Search Filters

Search Results

Found 5 results

510(k) Data Aggregation

    K Number
    K200069
    Date Cleared
    2020-03-13

    (60 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Disposable SpO2 Sensor is indicated for continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR) for adults in hospital environment.

    Device Description

    The proposed device, Disposable SpO2 Sensor is an accessory to the patient monitors, which are intended for continuous monitoring of functional arterial oxygen saturation and pulse rate. The compatible patient monitor is EDAN iM50 cleared in K113623. The sensor shall be connected to its corresponding monitor through adapter cable model CK-03-452. Oxygenation of blood is measured by detecting the infrared and red-light absorption characteristics of deoxygenated hemoglobin and oxygenated hemoglobin, which consists of a probe attached to the patient's finger. The sensor is connected to a data acquisition system which is used to calculate and display oxygen saturation levels and heart rate conditions. Each sensor has two LEDs, emitting both red and infrared light, and a photodiode. Red and infrared light are emitted through fingertips and received by a photodiode can be induced to change with pulse light intensity; the electrical signals in the form of change. Then the received signal is forwarded to the corresponding oximeter that amplifies the signal and an algorithm that calculates the ratio. By measuring the wave crest of the pulse wave and the absorbance of the trough, SpO2 is calculated to obtain the correct oxygen saturation value. The saturation value is determined by the percentage ratio of the oxygenated hemoglobin (HbO2) to the total amount of hemoglobin (Hb).

    AI/ML Overview

    The provided text is a 510(k) Summary for a Disposable SpO2 Sensor (K200069). It details the device's technical specifications, intended use, and comparison to a predicate device (K191279). The document also outlines the performance data submitted to support the substantial equivalence determination, including biocompatibility, non-clinical, and clinical studies.

    Based on the provided text, here's the information requested:

    1. Table of Acceptance Criteria and Reported Device Performance

    ParameterAcceptance Criteria (Predicate Device)Reported Device Performance (Subject Device)
    SpO2 Range70% - 100%70% - 100%
    SpO2 Accuracy+/- 3%+/- 3%
    PR Range30 bpm - 250 bpm30 bpm - 250 bpm
    PR Accuracy+/- 3+/- 3
    Electrical SafetyComplied with IEC 60601-1Complied with IEC 60601-1
    EMCComplied with IEC 60601-1-2Complied with IEC 60601-1-2
    PerformanceComplied with ISO 80601-2-61Complied with ISO 80601-2-61
    Biocompatibility (Cytotoxicity)Complied with ISO 10993-5Complied with ISO 10993-5
    Biocompatibility (Skin Irritation)Complied with ISO 10993-10Complied with ISO 10993-10
    Biocompatibility (Sensitization)Complied with ISO 10993-10Complied with ISO 10993-10

    Study Proving Acceptance Criteria:

    The study that proves the device meets the acceptance criteria is a clinical hypoxia test conducted on human adult volunteers to validate the accuracy of the Disposable SpO2 Sensor against arterial oxygen saturation (SaO2) determined by co-oximetry. This clinical study was performed according to ISO 80601-2-61:2017 and FDA guidance for Pulse Oximeters - Premarket Notification Submissions.

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

    • Sample Size: The document states "human adult volunteers" but does not specify the exact number of subjects used in the clinical hypoxia test.
    • Data Provenance: The data is prospective clinical data obtained from human adult volunteers. The country of origin is not explicitly stated, but the applicant and correspondent are based in Shenzhen, China.

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

    The document does not provide information about the number or qualifications of experts used to establish the ground truth. It states that arterial oxygen saturation (SaO2) was "determined by co-oximetry," which is a laboratory method, not typically an expert consensus per se.

    4. Adjudication Method for the Test Set

    The document does not mention any adjudication method for the test set. The ground truth was established by co-oximetry.

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

    No, an MRMC comparative effectiveness study was not conducted. This is a medical device, specifically a sensor, that provides a direct measurement, rather than an interpretation requiring multiple readers.

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

    Yes, the clinical hypoxia test evaluated the standalone performance of the device's ability to measure SpO2. The device functions as a sensor with an algorithm to calculate SpO2 and PR, and the clinical study validated this algorithm's accuracy without a human explicitly "in the loop" for interpretation.

    7. The Type of Ground Truth Used

    The type of ground truth used was outcomes data / reference standard measurement, specifically arterial oxygen saturation (SaO2) as determined by co-oximetry. Co-oximetry is a highly accurate laboratory method for measuring various hemoglobin species, including SaO2.

    8. The Sample Size for the Training Set

    The document does not specify a sample size for a training set. This device is a sensor and likely uses empirically derived algorithms and calibration, rather than a machine learning model that requires a distinct training set. The clinical study mentioned is for validation/testing.

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

    As no training set is explicitly mentioned or implied for a machine learning model, the method for establishing its ground truth is not applicable in this context. The core algorithm for pulse oximetry is based on known physical principles of light absorption by blood components.

    Ask a Question

    Ask a specific question about this device

    K Number
    K192608
    Date Cleared
    2020-01-24

    (126 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Disposable SPO2 Sensor is indicated for continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR) for adult patients weighing greater than 40 kg at hospital facilities.

    Device Description

    The proposed device, Disposable SpO2 Sensor is accessory to the oximeter, which is intended for continuous monitoring of functional arterial oxygen saturation and pulse rate in non-invasive with U.S. legally marketed oximeter. It is only intended for adult. The sensor shall be connected with the corresponding monitor (Nellcor N-600). Oxygenation of blood is measured by detecting the infrared and red-light absorption characteristics of deoxygenated hemoglobin and oxygenated hemoglobin, which consists of a probe attached to the patient's finger. The sensor is connected to a data acquisition system which is used to calculate and display oxygen saturation levels and heart rate conditions. Each sensor has two LEDs, emitting both red and infrared light, and a photodiode. Red and infrared light lit alternately according to certain sequence, when the fingertips of capillary repeatedly with the heart pumps blood congestion, light emitting diode after blood vessels and projected onto a photodiode, photodiode can be induced to change with pulse light intensity, the electrical signals in the form of change. Then the received signal is forwarded to the corresponding oximeter that amplifies the signal and an algorithm that calculates the ratio. By measuring the wave crest of the pulse wave and the absorbance of the trough, SpO2 is calculated to obtain the correct oxygen saturation value. The saturation value is determined by the percentage ratio of the oxygenated hemoglobin (HbO2) to the total amount of hemoglobin (Hb).

    AI/ML Overview

    The provided text describes a 510(k) premarket notification for a Disposable SpO2 Sensor and includes information about its performance data. However, it does not contain a detailed study proving the device meets specific acceptance criteria in the format requested. While it states that clinical studies were conducted to verify accuracy and that the device complies with ISO 80601-2-61:2017, the specifics of those studies (sample size, ground truth methodology, expert qualifications, etc.) are lacking.

    Therefore, I will extract what is available and indicate where information is not provided in the document.

    1. Table of Acceptance Criteria and Reported Device Performance

    ParameterAcceptance Criteria (Predicate Device)Reported Device Performance (Subject Device)
    SpO2 Range70% - 100%70% - 100%
    SpO2 Accuracy±3%±3%
    PR Range35 bpm - 240 bpm30 bpm - 250 bpm
    PR Accuracy±2 bpm±3 bpm
    SterilityNoNo
    UsageDisposableDisposable
    Electrical SafetyComplied with IEC 60601-1Complied with IEC 60601-1
    EMCComplied with IEC 60601-1-2Complied with IEC 60601-1-2
    PerformanceComplied with ISO 80601-2-61Complied with ISO 80601-2-61
    BiocompatibilityComplied with ISO 10993-5Complied with ISO 10993-5
    Skin IrritationComplied with ISO 10993-10Complied with ISO 10993-10
    SensitizationComplied with ISO 10993-10Complied with ISO 10993-10

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

    The document states: "Clinical hypoxia test results were obtained in human adult volunteers to validate the accuracy of disposable SpO2 Sensor versus arterial oxygen saturation (SaO2) as determined by co-oximetry."

    • Sample Size (Test Set): Not specified.
    • Data Provenance: Human adult volunteers, prospective study (clinical hypoxia test). Country of origin is not specified, but the submission sponsor and correspondent are based in Shenzhen, China.

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

    • Number of Experts: Not specified.
    • Qualifications of Experts: Not specified.

    4. Adjudication method for the test set

    • Adjudication Method: Not specified. The ground truth was established by "co-oximetry," which is an objective measurement rather than expert consensus on images.

    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 an accessory device (SpO2 sensor) for an oximeter, not an AI-powered diagnostic system involving human readers. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is not applicable and was not performed.

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

    Yes, the performance evaluation of the Disposable SpO2 Sensor for SpO2 accuracy and PR accuracy is a standalone assessment of the device's measurement capabilities. The clinical hypoxia test specifically aims to validate the accuracy of the device against a reference standard (co-oximetry). There is no "human-in-the-loop" component in the performance of the sensor itself, as it is a measurement device.

    7. The type of ground truth used

    • Type of Ground Truth: Arterial oxygen saturation (SaO2) as determined by co-oximetry, which is considered an objective, established medical measurement for blood oxygen levels.

    8. The sample size for the training set

    The document does not mention a "training set" in the context of machine learning. The device's performance is verified through clinical testing against a reference standard rather than through algorithm training on a dataset.

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

    Not applicable as no training set for a machine learning algorithm is discussed. The device is a direct measurement sensor.

    Ask a Question

    Ask a specific question about this device

    K Number
    K191279
    Date Cleared
    2019-12-06

    (207 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Caremed Disposable SpO2 Sensors are indicated for continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR) for adult, pediatric and infant patient populations.

    Device Description

    The proposed device, Disposable SpO2 Sensors are accessories to the patient monitors, which are intended for continuous non-invasive monitoring of functional arterial oxygen saturation and pulse rate. The compatible patient monitor is Nihon Kohden BSM-5135A. The sensor shall be connected to its corresponding monitor through Caremed adapter cable model SZ30-36. Oxygenation of blood is measured by detecting the infrared and red-light absorption characteristics of deoxygenated hemoglobin and oxygenated hemoglobin, which consists of a probe attached to the patient's finger. The sensor is connected to a data acquisition system which is used to calculate and display oxygen saturation levels and heart rate conditions. Each sensor has two LEDs, emitting both red and infrared light, and a photodiode. Red and infrared light lit alternately according to certain sequence, when the fingertips of capillary repeatedly with the heart pumps blood congestion, light emitting diode after blood vessels and projected onto a photodiode, photodiode can be induced to change with pulse light intensity, the electrical signals in the form of change. Then the received signal is forwarded to the corresponding oximeter that amplifies the signal and an algorithm that calculates the ratio. By measuring the wave crest of the pulse wave and the absorbance of the trough, SpO2 is calculated to obtain the correct oxygen saturation value. The saturation value is determined by the percentage ratio of the oxygenated hemoglobin (HbO2) to the total amount of hemoglobin (Hb).

    AI/ML Overview

    This document describes the performance data and acceptance criteria for the Disposable SpO2 Sensor (K191279).

    1. Table of Acceptance Criteria and Reported Device Performance:

    FeatureAcceptance Criteria (Predicate Device K142832)Reported Device Performance (Subject Device)Comparison
    SpO2 Range70%-100%70%-100%Same
    SpO2 Accuracy±3%±3%Same
    PR Range30 bpm - 250 bpm30 bpm - 250 bpmSame
    PR Accuracy±3±3Same
    Electrical SafetyComplied with IEC 60601-1Complied with IEC 60601-1Same
    EMCComplied with IEC 60601-1-2Complied with IEC 60601-1-2Same
    PerformanceComplied with ISO 80601-2-61Complied with ISO 80601-2-61Same
    Biocompatibility: CytotoxicityComplied with ISO 10993-5Complied with ISO 10993-5Same
    Biocompatibility: Skin IrritationComplied with ISO 10993-10Complied with ISO 10993-10Same
    Biocompatibility: SensitizationComplied with ISO 10993-10Complied with ISO 10993-10Same

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

    The document states that "Clinical hypoxia test results were obtained in human adult volunteers to validate the accuracy of Caremed Disposable SpO2 Sensors versus arterial oxygen saturation (SaO2) as determined by co-oximetry."
    For the expanded indication to include infants (3 kg < weight < 15 kg), the document states, "This specification has been verified and validated according to ISO 80601-2-61: 2017 clause 201.12.1.101 SpO2 accuracy of pulse oximeter equipment."

    • Sample Size: The exact number of human adult volunteers used for the clinical hypoxia test is not explicitly stated. Similarly, the sample size for the infant validation is not provided.
    • Data Provenance: The general nature of the clinical hypoxia test in "human adult volunteers" suggests prospective data collection for the purpose of the study. The document does not specify the country of origin, but the submission sponsor is Shenzhen Caremed Medical Technology Co., Ltd. in China.

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

    The document mentions that "Clinical hypoxia test results were obtained in human adult volunteers to validate the accuracy of Caremed Disposable SpO2 Sensors versus arterial oxygen saturation (SaO2) as determined by co-oximetry."

    • Number of Experts: The document does not specify the number of experts used.
    • Qualifications of Experts: The document does not specify the qualifications of the experts, other than implying they would be qualified to perform arterial blood gas measurements and co-oximetry.

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

    The document does not provide information regarding any adjudication method used for the clinical test set data. The ground truth was established by co-oximetry.

    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 device is a Disposable SpO2 Sensor, a medical device for physiological monitoring, not an AI-powered diagnostic imaging tool. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is not applicable to this submission.

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

    The device itself is a sensor that generates measurements (SpO2 and pulse rate) which are then processed by an oximeter (patient monitor). The clinical testing assessed the accuracy of these measurements against a gold standard (co-oximetry), which effectively evaluates the "standalone" performance of the sensor's ability to accurately measure physiological parameters. There is no explicit mention of a "human-in-the-loop" component for interpretation of the SpO2 values that would differ from standard clinical practice with such devices.

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

    The ground truth for the clinical accuracy study was established by arterial oxygen saturation (SaO2) as determined by co-oximetry. This is considered a gold standard for measuring blood oxygen levels.

    8. The sample size for the training set:

    Pulse oximetry devices typically do not have a "training set" in the context of machine learning algorithms for image interpretation or complex diagnostic tasks. Their performance is primarily based on the physical principles of light absorption by hemoglobin. While there might be internal calibration data or historical performance data used in the development of the device's signal processing algorithms, the document does not specify a training set sample size in the way it would be defined for AI/ML models.

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

    As noted above, a distinct "training set" in the AI/ML sense is not applicable to traditional pulse oximetry devices. The ground truth for developing and calibrating the device's underlying principles and algorithms would be based on controlled experiments and physiological models that relate light absorption to blood oxygen saturation, typically validated against gold standard measurements like co-oximetry in a laboratory or controlled clinical setting. The document does not provide details on how this early-stage ground truth was established for the development of the device's core technology. The clinical studies mentioned are for validation of the final product.

    Ask a Question

    Ask a specific question about this device

    K Number
    K181270
    Manufacturer
    Date Cleared
    2018-09-07

    (116 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Disposable and Reusable SPO2 Sensors are indicated for continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR) for adult patients weighing greater than 40 kg at hospital facilities.

    Device Description

    The proposed device, Disposable and Reusable SpO2 Sensors are accessories to the oximeters, which are intended for spot checking or continuous monitoring of functional arterial oxygen saturation and pulse rate in non-invasive with U.S. legally marketed oximeters or patient monitors. The SSD-001-W09AN sensors is disposable while the SS-010-AF10 and SS-018-AF10 sensors are reusable. They are only intended for adult.

    The sensor shall be connected with its corresponding monitor. Oxygenation of blood is measured by detecting the infrared and red light absorption characteristics of deoxygenated hemoglobin and oxygenated hemoglobin, which consists of a probe attached to the patient's finger. The sensor is connected to a data acquisition system which is used to calculate and display oxygen saturation levels and heart rate conditions.

    Each sensor has two LEDs, emitting both red and infrared light, and a photodiode. Red and infrared light lit alternately according to certain sequence, when the fingertips of capillary repeatedly with the heart pumps blood congestion, light emitting diode after blood vessels and projected onto a photodiode, photodiode can be induced to change with pulse light intensity, the electrical signals in the form of change. Then the received signal is forwarded to the corresponding oximeter that amplifies the signal and an algorithm that calculates the ratio. By measuring the wave crest of the pulse wave and the absorbance of the trough, SpO2 is calculated to obtain the correct oxygen saturation value. The saturation value is determined by the percentage ratio of the oxygenated hemoglobin (HbO2) to the total amount of hemoglobin (Hb).

    AI/ML Overview

    Here's an analysis of the provided information regarding the acceptance criteria and study for the Disposable SpO2 Sensors and Reusable SpO2 Sensors:

    1. Table of Acceptance Criteria and Reported Device Performance

    The document explicitly states the acceptance criteria for SpO2 and Pulse Rate (PR) accuracy, and it reports that the device meets these requirements.

    Acceptance CriteriaReported Device Performance
    SpO2 Accuracy±3% @ 70-100%
    PR Accuracy±2 bpm

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

    • Sample Size: 12 human adult volunteers were used for each clinical study (there were two studies). This means a total of 24 human adult volunteers were used for the two studies combined.
    • Data Provenance: The studies were described as "Clinical hypoxia test results obtained in human adult volunteers." The document doesn't specify the country of origin, but it implies a prospective clinical study using induced hypoxia.

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

    The document does not specify the number of experts or their qualifications for establishing the ground truth. It only states that the ground truth for arterial oxygen saturation (SaO2) was "determined by co-oximetry."

    4. Adjudication Method for the Test Set

    The document does not provide details on any adjudication method used for the test set.

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

    No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device is a sensor, and the clinical study focuses on its accuracy against a gold standard (co-oximetry) rather than a comparison of human reader performance with and without AI assistance.

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

    Yes, the accuracy tests described are effectively a standalone performance evaluation of the device. The device itself (sensor and its internal algorithms for calculating SpO2 and PR) is directly compared against the ground truth (co-oximetry) measurements. There's no human 'reading' or interpretation of the sensor's output being evaluated in this context, other than potentially reading the numerical display that the device provides.

    7. The Type of Ground Truth Used

    The ground truth used was arterial oxygen saturation (SaO2) as determined by co-oximetry. This is a recognized gold standard for measuring oxygen saturation in blood.

    8. The Sample Size for the Training Set

    The document does not mention the sample size for any training set. Given that this is a sensor (hardware with embedded algorithms) rather than a software-as-a-medical-device (SaMD) based on AI/Machine Learning that typically requires extensive re-training, it's possible that a distinct "training set" as understood in deep learning contexts was not highly relevant or explicitly documented. The development process likely involved calibration and verification, which might use internal datasets not explicitly labeled as "training."

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

    Since a "training set" is not explicitly mentioned, the method for establishing its ground truth is also not provided.

    Ask a Question

    Ask a specific question about this device

    K Number
    K091572
    Date Cleared
    2009-09-22

    (112 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Philips disposable SpO2 sensor M1134A is indicated for use by health care professionals whenever there is a need for acquiring non-invasively the arterial oxygen sturation a support the measurement of oxygen saturation. Intended for monitoring, recording, and alarming of the physiological parameters arterial oxygen saturation (SpO2) and pulse rate of adults, infants, and neonates in a healthcare environment and during transport inside and outside of healthcare environments.

    Device Description

    The modified device uses adhesive-free material (adhesive-free skins) which covers the optical parts of the sensor and which comes into contact with the patient. Such a modified SpO2 sensor can be applied to patients whenever skin sensitivity is a concern. The new disposable SpO2 sensors M1134A are for single use, when continuous non-invasive arterial oxygen saturation and pulse rate monitoring are required. The measurement method is based on the absorption of light, which is sent through human tissue (for example through the index finger). The light is emitted from two sources with different wavelengths and is received by a photodiode. Through interference with the human tissue the two distinct wavelengths will be differently absorbed. Out of this different absorption behavior a so-called Ratio can be calculated. Based on calibration curves, the Ratio can be related to a SpO2 value.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study details for the Philips disposable SpO2 sensor M1134A, based on the provided text:

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

    Acceptance CriteriaReported Device Performance
    SpO2 AccuracyMeets reliability requirements and performance claims (validated according to ISO 9919, similar to predicate M1133A)
    Pulse Rate AccuracyNot influenced by modification, M1133A testing valid for M1134A

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

    • Test Set Sample Size: 12 volunteers (6 male, 6 female).
    • Data Provenance: The study was conducted in a controlled environment as a "desaturation study." The country of origin is not explicitly stated, but the manufacturer is based in Germany, and the submission is to the FDA in the USA. This was a prospective study, as it involved actively collecting new data from volunteers.

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

    The document does not explicitly state the number of experts used or their qualifications for establishing ground truth. The primary ground truth for SpO2 accuracy was established by a CO-Oximeter as a reference, which is a gold standard for blood oxygen measurement.

    4. Adjudication method for the test set

    The document does not describe an adjudication method involving multiple human readers for the test set. The validation appears to rely on a direct comparison between the device's readings and the reference CO-Oximeter.

    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, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device is a sensor for direct physiological measurement, and the study focuses on its accuracy against a reference device, not on diagnostic image interpretation by humans with or without AI assistance.

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

    Yes, the study described is a standalone performance study of the sensor. The device itself (the SpO2 sensor) is an "algorithm only" in the sense that it mechanically measures and calculates SpO2 and pulse rate. The study assesses the accuracy of these measurements against a gold standard (CO-Oximeter) without human interpretation being the primary variable.

    7. The type of ground truth used

    The type of ground truth used was CO-Oximeter measurements. This is a highly accurate, direct measurement of arterial oxygen saturation and serves as the reference standard to which the SpO2 sensor's readings were compared.

    8. The sample size for the training set

    The document does not mention a separate "training set" in the context of machine learning. The device's accuracy is based on its fundamental measurement principle and calibration curves, which would have been developed during the device's design phase. The mentioned "more than 300 blood samples" were part of the validation study (test set) to confirm the accuracy, not for training a model.

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

    As there's no explicitly mentioned "training set" in the context of machine learning, the establishment of "ground truth for the training set" is not applicable in this document. The device's underlying principle relies on light absorption and pre-established calibration curves, which would have been developed using known SpO2 values and corresponding light absorption ratios during the initial design and development of oximetry technology. The presented study focuses on validating the final device's performance.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1