Search Results

This Pulse Oximeter is intended for measuring the functional oxygen saturation (SpO2) and pulse rate (PR). It is intended for spot check and continuous recording of SpO2, PR of adult or pediativ patients in hospitals, clinics, or home. This device is not intended for continuous monitoring.

This AP-10 Pulse Oximeter is wrist-worn. It measures the SPO2 physiological parameter, and the measurement results are displayed and stored. The data can be transferred to a phone or PC via a USB connection or via Bluetooth. The AP-10 Pulse Oximeter measures SPO2 and Pulse Rate simultaneously. The device can store up to 500 hours of SPO2 and Pulse rate data.

The Shenzhen Creative Industry Co., Ltd. Pulse Oximeter, AP-10, underwent a clinical study to establish its accuracy for measuring oxygen saturation (SpO2). The study was conducted in accordance with Annex EE of ISO 80601-2-61:2018 (or 2011, as listed in the provided text).

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

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document explicitly states that the AP-10's reported performance for SpO2 and Pulse Rate accuracy meets the ISO 80601-2-61 standard's requirements, which are the acceptance criteria.

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

The document states that clinical testing was conducted. However, it does not explicitly mention the sample size for the test set or the country of origin. It refers to the "Guideline for evaluating and documenting SpO2 accuracy in human subjects of ISO 80601-2-61:2011." This guideline typically involves healthy volunteers studied under controlled hypoxia conditions. Therefore, the data would be prospective.

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

The provided text does not contain information regarding the number of experts or their qualifications used to establish ground truth for the test set. For pulse oximetry, the "ground truth" for SpO2 is usually established via a co-oximeter measuring arterial blood gas (PaO2), overseen by medical professionals, but this detail is not present in the document.

4. Adjudication Method

The document does not specify an adjudication method. For pulse oximetry studies, adjudication typically refers to how reference SpO2 values are determined from blood samples, which doesn't usually involve multiple human readers in the same way imaging studies might.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed or described. This type of study is typically used for diagnostic imaging devices where human readers interpret results, and the AI's impact on their performance is being evaluated. The AP-10 is a direct measurement device (pulse oximeter), so this type of study is not applicable.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance evaluation was conducted. The "Reported Device Performance" in the table above reflects the algorithm's accuracy in measuring SpO2 and pulse rate as a standalone device. The clinical study mentioned in "Clinical: Clinical testing was conducted per Annex EE Guideline for evaluating and documenting SpO2 accuracy in human subjects of ISO 80601-2-61:2011" specifically evaluates the device's intrinsic accuracy.

7. Type of Ground Truth Used

The type of ground truth used, though not explicitly stated as "co-oximetry," is implied by the reference to Annex EE of ISO 80601-2-61. This standard's Annex EE describes a method where arterial oxygen saturation (SaO2) measured by a co-oximeter from arterial blood samples is considered the ground truth against which the pulse oximeter's SpO2 readings are compared.

8. Sample Size for the Training Set

The document does not provide any information about the sample size for the training set. It refers to non-clinical and clinical testing for the current device's performance validation, but not to machine learning model training data. Given that pulse oximeters primarily rely on established biophysical principles (light absorption at different wavelengths by oxygenated and deoxygenated hemoglobin) rather than complex machine learning models directly trained on vast datasets in the same way an AI diagnostic tool might, the concept of a "training set" for the core physiological measurement might not be directly applicable or detailed in this type of submission.

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

As with the previous point, the document does not provide information on how ground truth for a training set (if one was used for specific algorithm development within the device) was established. The focus of the submission is on the device's adherence to established performance standards for pulse oximetry.

Ask a specific question about this device

This Patient Monitor is a multi-functional instrument designed for monitoring the vital physiological signs of adult and pediatric (but not neonatal) patients. With the functions of real-time recording and displaying parameters, such as ECG, heart rate(HR), non-invasive blood pressure (NIBP), functional oxygen saturation (SpO2), respiration rate (RESP), body temperature (TEMP), end-tidal CO2 concentration (EtCO2), it allows comprehensive analysis of patient's physiological conditions.

This instrument is applicable for use in hospitals and clinical institutions. The operation should be performed by qualified professionals only.

This Patient Monitor is a multi-functional instrument designed for monitoring the vital physiological signs of adult and pediatric (not neonatal) patients. With the functions of real-time recording and displaying parameters, such as ECG, pulse rate (PR), noninvasive blood pressure (NIBP), functional oxygen saturation (SpOz), respiration rate (RESP), body temperature (TEMP), end-tidal CO2 concentration (EtCO2), it allows comprehensive analysis of patient's physiological conditions.

This instrument is applicable for use in hospitals and clinical institutions. The operation should be performed by qualified professionals only.

There are three versions of the K serial Patient Monitor, K10, K12 and K15. The primary difference is physical dimension and display TFT size; all other specifications remain unchanged. All versions have the same indications for use.

This document, a 510(k) summary for the Shenzhen Creative Industry Co., Ltd. Patient Monitor, Models K10, K12, and K15, primarily focuses on demonstrating substantial equivalence to a predicate device (Shenzhen Creative Industry UP-7000 Patient Monitor, K123711) rather than detailing the specific acceptance criteria and study proving performance for a novel AI/software device.

Therefore, much of the requested information regarding AI device performance (e.g., sample sizes for training/test sets, expert adjudication, MRMC studies, standalone performance, ground truth establishment for training) is not applicable or present in this document. This document describes a traditional medical device (patient monitor) and its components, and the "study" referred to is non-clinical and clinical testing to ensure compliance with relevant performance standards for vital sign monitoring.

However, I can extract the information that is applicable based on the provided text, particularly focusing on the performance criteria for the integrated vital sign modules.

Here's an analysis based on the provided text:

Device: Patient Monitor, Models K10, K12, K15

Indications for Use: Monitoring the vital physiological signs of adult and pediatric (but not neonatal) patients, including ECG, heart rate (HR), non-invasive blood pressure (NIBP), functional oxygen saturation (SpO2), respiration rate (RESP), body temperature (TEMP), and end-tidal CO2 concentration (EtCO2). Applicable for use in hospitals and clinical institutions, operation by qualified professionals only.

Study Type: This is a 510(k) submission seeking substantial equivalence to a predicate device. The "studies" involve non-clinical (safety and performance) and clinical (NIBP validation) testing against recognized standards rather than a comparative effectiveness study of a novel AI algorithm's diagnostic performance.

1. Table of acceptance criteria and the reported device performance:

The document lists performance specifications for each physiological parameter module, often directly comparing them to the predicate device. The acceptance criteria are implicitly that the devices meet or are substantially equivalent to the established performance requirements of the predicate device and relevant industry standards.

Note: The document explicitly states for the NIBP and TEMP modules that "The new [module] used in subject devices complies with the same ISO [standard] and design requirement as Predicate device." This implies the acceptance criterion for these components is compliance with the cited ISO standards (e.g., ISO 80601-2-30 for NIBP, ISO 80601-2-56 for TEMP).

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

• Test Set Sample Size:
  • For NIBP (Non-invasive sphygmomanometers) clinical validation (ISO 81060-2), this standard typically requires a minimum of 85 subjects (adults and children combined) for a full validation. While the exact number isn't stated in the provided text, the reference to this specific standard implies adherence to its sample size requirements.
  • For other parameters (SpO2, CO2, ECG, RESP, TEMP), the "performance data" section refers to IEC/ISO standards (e.g., 60601-2-49, 80601-2-61, 80601-2-55, 60601-2-27, 80601-2-56). These standards define particular requirements for the performance of the devices and often involve bench testing, simulations, or phantom studies rather than large-scale human clinical trial "test sets" in the AI sense.
• Data Provenance: Not specified in the provided text (e.g., country of origin). The testing is referred to as "Non-Clinical Study" and "Clinical Study" without detail on whether retrospective or prospective data was used, except for the NIBP clinical validation which would be prospective.

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

• Not Applicable in the AI/Software Sense: This document describes a traditional patient monitor. The "ground truth" for a patient monitor's vital sign measurements is established against recognized reference measurement methods or calibrated instruments (e.g., a known SpO2 reading from a CO-oximeter, a calibrated pressure sensor for NIBP, or a physiological simulator for ECG).
• For NIBP (ISO 81060-2): This standard for clinical validation of automated sphygmomanometers typically requires measurements to be taken by trained observers (not necessarily "experts" in the diagnostic sense, but highly skilled in manual auscultatory measurements) and compared against a reference standard. The number of observers is also specified in the standard (e.g., at least 3 observers taking sequential measurements). Their "qualification" would be their training and demonstrated proficiency in the reference method.

4. Adjudication method for the test set:

• Not Applicable in the AI/Software Sense: There is no "adjudication" of expert interpretations as seen in AI studies, as the device measures physiological parameters directly.
• For NIBP (ISO 81060-2): The standard defines specific statistical methods for comparing the device's measurements to the reference measurements, often involving Bland-Altman analysis and calculating mean difference and standard deviation. There's no "adjudication" in the sense of resolving conflicting human interpretations; rather, it's a statistical comparison to a pre-defined reference.

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 device is a patient monitor, not an AI diagnostic imaging tool or a system that assists human "readers" with interpretation. Therefore, no MRMC study was performed or is relevant to this submission.

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

• Not Applicable in the AI/Software Sense: The described device functions as a standalone vital sign monitor. Its "performance" is inherently "algorithm only" in that its internal processing generates the vital sign values. However, this is not an "AI algorithm" in the context of complex pattern recognition or decision support. The performance is assessed by comparing its output against reference standards, which is a form of standalone evaluation for a monitor.

7. The type of ground truth used:

The ground truth for the performance evaluations of this patient monitor would be derived from:

• Reference Measurements/Calibrated Standards:

  • Physiological Simulators: For ECG, RESP, and potentially SpO2 and NIBP, to generate known, controlled physiological signals.
  • Calibrated Instruments: For SpO2 (e.g., CO-oximeter), CO2 (calibrated gas mixtures), NIBP (auscultatory measurements by trained observers or calibrated pressure transducers), and Temperature (calibrated thermometers).
  • In-vitro/Bench Testing: As implied by adherence to IEC/ISO performance standards, which often dictate specific test setups and reference instruments.

• Clinical Data (for NIBP): As per ISO 81060-2, the ground truth for NIBP accuracy relies on trained human observers taking simultaneous or sequential auscultatory blood pressure measurements (the "reference method").

8. The sample size for the training set:

• Not Applicable: This device is a traditional patient monitor, not an AI/machine learning device that requires a "training set" in the context of deep learning models. Its algorithms are based on established physiological signal processing principles.

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

• Not Applicable: As stated above, there is no "training set" for this type of device. The ground truth for its performance verification (as opposed to AI training) is established using validated, calibrated reference standards and methods as described in point 7.

Ask a specific question about this device

The Handheld Pulse Oximeter is intended for measuring the pulse rate, functional oxygen saturation (SpO2) and temperature (optional). It is intended for spot checking and recording of SpO2, pulse rate and temperature of adult and pediatric patients in clinical institutions and homes. The Handheld Pulse Oximeter is not intended for active continuous monitoring.

This SP-20 Handheld Pulse Oximeter is an integrated product with a modular design. It simultaneously measures physiological parameters by integrated modules and corresponding accessories. The measurement results are displayed, stored and transferred by the central processing unit. The SP-20 Handheld Pulse links with the compatible 510(k) cleared IR Ear thermometer Device (option). Since the SP-20 receives data from the 510(k) cleared IR Ear thermometer and no data is transmitted to the thermometer, it does not affect the operations or accuracy of the linked IR Ear thermometer Device.

Here's an analysis of the acceptance criteria and study information for the Shenzhen Creative Industry Co., Ltd. Handheld Pulse Oximeter, SP-20 based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text focuses on demonstrating substantial equivalence to predicate devices and adherence to various safety and performance standards rather than explicitly stating numerical acceptance criteria for SpO2 and Pulse Rate accuracy with corresponding numerical performance results. However, it does state compliance with the general requirements of the standards.

Based on the information, the primary performance standard for the pulse oximeter function is:

Important Note for SpO2 and Pulse Rate: While ISO 80601-2-61 covers the particular requirements for pulse oximeter equipment, the document does not explicitly state the specific accuracy (e.g., Arms value) or bias results for SpO2 or Pulse Rate as acceptance criteria or reported performance results. It only states general compliance with the standard. Typically, pulse oximeter standards define specific accuracy requirements (e.g., Arms ≤ 3% for SpO2 between 70-100%). It's implied that the device meets these within the standard, but the specific numbers are not provided in this summary.

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

• Sample Size: Twelve (12) subjects.
• Data Provenance: The subjects consisted of volunteers (3 women and 9 men) with no known illnesses and no anemia. They represented a mixture of ethnic backgrounds with skin colors ranging from light to dark, and ages from 22 to 38. A total of 24 samples were obtained per subject.
• Study Type: This appears to be a prospective clinical testing for performance validation. The location of the test is not explicitly stated as a country, but it says "Data was recorded by Bickler-Ye Lab and provided for analysis," which might hint at a US-based lab given Dr. Jeffrey Bickler's affiliation with UCSF.

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

The document does not mention the use of experts to establish ground truth for the clinical testing in the traditional sense of consensus reading for diagnostic imaging. Instead, for pulse oximetry, the "ground truth" for oxygen saturation is typically established through direct arterial blood gas analysis, a recognized clinical standard. However, this document does not explicitly state how ground truth for SpO2 was established in the clinical test. It states "Testing validated the submitted device was effective in determining SPO2."

4. Adjudication Method for the Test Set

Not applicable in the context of this pulse oximeter performance testing. Adjudication methods like "2+1" or "3+1" are typically used in studies where human readers are interpreting images or data and their disagreements need to be resolved. For pulse oximetry, the comparison is usually against a physiological standard (e.g., co-oximetry).

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

No. An MRMC study was not done. The study described is a clinical validation of the device's accuracy in measuring SpO2 and pulse rate, not a comparative effectiveness study involving human readers with and without AI assistance.

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

Yes, the described "Clinical testing" focuses on the device's performance in measuring SpO2. This is a standalone performance test of the device (algorithm/sensor system) without human interpretation in the loop. The device directly provides numerical readings (SpO2, Pulse Rate).

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The document does not explicitly state the method for establishing ground truth for SpO2 in the clinical trial. For pulse oximeters, the accepted gold standard for SpO2 is typically fractional arterial oxygen saturation (SaO2) measured by a co-oximeter from an arterial blood sample. While the document mentions "Testing validated the submitted device was effective in determining SPO2," it doesn't detail the comparison method.

8. The Sample Size for the Training Set

No information about a training set is provided. This device is a pulse oximeter, not an AI/ML-driven diagnostic algorithm that typically requires a separate training set. Its principle of operation is based on optoelectronics and signal processing, which doesn't usually involve a "training phase" in the same way an AI model does.

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

Not applicable, as a training set for an AI/ML algorithm is not relevant to this type of device based on the provided information.

Ask a specific question about this device

The All-in-One Health Monitor PC-303 is a device designed for spot-checking measuring of the patient's physiological parameters, such as Non-Invasive Blood Pressure (NIBP), Oxygen saturation (SpO2), Pulse Rate (PR) and Body Temperature (TEMP);

Additionally, the device is available to communicate with the compatible Blood Glucose Monitoring System and ECG monitor to make the measurement.

This device is applicable for Adult and Pediatic (age>3 years old) use in clinical institutions and has no conditions or factors of contraindication.

The All-in-One Health Monitor, PC-303 is mobile modular designed patient monitor. It monitors the patient's blood oxygen saturation (SpO2) and pulse rate (PR) non-invasively by the photoelectric method. It can also measure non-invasive blood pressure (NIBP, the pressures of systolic, diastolic and mean) by the oscillating method and body temperature (TEMP) by the infrared radiation energy technology.

Additionally, the device is also capable to link and communicate with the compatible Blood Glucose Meter and ECG monitor to make the measurement.

This device system measure the patient's physical parameters with variety modules. It takes digital signals from NIBP, SpO2, Temperature module through COM ports, and receives ECG data, blood glucose data from compatible legally marketed ECG Monitor or BLOOD GLUCOSE MONITORING Device. The software to process the data, then display parameters on the screen and storage some useful information.

This device is applicable for use in clinical institutions and has no conditions or factors of contraindication.

The provided document describes the All-in-One Health Monitor, PC-303, and its substantial equivalence to a predicate device (UP-7000 Patient Monitor, K123711). The acceptance criteria are primarily based on meeting relevant international standards for medical electrical equipment and specific performance characteristics in comparison to the predicate device.

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

The acceptance criteria are not explicitly stated as distinct numerical targets in a single table within the document but are inferred from the comparison with the predicate device and the adherence to recognized international standards. The "reported device performance" is the claim of compliance with these standards and the equivalent performance to the predicate.

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

The document states that "Clinical testing was performed for the NIBP functions and are submitted as part of this submission." However, it does not specify the sample size used for this clinical testing or the data provenance (e.g., country of origin, retrospective/prospective).

For biocompatibility testing, the "In Vitro Cytotoxicity Test" used L929 mouse fibroblast cells, and the "Tests for irritation and skin sensitization" used guinea pigs. These are standard biological test methods, not human clinical sample sizes.

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

The document does not provide information on the number or qualifications of experts used to establish ground truth for any of the performance or clinical studies.

4. Adjudication method for the test set

The document does not describe any adjudication method used for the test set.

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 patient monitor with built-in and external measurement capabilities for physiological parameters (SpO2, NIBP, TEMP, Blood Glucose, ECG). It is not an AI-assisted diagnostic device, and therefore, an MRMC comparative effectiveness study involving human readers improving with AI assistance would not be applicable and was not reported.

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

The device is a medical instrument that provides physiological measurements. Its performance is inherent in its measurement capabilities and adherence to performance standards. The "standalone" performance is essentially its ability to accurately measure the parameters as specified, which is verified through testing against standards and comparison to a predicate device. The document mentions "Performance testing was performed to ensure that all of the device operated within specified parameters independently and with all other functions of the device operating." This indicates standalone performance testing of its direct measurement capabilities.

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

The ground truth for the measurements would typically be established by highly accurate reference instruments or established clinical methods, as dictated by the specific IEC/ISO/ASTM standards (e.g., for NIBP, a reference sphygmomanometer; for SpO2, a co-oximeter with induced hypoxia studies; for temperature, a reference thermometer). The document implies adherence to these standards for validation rather than explicitly stating ground truth derivation methods for each measurement. For NIBP, the reference to "clinical testing" would imply comparison to a clinically accepted gold standard.

8. The sample size for the training set

This device is a physiological monitor, not an AI/machine learning device that typically requires a "training set" in the context of algorithm development. Therefore, the concept of a training set sample size does not apply here.

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

As the device does not employ a machine learning algorithm requiring a "training set," this question is not applicable.

Ask a specific question about this device

The Pulse Oximeters are intended for measuring the pulse rate and functional oxygen saturation (SpO2) through patient's finger, indicating the pulse intensity by a bar-graph display.

These devices are used for spot-checking a patient's SpO2 and pulse rate in a home or clinical environment. They are used by adult and pediatric patients. These devices are recommended for use on the index fingers of 1.0 - 2.2 cm thick.

A blood-oxygen saturation reading indicates the percentage of hemoglobin molecules in the arterial blood which are saturated with oxygen. The reading may be referred to as SaO2. Readings vary from 0 to 100%. Normal readings in a healthy adult, however, range from 94% to 100%. The term SpO2 means the SaO2 measurement determined by pulse oximetry. In its most common (transmissive) application mode, a sensor device is placed on a thin part of the patient's body. The device passes two wavelengths of light through the body part to a photodetector. It measures the changing absorbance at each of the wavelengths, allowing it to determine the absorbances due to the pulsing arterial blood alone, excluding venous blood, skin, bone, muscle and fat. For the purpose of measuring the SpO2 more easily and accurately, our company developed the Fingertip Oximeter. The device can measure SpO2 and body pulse simultaneously.

The PC-66A; PC-66B; PC-66C;PC-60B1; PC-60B5; PC-60D; PC-60D2; PC-60E; PC-60N; POD-1; POD-2; POD-3; PC-68A; PC-68B; PC-68C; POD-1W; POD-60NW-1 Fingertip Oximeter is intended for measuring the pulse rate and functional oxygen saturation (SpO2) through patient's finger, indicating the pulse intensity by a bar-graph display. This device is powered by 2 AAA batteries. This device is applicable for spotchecking of SpO2 and pulse rate in a home and clinical environment. The index finger is the recommended site. It is intended for spot-checking adult and pediatric patients on fingers between 1.0 -2.2 cm thick.

This oximeter has a wireless data transmission function. The user can transmit the SPO2 and pulse rate data to a computer through the wireless communication module.

This document, a 510(k) summary for various Pulse Oximeter models from Shenzhen Creative Industry Co., Ltd., primarily asserts substantial equivalence to predicate devices and focuses on mechanical, electrical, and biocompatibility testing. It does not describe a study to prove the device meets acceptance criteria for its core function (SpO2 and pulse rate measurement) beyond a "Bench Test of SpO2 and Pulse Rate" which references accuracy ranges using a simulator.

Therefore, many of the requested details about a study proving the device meets acceptance criteria are not available in this document. The document explicitly states: "In that the measuring device in the electro-circuit module, cushion rubber, emitter and receiver are the same as predicate devices, we concluded that this will not affect the device performance. No new clinical validation needed." This implies reliance on the predicate device's clinical validation.

Here's an analysis of the provided information based on your requests:

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

Based on the document, the "performance" for SpO2 and Pulse Rate is presented as a target accuracy range tested using a simulator.

Note: The document only provides the tested accuracy range with the simulator, not explicit acceptance criteria from an independent study. The wording "we conducted additional verification to show it complies with the requirement" implies these ranges are the requirements, but they are presented as results from a bench test with a simulator, not from a clinical study on human subjects.

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 available in the provided document for the SpO2 and pulse rate accuracy claims. The document states a "Bench Test of SpO2 and Pulse Rate" was performed using an "SpO2 simulator method (simulator model: Index 2 series)". This is a laboratory test, not a clinical study on a human test set. Therefore, there is no information on human sample size, data provenance, or retrospective/prospective nature.

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

This information is not available. Since the primary claims for SpO2 and pulse rate accuracy were validated using a simulator, there were no human experts involved in establishing ground truth for a clinical test set.

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

This information is not available. As there was no clinical test set involving human subjects to establish ground truth, an adjudication method for such a test set is not applicable.

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 to the device described. This document pertains to a pulse oximeter, which is a standalone measurement device, not an AI-assisted diagnostic tool that would involve human "readers" or interpretation in the way an MRMC study evaluates.

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

Yes, in the context of a pulse oximeter, its performance is inherently standalone. The "Bench Test of SpO2 and Pulse Rate" using a simulator can be considered a standalone performance evaluation of the device's measurement capabilities.

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

For the "Bench Test of SpO2 and Pulse Rate," the ground truth was based on the output of an SpO2 simulator (Index 2 series). This is a synthetic ground truth, not derived from biological sources like expert consensus, pathology, or outcomes data.

8. The sample size for the training set

This information is not available and likely not applicable in the traditional sense of machine learning. The device is a hardware-based measurement instrument, and while it contains embedded software/firmware, the document does not describe it as an AI/ML device that requires a "training set." The performance relies on the physics of pulse oximetry and the calibration of its components.

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

This information is not available and not applicable. As explained above, the device is not described as an AI/ML device that typically uses a training set with established ground truth.

Ask a specific question about this device