switch electrode pairs between the EEG recording amplifier and the external cortical stimulator for stimulus delivery.

The Natus Quantum Amplifier is intended to be used by trained medical professionals, and is designed for use in clinical environments such as hospital rooms, epilepsy monitoring units, intensive care units, and operating rooms. It can be used with patients of all ages, but is not designed for fetal use.

The Natus Quantum amplifier is comprised of a base unit and several breakout boxes. It is part of a system that is made up of a personal computer, a photic stimulator, an isolation transformer, video and audio equipment, networking equipment, and mechanical supports. The amplifier also contains an internal switch matrix to allow for a connection to an external cortical stimulator.

EEG and other physiological signals, from scalp electrodes, grid or needle electrodes, and other accessories such as pulse oximeters can be acquired by the Natus Quantum amplifier. These signals are digitized and transmitted to the personal computer running the Natus NeuroWorks software. The signals are displayed on the personal computer and can be recorded to the computer's local storage or to remote networked storage for later review.

The provided text describes the Natus Quantum Amplifier, an electroencephalograph, and its regulatory submission (K143440). However, the document does not contain a study that directly proves the device meets specific acceptance criteria in terms of clinical performance metrics like sensitivity, specificity, or accuracy.

The document focuses on demonstrating substantial equivalence to predicate devices (EMU128S and NeuroLink IP 256) primarily through technical specifications and compliance with various safety, EMC, and quality standards. The "Performance Tests" section is very brief and refers to non-clinical verification testing rather than clinical efficacy studies.

Therefore, the following information is based on what is available or can be inferred from the provided text. Many requested fields will be marked as "Not Applicable" or "Not Provided" because the document does not describe the kind of clinical study you're asking about.

1. Table of Acceptance Criteria and Reported Device Performance

Note on Acceptance Criteria: The document implies that meeting the specified technical characteristics that are substantially equivalent or superior to the predicate devices, and passing internal design verification tests, are the "acceptance criteria" for regulatory clearance based on substantial equivalence. It does not provide clinical acceptance criteria.

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

• Sample Size: Not Applicable. The document describes non-clinical verification testing of the device hardware/software, not a clinical study on patient data.
• Data Provenance: Not Applicable. No patient data was used for the described performance tests.

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

• Number of Experts: Not Applicable. Ground truth for clinical data is not relevant to the described non-clinical verification tests.
• Qualifications of Experts: Not Applicable.

4. Adjudication method for the test set

• Adjudication Method: Not Applicable. No clinical test set requiring adjudication was described.

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. This document describes an EEG amplifier, not an AI-assisted diagnostic tool.

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

• Standalone Performance: Not Applicable. This is a hardware device (EEG amplifier) with associated software for data acquisition, display, storage, and archiving. It is not an algorithm for standalone diagnostic performance.

7. The type of ground truth used

• Type of Ground Truth: For the "Performance Tests" (Signal Quality Verification Test, Functionality Verification Test), the ground truth would be the design specifications and expected operational parameters of the device. These tests verify if the actual output matches the designed output. No clinical "ground truth" (e.g., pathology, outcomes data) for diagnosis is mentioned for these tests.

8. The sample size for the training set

• Sample Size: Not Applicable. This is not an AI/machine learning device that requires a training set.

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

• Ground Truth Establishment: Not Applicable. (See point 8)

Ask a specific question about this device

Model X-100: Nonin's SenSmart™ Model X-100 Universal Oximetry System is a modular system and is indicated for use in simultaneously measuring, displaying, monitoring, and recording up to six (6) channels of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate or cerebral or somatic hemoglobin oxygen saturation (rSO2) of blood underneath the sensor. Patient populations include adult, pediatric, infant, and neonate through the use of SenSmart compatible sensors. The SenSmart system is intended for use in hospitals, long-term care, medical facilities, sleep laboratories, sub-acute environments, and Emergency Medical Services (EMS), including patient transport. The X-100 SenSmart system may be used for spot-checking and continuous monitoring with patient alarms. The SenSmart pulse oximetry (SpO2) functionality is suitable for use in both motion and non-motion conditions, including patients who are well or poorly perfused.

Model 8100S(x): Nonin's Model 8100S(X) reusable soft sensor is indicated for non-invasive spot checking and/or continuous monitoring of adult and pediatric patients who are well or poorly perfused, during both motion and non-motion conditions. It is intended for use in environments including the operating room, surgical recovery, critical care, emergency room, long-term care, and mobile environments.

SenSmart Download Software: The SenSmart Download Software is an optional accessory for use with Nonin's X-100M SenSmart Monitor only. It is intended for use by healthcare professionals when 1) transferring data from the X-100M to a computer in order to maintain individual records of oximetry data, 2) reviewing data according to user-selected parameters, and 3) generating reports.

The SenSmart X-100 Oximetry System performs both pulse oximetry and regional oximetry measurements. The SenSmart X-100 Oximetry System works with all Nonin Equanox regional oximetry sensors (Model 8004CA, Model 8003CA, Model 8004CB and Model 8004CB-NA). The SenSmart compatible pulse oximetry Soft Sensor Model 8100S(x) is used with the Model X-100 System. The system consists of the sensor, the X-100SP signal processor (up to 6), extensions cables, the X-100H hub for multiple channels, the X-100M SenSmart Monitor which includes display, alarms, and memory. The SenSmart Download software is included for data storage review and reporting on a Windows PC.

The Nonin Medical, Inc. Model X-100 Universal Oximetry System is designed to measure and monitor arterial hemoglobin oxygen saturation (SpO2), pulse rate, and cerebral or somatic hemoglobin oxygen saturation (rSO2). The device underwent several tests to ensure its performance and safety, including functional and safety testing, rSO2 accuracy testing, SpO2 accuracy testing, and a usability study.

Here's the breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

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

• SpO2 Accuracy Testing:

  • Sample Size: 13 healthy, non-smoking, light-to-dark-skinned subjects.
  • Data Provenance: Prospective, conducted in an independent research laboratory. The document does not specify the country of origin, but "Nonin Medical, Inc." is based in Plymouth, MN, USA.

• Usability / Human Factors Study:

  • Sample Size: 20 healthcare professionals.
  • Data Provenance: Prospective, likely conducted within a controlled environment to simulate clinical use. Country of origin not specified, but implied to be in the same geographic region as the manufacturer.

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

• SpO2 Accuracy Testing:

  • The ground truth for SpO2 was established by comparing the device's SpO2 measurements to arterial hemoglobin oxygen (SaO2) values determined from blood samples using four (4) laboratory co-oximeters. The final SpO2 values were paired with the average of three Radiometer CO-oximeters (ALB80Flex OSM). While these are not "experts" in the human sense, the co-oximeters serve as a highly accurate, standardized ground truth instrument for SaO2 measurement. No human experts are mentioned for establishing this specific ground truth.

• Usability Study:

  • The "ground truth" for usability was established through the observations of the study personnel and user feedback captured via questionnaires. No specific number or qualifications of "experts" are provided to establish the ground truth for usability, beyond the general conduct by "Nonin personnel" who provided in-service training and an "observer" during task performance.

4. Adjudication Method for the Test Set

• SpO2 Accuracy Testing: The method involved taking multiple arterial blood samples at different plateaued SpO2 levels and running them on four co-oximeters. The average of three Radiometer co-oximeters was used as the reference against which the device's SpO2 readings were compared. This isn't a traditional "adjudication" in the sense of multiple human readers resolving discrepancies, but rather a robust method of establishing a highly accurate instrumental ground truth.

• Usability Study: An observer was present to document whether tasks were performed appropriately and if the user had difficulty. User responses and body language were also documented. Task effectiveness was the primary objective, suggesting a pass/fail assessment based on predefined criteria, but no formal adjudication process by multiple individuals is described.

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 comparative effectiveness study was not done. This device is an oximetry system and does not involve AI for interpretation or human-in-the-loop performance improvement. The studies described focus on the device's accuracy in measuring physiological parameters and its usability without, or as a replacement for, human interpretation of raw data.

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

• Yes, a standalone performance study was clearly the primary focus for SpO2 and rSO2 accuracy. The SpO2 accuracy testing directly compared the device's measured SpO2 values to the co-oximeter reference, operating independently of human interpretation of the measurement output. The rSO2 accuracy was demonstrated through direct device comparison and testing with the predicate system. The Usability study evaluated human interaction with the device, but the core accuracy measurements were standalone.

7. The Type of Ground Truth Used

• SpO2 Accuracy Testing: Instrumental Ground Truth (Laboratory Co-oximetry for SaO2 values).
• rSO2 Accuracy Testing: Comparison to a predicate device's measured rSO2 values, which would have been established with similar instrumental ground truth methods.
• Usability Study: User feedback and observation of task completion against predefined usability criteria.

8. The Sample Size for the Training Set

• The provided document describes pre-market testing for substantial equivalence. It does not mention a "training set" as would be relevant for machine learning algorithms. The device is hardware-based with embedded software, and its performance is verified through testing, not developed through machine learning. Therefore, this question is not applicable in the context of this device.

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

• As the concept of a "training set" is not applicable to this pre-market submission for a hardware medical device, this question is also not applicable.

Ask a specific question about this device