Search Results

The Pulse Oximeter is a non-invasive device indicated for use in measuring, displaying, storing and transmitting functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate for adult patients. It is intended for spot- check and/or continuous data collection, and not continuous monitoring. It can be used in sleep labs, long-term care, hospitals and home use.

The Pulse Oximeter is a lightweight, portable health finger ring oximeter for home or healthcare facilities. SpO2 measurement technology is based on the developed photoelectron method and circuit design, and Shenzhen Viatom Technology Co., Ltd. developed calculation software. The SpO2 sensor receives the optical signal from the red light and infrared light through the finger into the oximeter. Two emitting tubes (red light diodes and infrared diodes) are located on the inner right side of the sensor, and they can emit red light and infrared. The receiving end is located on the inner left side of the sensor, and it can receive the red light and infrared through the finger. The MCU receives the pulse signal, gets the frequency signal by counting, processes its digital signal, and finally gets the measured SpO2 value. The PR is calculated on average by the above peak intervals of the PR waveform.

The provided text is a 510(k) summary for a Pulse Oximeter (Models PO2, PO2A, PO2B) and does not contain information about an AI/ML-driven device. Therefore, it is not possible to describe acceptance criteria or a study related to an AI/ML device based on this document.

The document primarily focuses on demonstrating the substantial equivalence of the subject pulse oximeter to a predicate pulse oximeter (K191088 Checkme O2 Pulse Oximeter) by meeting established performance standards for pulse oximeters, such as ISO 80601-2-61.

Here's an analysis based on the information available in the document, demonstrating why it doesn't fit the AI/ML framework you've described:

General Device Performance (Pulse Oximeter):

1. A table of acceptance criteria and the reported device performance:
   The document does not present a formal "acceptance criteria table" in the context of an AI/ML model. Instead, it provides a comparison table of the subject device's specifications and performance metrics against a predicate device.

   Characteristic	Acceptance Criteria (Implicit from Predicate & Standards)	Reported Device Performance (Subject Device)
   SpO2 Accuracy (70-100%)	±2%	1.77% ARMS
   Pulse Rate Accuracy	±2bpm or ±2% (whichever is greater)	±2bpm or ±2% (whichever is greater)
   SpO2 Measurement Accuracy (ARMS)	≤ 2% (from ISO 80601-2-61)	1.77%
   Work Mode	Spot-check and continuous data collection (not continuous monitoring)	Spot-check and continuous data collection (not continuous monitoring)
   Intended Application Site	Finger	Finger

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

   • Test Set Description: The "clinical validation testing of the SpO2 performance" was conducted on "healthy adult volunteers."
   • Sample Size: The exact number of healthy adult volunteers is not specified in the document.
   • Data Provenance: The document states "Measured values are from a controlled lab study in healthy volunteers." It does not specify the country of origin. The study appears to be prospective, as it involved actively testing subjects with the device.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
   This question is not applicable to this device. For a pulse oximeter, "ground truth" for SpO2 and pulse rate is established using a co-oximeter and ECG (or similar reference standard) on induced hypoxia studies, as per ISO 80601-2-61. There are no "experts" in the AI/ML sense establishing ground truth labels for images or other complex data. The "ground truth" clinical values are collected by qualified personnel trained in conducting such studies.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
   This question is not applicable. Adjudication methods like 2+1 or 3+1 are used in studies involving human interpretation (e.g., radiology reads) to resolve discrepancies and establish a consensus ground truth. For a pulse oximeter, the reference measurements from the co-oximeter are the ground truth, and human adjudication is not part of the process.

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 question is not applicable. The device is not an AI-assisted diagnostic tool. No MRMC study was performed or is relevant for this type of device.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
   This question is not applicable in the context of an AI/ML algorithm. The performance of the pulse oximeter itself (which contains an algorithm to calculate SpO2 and PR from optical signals) was evaluated in a standalone manner against reference standards in the clinical study. The device's performance is inherently "standalone" in its measurement function, as it provides direct numerical outputs.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
   For SpO2 accuracy, the ground truth was arterial oxygen saturation measured by a co-oximeter (from blood samples) during induced hypoxia, as per ISO 80601-2-61. For pulse rate, the ground truth would typically be derived from an electrocardiogram (ECG) monitor. This is a physiological reference standard, not expert consensus or pathology.

8. The sample size for the training set:
   This question is not applicable. The document describes a traditional medical device (pulse oximeter) that uses a pre-defined algorithm based on physical principles (absorption of red and infrared light). It does not mention any "training set" for an AI/ML model. The "algorithm" for SpO2 calculation is based on principles of spectroscopy and physiological models, not machine learning from a dataset in the way a deep learning model would be trained.

9. How the ground truth for the training set was established:
   This question is not applicable for the same reasons as #8. There is no training set for an AI/ML model described.

In summary, the provided document details the regulatory clearance for a traditional medical device (pulse oximeter) based on established performance standards, and therefore, the questions tailored for AI/ML device evaluations are generally not relevant.

Ask a specific question about this device

The Fingertip Pulse Oximeter are intended for measuring function of atterial hemoglobin (SpO2) and pulse rate for adults as non-invasive spot checking in professional caring environment. It is designed for fingers between 0.8cm and 2.3cm (0.3 inches to 0.9 inches) and for patients during no-motion condition. The device is prescription only.

The subject device AVITA Pulse Oximeter with Bluetooth is non-invasive spot checking, not provided sterile, multi-use device, which can measure and display user's oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR) through finger during no-motion condition. The subject device is not for lifesustaining, not for implant and does not contain drug or biological products. The device is for prescription use. The subject device consists of sensor, electronic circuits, display and plastic enclosures. It is a battery powered device and is adopted with two color OLED screen to display SpO2 and PR. It is software-driven and does not include alarms.

The provided text is a 510(k) Summary for the AViTA Pulse Oximeter (SP62B). It addresses medical device regulation, but it does not describe acceptance criteria and a study that proves the device meets specific acceptance criteria in the manner requested (e.g., in the context of an AI/ML algorithm's performance).

Instead, the document details the equivalence of the new device to a predicate device based on various non-clinical performance and safety tests, and a clinical validation of SpO2 performance.

Therefore, I cannot fully answer your request based on the provided text because the information specifically about "acceptance criteria and a study that proves the device meets the acceptance criteria" for an AI/ML device's performance, including details like sample size for test sets, data provenance, expert ground truth establishment, adjudication, MRMC studies, or standalone algorithm performance, is not present.

The document mentions "acceptance criteria" generally for biocompatibility tests, electrical safety, and EMC testing, but not for an AI/ML performance study as implied by your detailed questions.

Here's what can be extracted and inferred from the text regarding the device's overall performance validation, with limitations noted:

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

The document states performance specifications rather than explicit acceptance criteria in a table format for each test, but the overall statement is that the device "met the acceptance criteria" for various tests. For SpO2 accuracy, the performance is explicitly stated.

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

• Test set sample size: For the clinical performance testing, it mentions "healthy, adult volunteers." The exact number (sample size) is not specified in the provided text.
• Data provenance: "healthy, adult volunteers." The country of origin is not specified. The study was prospective as it involved clinical validation testing.

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

• This information is not applicable in the context of a pulse oximeter's SpO2 accuracy against a reference measurement. Pulse oximeters are typically validated against arterial blood gas (ABG) measurements (co-oximetry) in a controlled desaturation study, where the ABG is the direct, objective ground truth. Expert readers are not usually involved in establishing ground truth for SpO2 values.
• The document implies the adherence to ISO 80601-2-61 for clinical performance, which outlines the methodology for such studies.

4. Adjudication method for the test set:

• Not applicable/Not specified. For SpO2 accuracy, the "ground truth" is typically the co-oximeter measurement from arterial blood, not a subjective interpretation requiring adjudication.

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. This is not an AI/ML device for diagnostic image interpretation. It is a pulse oximeter measuring physiological parameters.

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

• Not applicable in the AI/ML sense. The device itself is "standalone" in that it directly measures SpO2 and PR; it's not an AI algorithm assisting a human interpreter.

7. The type of ground truth used:

• For SpO2 accuracy, the ground truth is implied to be co-oximetry measurement from arterial blood gas (ABG), as is standard for pulse oximeter validation according to ISO 80601-2-61. The document states "Clinical performance was conducted per ISO 80601-2-61. The clinical validation testing of the SpO2 performance under no motion on healthy, adult volunteers in the range of 70% to 100%."

8. The sample size for the training set:

• Not applicable. This is not an AI/ML device that requires a "training set" in the machine learning sense.

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

• Not applicable. (See point 8)

Ask a specific question about this device

The Pulse Oximeter FS20P is a handheld non-invasive device intended for spot-checking of oxygen saturation of arterial hemoglobin (SpO2) and Pulse Rate of adolescent, child and infant patients in hospitals, hospital-type facilities and homecare. The device is not intended for continuous monitoring, use during motion or use with low perfusion. The device is intended for reuse. The device is wearing on fingertips while using.

The Pulse Oximeter FS20C and FS10C is a handheld non-invasive device intended for spotchecking of oxygen saturation of arterial hemoglobin (SpO2) and Pulse Rate of adult patients in hospitals, hospital-type facilities and homecare. The device is not intended for continuous monitoring, use during motion or use with low perfusion. The device is intended for reuse. The device is wearing on fingertips while using.

The subject device Pulse Oximeter is a battery powered device, which can mainly detect and display the measured oxyhemoglobin saturation (SpO2) and pulse rate (PR) value. Place one fingertip into the photoelectric sensor for diagnosis and the pulse rate and oxygen saturation will appear on the display. The device is normally applied to infants, children, adolescents and adult in hospitals, hospital-type facilities and homecare.

The subject device is composed of following components to achieve the above detection process: power supply module, detector and emitter LED, signal collection and process module (MCU), OLED/LED display screen, user interface and button control circuit.

The document provided is a 510(k) Premarket Notification from the FDA for a Pulse Oximeter. It describes the device, its intended use, and a comparison to a predicate device, including non-clinical and clinical data.

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

1. Acceptance Criteria Table and Reported Device Performance

• IEC 60601-1-2005+CORR.1:2006+CORR.2:2007+A1:2012
• IEC 60601-1-2:2014
• IEC 60601-1-11 Edition 2.0 2015-01
• ISO 80601-2-61: 2017
  (Statement of compliance, not a numerical performance metric, beyond the clinical accuracy which is detailed elsewhere). Electrical safety explicitly stated: "Conformed to IEC60601-1, IEC 60601-1-11". |

2. Sample Size and Data Provenance

• Test Set Sample Size:
  • FS20P: 10 healthy female adult volunteer subjects.
  • FS20C: 13 healthy adult volunteer subjects.
• Data Provenance: The studies involved volunteer subjects, implying prospective data collection. The document does not specify the country of origin of the study data, but the submitting company is based in China, so it is highly likely the studies were conducted there. The subject skin tones (Fitzpatrick 1-6) suggest a diverse population, but this is a characteristic, not a location.

3. Number of Experts and Qualifications for Ground Truth

• The document describes a clinical study for SpO2 accuracy compared to arterial blood CO-Oximetry. This is a direct physiological measurement, implying that no human expert adjudication was used to establish the ground truth for SpO2. The CO-Oximeter itself is the "expert" or gold standard.
• Therefore, the concept of "number of experts" for ground truth establishment, as typically applied to image-based diagnostic AI, is not directly applicable here.

4. Adjudication Method for the Test Set

• None, as the ground truth was established by direct physiological measurement using a CO-Oximeter, which is considered a gold standard for SpO2. No human adjudication process (like 2+1 or 3+1) was necessary or mentioned for the SpO2 values.

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

• No, a MRMC comparative effectiveness study was not done. This type of study is more common for diagnostic imaging AI devices where human readers interpret medical images with and without AI assistance.
• For a pulse oximeter, the device directly measures physiological parameters (SpO2 and PR). The clinical study focused on validating the device's accuracy against a gold standard (arterial blood CO-Oximetry), not on improving human reader performance.

6. Standalone (Algorithm Only) Performance

• Yes, a standalone performance study was done. The clinical studies directly measured the device's (i.e., the pulse oximeter's algorithm/measurement system) SpO2 accuracy (ARMS) against a gold standard (arterial blood CO-Oximetry). The reported ARMS values (1.70% for FS20P and 1.71% for FS20C) are metrics of the device's standalone performance.

7. Type of Ground Truth Used

• The ground truth used was outcomes data / physiological measurement, specifically arterial blood CO-Oximetry. This method provides a direct, highly accurate measurement of arterial oxygen saturation, serving as the gold standard for SpO2.

8. Sample Size for the Training Set

• The document does not specify a separate training set or its sample size. For a traditional medical device like a pulse oximeter, particularly one based on well-established principles of optical measurement, there isn't typically an "AI training set" in the sense of machine learning. The device's calibration and design would be based on engineering principles and potentially internal validation data, but not typically a labeled "training set" like an AI performs. The studies described are for validation/testing the accuracy of the final device.

9. How Ground Truth for the Training Set Was Established

• This question is not applicable as there is no mention of an "AI training set" or a separate training set in the context of this device's submission. The described clinical studies are for performance validation (test set), not for training an algorithm.

Ask a specific question about this device

The pulse oximeter is a reusable device and intended for spot-checking of oxygen saturation and pulse rate for use with the finger of adult patients in healthcare environment. And it is not intended to be used under motion or low perfusion scenarios.

The oximeter consists of probe, electronic circuits, and display and plastic enclosures. And one side of probe is designed to locate light emitting diodes and a light detector (called a photo-detector). Red and Infrared lights are shone through the tissues from one side of the probe to the other. Then parts of the light emitted absorbed by blood and tissues. The light absorbed by the blood varies with the oxygen saturation of haemoglobin. After that, the photo-detector detects the light volume transmitted through the tissues which depends on blood pulse, Hereafter, the microprocessor calculates a value for the oxygen saturation (SpQ2), The subject device is a reusable device, and need to reprocess as suggested in the user manual after each use. And the device is intended to be used on the finger, and powered by 2*1.5V AAA battery. Bluetooth function is available for Alpine20B, Alpine20BA, Alpine20BH, Alpine20BHA, Alpine30B, Alpine30BA, Alpine30BH, Alpine20LB, Alpine20LB, Alpine20LBH, Alpine30LB and Alpine30LBH only.

Here's a breakdown of the acceptance criteria and study details for the Fingertip Pulse Oximeter, based on the provided document:

This document describes a 510(k) premarket notification for a medical device, which means the manufacturer is seeking to demonstrate substantial equivalence to a legally marketed predicate device, rather than proving efficacy from scratch. Therefore, the "acceptance criteria" discussed here are primarily focused on meeting regulatory standards and demonstrating comparable performance to the predicate device, rather than establishing de novo clinical effectiveness.

1. Table of Acceptance Criteria and Reported Device Performance

The core performance claims for this pulse oximeter relate to SpO2 accuracy and Pulse Rate accuracy. The acceptance criteria are implicitly defined by the standard ISO 80601-2-61 and the device's stated accuracy, which is compared directly to the predicate device.

Note on SpO2 Range Difference: The document explicitly states and justifies the difference in SpO2 range. While the predicate measures 0-100%, the subject device measures 35-100%. The justification is that this difference is acceptable as it aligns with the verification per ISO 80601-2-61.

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

• Sample Size (Clinical Test Set): 12 adult healthy volunteers.
• Data Provenance: The document does not explicitly state the country of origin for the clinical study. It describes the study as "Clinical testing conducted per Annex EE Guideline for evaluating and documenting SpO2 ACCURACY in human subjects of ISO 80601-2-61:2017... and the FDA Guidance Document for Pulse Oximeters." This suggests it was a prospective study designed to meet these specific guidelines. The volunteers had varying skin tones (Fitzpatrick I-VI), indicating an effort for demographic representation.

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

This type of device (pulse oximeter) does not typically involve expert readers for ground truth establishment. The ground truth for SpO2 accuracy is based on arterial blood CO-Oximetry, which is considered the gold standard for measuring blood oxygen saturation. This is a direct physiological measurement and does not require subjective expert interpretation in the same way imaging studies might.

4. Adjudication Method for the Test Set

Not applicable. As noted above, the ground truth is established by direct physiological measurement (CO-Oximetry), which does not involve subjective interpretation or a need for adjudication among experts.

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

No, an MRMC comparative effectiveness study was not done. This type of study is primarily relevant for diagnostic imaging AI algorithms where human readers interpret medical images, and the AI is used to assist or replace human interpretation. A pulse oximeter directly measures physiological parameters and does not involve human interpretation of complex medical cases.

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

Yes, the core performance testing of the device for SpO2 and Pulse Rate accuracy is a standalone assessment of the algorithm's ability to measure these parameters against the gold standard (CO-Oximetry). The device operates independently to provide these measurements.

7. The Type of Ground Truth Used

The type of ground truth used was outcomes data / physiological measurement, specifically: arterial blood CO-Oximetry. This is the standard reference method for determining actual arterial oxygen saturation.

8. The Sample Size for the Training Set

The document does not provide information on the training set size. For a medical device like a pulse oximeter, "training" might refer to the development and calibration of the internal algorithms and hardware during the design phase, rather than a distinct "training set" of data in the common machine learning sense used for AI algorithms. The clinical study described served as the validation test set.

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

The document does not describe how a "training set" ground truth was established. The focus of this 510(k) submission is on validating the final device's performance against established standards (ISO 80601-2-61) and comparing it to a predicate device, using clinical data collection and CO-Oximetry as ground truth for that validation. If there were internal iterative development and calibration, the specifics of those processes are not detailed in this public regulatory summary.

Ask a specific question about this device

The Nonin Medical 3250 Finger Pulse Oximeter is a small, portable device indicated for use in measuring and displaying functional oxygen saturation of arterial hemoglobin (%SpO2) and pulse rate of individuals who are well or poorly perfused under no motion conditions for medical use without a prescription. It is intended for spot-checking of individuals 18 years and older with finger thickness between 0.8-2.5 cm (0.3-1.0 inch). It is not intended for the diagnosis or screening of lung disease, for use in treatment decisions, and should only be used for making heathcare decisions under the advice of a healthcare provider.

Model 3250 Pulse Oximeter is a small, lightweight, portable, battery operated, digit pulse oximeter that displays numerical values for functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate and is intended for over-the-counter use.

The device measures the absorption caused by the pulsation of blood in the vascular bed, which are used to determine oxygen saturation and pulse rate. Light emitting diodes (LEDs) are contained within the device along with the photo detector, which is on the opposite side of the probe from the LEDs. The SpO2 and pulse rate are displayed on the LCD display of the device. The LCD also provides a visual indication of the pulse signal, while blinking at the corresponding pulse rate. The display will indicate poor pulse quality that may affect the readings. All associated electronics and the microcontrollers are within the sensor, which is activated by inserting a patient's digit. This simple operation activates the internal circuitry automatically upon application.

The Model 3250 includes a Bluetooth radio to send real time oximeter readings to a host device. The Model 3250 features a Bluetooth LE version 4.0 radio to ease the connectivity setup configuration with options to implement secure connections for the point-to-point data connection. This oximeter uses ISP3, Nonin's core signal processing technology software.

Acceptance Criteria and Device Performance Study for Nonin OTC Pulse Oximeter Model 3250 (K211498)

The Nonin OTC Pulse Oximeter Model 3250 is intended for measuring and displaying functional oxygen saturation of arterial hemoglobin (%SpO2) and pulse rate in individuals under no motion conditions for over-the-counter medical use. The device's performance was evaluated through clinical and non-clinical testing to ensure compliance with relevant standards and demonstrate substantial equivalence to predicate and reference devices.

1. Acceptance Criteria and Reported Device Performance

The primary acceptance criteria for the pulse oximeter's accuracy is based on the ISO 80601-2-61:2017 standard, which specifies an ARMS (Accuracy Root Mean Squared) of ≤ 3.0%. The device's performance was assessed across different SaO2 ranges and skin pigmentations.

The reported device performance consistently falls within the 3.0% ARMS guidance, demonstrating the device meets the accuracy acceptance criteria across various SaO2 ranges and skin pigmentations. The bias values also indicate no clinically significant bias.

2. Sample Sizes and Data Provenance

The clinical performance testing utilized data from two studies:

• Leeb Study:
  • Sample Size (Test Set): 34 participants.
  • Data Provenance: Not explicitly stated, but it is an "independent study." Controlled desaturation study.
• UCSF Study:
  • Sample Size (Test Set): 26 participants.
  • Data Provenance: Conducted at UCSF (University of California, San Francisco). Controlled desaturation study.

Both studies involved "controlled desaturation studies with arterial oxygen saturation (SaO2) plateaus between 70% and 100%," suggesting a prospective clinical study design where participants' oxygen levels were intentionally varied under medical supervision. The text emphasizes "diverse skin pigmentation" in both studies, indicating an effort to include a representative demographic.

3. Number of Experts and Qualifications for Ground Truth

The document does not explicitly state the number or qualifications of experts used to establish the ground truth for the test set. For pulse oximeter accuracy studies using controlled desaturation, the ground truth for arterial oxygen saturation (SaO2) is typically established through co-oximetry measurements of arterial blood samples, which are analyzed by laboratory professionals using specialized equipment. This process does not usually involve subjective expert interpretation in the same way, for example, a radiology image would.

4. Adjudication Method

The document does not describe an adjudication method for the test set. In pulse oximetry accuracy studies, the direct comparison is between the device's SpO2 readings and the established SaO2 ground truth (from co-oximetry). There isn't typically an expert panel review or adjudication process for interpreting the ground truth data itself.

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

There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study being performed for the Nonin Model 3250 or its reference device. This type of study is more common for diagnostic imaging AI systems where human readers interpret medical images. Pulse oximetry device validation focuses on the accuracy of the device's direct measurement against a physiological gold standard.

6. Standalone (Algorithm Only) Performance

The study primarily evaluates the standalone performance of the pulse oximeter device, which integrates the sensor and the algorithm. The text states: "Nonin oximeters utilize the same oximeter technology thus the accuracy of Model 3250 is identical to the results of the reference device, Model 3230" and "The optical path and algorithm for the Model 3250 is equivalent to the Model 9590." This indicates that the performance data presented directly reflects the algorithm's capability as integrated into the device, without a human-in-the-loop component for interpreting the raw signal.

7. Type of Ground Truth Used

The ground truth used for the clinical accuracy studies (Leeb and UCSF studies) was arterial oxygen saturation (SaO2) measured from arterial blood samples (co-oximetry). This is considered the gold standard for determining actual arterial oxygen saturation. The studies are described as "controlled desaturation studies," confirming the use of direct physiological measurement for ground truth.

8. Sample Size for the Training Set

The document does not provide information on the sample size for the training set. The clinical data presented is for validation (test set) of the device's accuracy. For pulse oximeters, the core signal processing technology (ISP3 for Nonin) is likely developed and refined over time using extensive proprietary datasets, but specific "training set" details for a machine learning model are not typically disclosed or relevant in the same way as for AI software devices. The statement "Nonin oximeters utilize the same oximeter technology" and "The optical path and algorithm for the Model 3250 is equivalent to the Model 9590" suggests leveraging existing, established technology rather than a newly trained AI model.

9. How Ground Truth for the Training Set Was Established

As with the training set sample size, the document does not detail how the ground truth for any presumed "training set" for the underlying "ISP3" signal processing technology software or core algorithm was established. Given the nature of pulse oximetry, it's highly probable that any developmental data would similarly rely on arterial oxygen saturation (SaO2) measured from arterial blood samples (co-oximetry), following the established methodology for validating pulse oximeter accuracy.

Ask a specific question about this device

The pulse oximeter is a reusable device and intended for spot-checking of oxygen saturation and pulse rate for use with the finger of adult patients in healthcare environments. And it is not intended to be used under motion or low perfusion scenarios.

The oximeter consists of probe, electronic circuits, and display and plastic enclosures. And one side of probe is designed to locate light emitting diodes and a light detector (called a photo-detector). Red and Infrared lights are shone through the tissues from one side of the probe to the other. Then parts of the light emitted absorbed by blood and tissues. The light absorbed by the blood varies with the oxygen saturation of haemoglobin. After that, the photo-detector detects the light volume transmitted through the tissues which depends on blood pulse, Hereafter, the microprocessor calculates a value for the oxygen saturation (SpO2). The subject device is a reusable device, and need to reprocess as suggested in the user manual after each use. And the device is intended to be used on the finger, and powered by 2*1.5V AAA battery.

The provided document is a 510(k) summary for the Shenzhen Yimi Life Technology Co., Ltd. Pulse Oximeter (various models). It details the device's characteristics and its substantial equivalence to a predicate device. Here's an analysis of the acceptance criteria and the study information as requested:

1. Table of Acceptance Criteria and Reported Device Performance

The document explicitly refers to acceptance criteria for SpO2 accuracy and Pulse Rate accuracy based on the ISO 80601-2-61 standard.

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

• Sample Size: The document does not specify the exact sample size for the clinical test set. It only states that "Clinical testing is conducted per Annex EE Guideline for evaluating and documenting SpO2 ACCURACY in human subjects of ISO 80601-2-61:2011". Annex EE of ISO 80601-2-61 generally recommends a minimum of 10 healthy subjects for SpO2 accuracy testing, though more may be required depending on the specific design of the study and the range of SpO2 values assessed.
• Data Provenance: The document does not explicitly state the country of origin of the data or whether it was retrospective or prospective. Given it's a 510(k) submission for a Chinese manufacturer, the clinical testing was likely conducted in China or a similar jurisdiction following international standards. The nature of SpO2 accuracy testing typically involves prospective studies where subjects are intentionally desaturated under controlled conditions.

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 ground truth in the clinical test set. For pulse oximetry, the ground truth for SpO2 accuracy is typically established by co-oximetry measurements from arterial blood samples, which does not directly involve "experts" in the sense of clinical reviewers for image analysis. The "ground truth" (reference standard) in this context is the quantitative co-oximetry reading.

4. Adjudication Method for the Test Set

Not applicable in the context of pulse oximetry SpO2 accuracy testing. Ground truth is established by objective co-oximetry measurements, not through expert consensus or adjudication.

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

No, an MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic imaging devices where human readers interpret results, and the AI's impact on their performance is evaluated. Pulse oximeters provide a direct numerical output (SpO2 and pulse rate), so MRMC studies are not applicable.

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

Yes, a standalone performance study was done. The entire premise of the SpO2 accuracy testing described (clinical data per ISO 80601-2-61 Annex EE) is to evaluate the device's ability to accurately measure oxygen saturation and pulse rate independently, without human interpretation influencing the measurement. The device's output is compared directly against the reference standard (co-oximetry).

7. Type of Ground Truth Used

The ground truth used for SpO2 accuracy testing is co-oximetry measurements from arterial blood samples. This is the gold standard for determining actual arterial oxygen saturation. For pulse rate, the ground truth would typically be from an ECG monitor or a reference pulse rate measurement device.

8. Sample Size for the Training Set

The document does not provide information about a "training set" or its sample size. Pulse oximeters traditionally rely on established physiological principles and algorithms (e.g., Beer-Lambert law and pulsatile blood flow), rather than machine learning models that require extensive training data in the same way an AI image analysis algorithm would. Therefore, a distinct "training set" as understood in AI/ML development is not typically applicable for this type of device.

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

As no training set is described, this question is not applicable. The device's underlying principles are physics-based, and its performance is validated against physiological standards with direct measurements.

Ask a specific question about this device

Ask a specific question about this device

WS20A is a pulse oximeter indicated for use in measuring, displaying, storing and transmitting functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate for patients(≥10 years old, ≥30kg). It is designed for finger circumference more than 33mm. It is intended for spot-check, continuous data collection, recording and transmitting, not continuous monitoring. It can be used in sleep labs, long-term care, hospitals and home.

Pulse Oximeter WS20A is an internally powered pulse oximeter. The main functions of the devices include hemoglobin oxygen saturation (SpO2), pulse rate (PR) measurements and Pulse amplitude index (PAI), data storage and transmission. Place one fingertip into the sensor and the oxygen saturation (SpO2), pulse rate (PR) measurements and pulse amplitude index (PAI) will appear on the display. The device is intended to be applied to adult and pediatric patients in sleep labs, long-term care, hospital and home care environment. The subject device is composed of the following components to achieve the above detection process: power supply module, detector and emitter, signal collection and process module (MCU), TFT display screen and Bluetooth module.

The provided text describes the 510(k) summary for the Hunan Accurate Bio-Medical Technology Co., Ltd.'s Pulse Oximeter (WS20A). While it details the device, its intended use, and comparison to a predicate device, it does not contain a specific table of acceptance criteria with reported device performance in the format of typical medical device performance claims (e.g., sensitivity, specificity, accuracy for an AI/diagnostic device).

Instead, the performance criteria for this pulse oximeter are related to its accuracy in measuring SpO2 and Pulse Rate against a reference standard (CO-Oximetry). The acceptance criteria for pulse oximeters are typically defined by recognized standards such as ISO 80601-2-61, which specifies the accuracy requirements (e.g., ARMS value).

Based on the provided text, here's an attempt to extract the relevant information and present it as requested.

Overview of Device Performance and Study

The Pulse Oximeter (WS20A) underwent clinical studies to verify its accuracy in measuring functional oxygen saturation of arterial hemoglobin (SpO2) against arterial blood CO-Oximetry, in accordance with ISO 80601-2-61:2017 and FDA guidance for Pulse Oximeters - Premarket Notification Submissions.

1. Table of Acceptance Criteria and Reported Device Performance

For pulse oximeters, the key performance metric for SpO2 accuracy is typically the Accuracy Root Mean Square (ARMS) value when compared to a reference method (CO-Oximetry). The acceptance criterion is generally that the ARMS value should be within a specified limit, commonly ± 3% for 70-100% SpO2 range as per ISO 80601-2-61.

• All subjects: 1.81%
• Female subjects: 1.80%
• Male subjects: 1.83%
• Light-skinned: 1.78%
• Dark-skinned: 1.91%

Pediatric Patients:

• 10 female subjects: 1.80%
• Light-skinned: 1.81%
• Dark-skinned: 1.74% |
  | PR Accuracy (bpm) | ± 3bpm (as per predicate device spec) | Not explicitly reported from clinical study for WS20A. The 510(k) submission document for WS20A lists its PR accuracy as ± 3 bpm, which aligns with its own stated specifications and is compared to a similar specification for the predicate. |

Note: The acceptance criteria for ARMS are not explicitly stated as a number in the provided text but are inferred from common regulatory expectations for pulse oximeters based on the ISO standard cited.

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

• Adult Patients: 13 healthy adult subjects. 315 data sets (SpO2 vs SaO2) were obtained.
• Pediatric Patients: 10 healthy female subjects. 243 data sets (SpO2 vs SaO2) were obtained. (Note: The description states "healthy female subjects, aged 22-30" for 'pediatric patients' which seems to be a typo given the 'pediatric' labeling and the age range overlaps with 'adult'. Assuming this refers to subjects representing a pediatric patient population as defined by the study design, or a mislabeling of the subject group based on physical characteristics matching the pediatric profile for device testing.)
• Data Provenance: The document does not specify the country of origin of the data. The studies were described as "clinical studies" and appear to be prospective in nature, as they involved actively obtaining data sets from healthy subjects under stationary (non-motion) conditions through controlled desaturation.

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

The ground truth for pulse oximetry accuracy studies is established through arterial blood CO-Oximetry, which is a direct invasive measurement of arterial oxygen saturation (SaO2). This is a gold standard laboratory method, not typically established by physician experts in the same way as image interpretation. The text does not mention the use of experts for ground truth establishment; rather, it relies on the direct physiological measurement.

4. Adjudication Method for the Test Set

Not applicable. Ground truth for oxygen saturation in these studies is derived from direct physiological measurement (CO-Oximetry) rather than expert consensus requiring adjudication.

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 pulse oximeter for direct physiological measurement, not an AI-assisted diagnostic imaging device requiring human reader interpretation for a comparative effectiveness study.

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

Yes, the performance presented (ARMS values) represents the standalone accuracy of the pulse oximeter device algorithm in measuring SpO2 against the CO-Oximetry reference. While a human uses the device, the accuracy is derived from the device's measurement capabilities.

7. The Type of Ground Truth Used

The ground truth used was arterial blood CO-Oximetry (SaO2), which is a gold standard for measuring oxygen saturation in the blood. This is a direct physiological measurement, not expert consensus or pathology.

8. The Sample Size for the Training Set

The document describes clinical studies conducted to verify the accuracy of the proposed device. It does not explicitly mention a "training set" for an algorithm in the sense of machine learning. The data described (from 13 adult and 10 "pediatric" subjects) appears to be the test/validation set used to demonstrate the device's accuracy. For traditional medical devices like pulse oximeters, the core measurement principles are physics-based, not reliant on machine learning models that require distinct training sets. Any internal calibration or algorithm development would typically occur during the R&D phase, prior to these described validation studies, and the size of data used for such internal development is not generally disclosed in 510(k) summaries unless it's a novel AI/ML device.

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

Not applicable, as a distinct "training set" in the context of an AI/ML device is not described for this traditional pulse oximeter. If there were internal algorithm development or calibration, the ground truth would likely have been established using similar reference methods (CO-Oximetry) in controlled lab settings.

Ask a specific question about this device

The pulse oximeter is a reusable device and intended for spot-checking of oxygen saturation and pulse rate for use with the finger of adult patients in home and healthcare environments. And it is not intended to be used under motion or low perfusion scenarios.

The Pulse Oximeter is a battery powered device in measuring and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR). The Pulse Oximeter works by applying a sensor to a pulsating arteriolar vascular bed. The sensor contains a dual light source and photo detector. The one wavelength of light source is 660 m, which is red light; the other is 905 nm, which is Infrared light. Skin, bone, tissue, and venous vessels normally absorb a constant amount of light over time. The photodetector in finger sensor collects and converts the light into electronic signal which is proportional to the light intensity. The arteriolar bed normally pulsates and absorbs variable amounts of light during systole and diastole, as blood volume increases. The ratio of light absorbed at systole and diastole is translated into an oxygen saturation measurement. This measurement is referred to as SpO2. The device mainly composed of PCB board, On/Off button, mode button, OLED&LED screen, battery compartment, Bluetooth® module and plastic shell. There are five models AOJ-70A, AOJ-70C, AOJ-70E. Only AOJ-70E. Only AOJ-70D have wireless connection function via Bluetooth®. The device is a spot-check pulse oximeter and does not intended for life-supporting or life-sustaining.

The provided text is a 510(k) summary for a Pulse Oximeter (AOJ-70A-E). It describes the device, its intended use, and comparative testing to show substantial equivalence to a predicate device. However, it does not provide a table of acceptance criteria with reported device performance or information regarding a typical "AI/algorithm" study (e.g., sample sizes for training/test sets, expert adjudication, MRMC studies, types of ground truth, etc.). This document primarily focuses on regulatory compliance for a medical device (pulse oximeter), not an AI/ML-based diagnostic or assistive technology.

Therefore, I cannot fulfill the request as the necessary information (acceptance criteria table, detailed study design for an AI/ML model, expert data, ground truth establishment for AI/ML) is not present in the provided text. The text only mentions "software verification and validation testing" and "clinical data is referenced to K221039" for SpO2 accuracy, which refers to a standard medical device clinical trial for a pulse oximeter, not an AI/ML performance study.

The closest information found is the clinical study for SpO2 accuracy performance of the pulse oximeter itself, not an AI/ML component. Here's what is available regarding that:

Study on SpO2 Accuracy Performance (Not an AI/ML study):

• Study Name/Reference: Referenced to K221039.
• Location: Sir Run Run Shaw Hospital, Zhejiang University School of Medicine.
• Methodology: Conducted in accordance with ISO 14155-1, ISO 80601-2-61:2017, and FDA Guidance Document for Pulse Oximeters. Evaluated SpO2 accuracy performance during stationary (non-motion) conditions over a wide range of arterial blood oxygen saturation levels compared to arterial blood CO-Oximetry (which served as ground truth).
• Sample Size: 11 healthy adult volunteer subjects (ages 21-47yr, with skin tones varying from Fitzpatrick 2-6) were included.
• Ground Truth: Arterial blood CO-Oximetry.
• Reported Performance: The SpO2 accuracy performance results showed that the subject device had an ARMS (Accuracy Root Mean Square)

Ask a specific question about this device

The Pulse Oximeter is a handheld non-invasive device intended for spot-checking of oxygen saturation of arterial hemoglobin (SpO2) and Pulse Rate of adult, adolescent child and infant patients in hospitals, hospital-type facilities and homecare. The device can be used by the people whose finger thickness is between 8mm and 22mm(0.3 inches to 0.9 inches).

The proposed device, Pulse Oximeter, is a battery powered device, which can mainly detect and display the measured oxyhemoglobin saturation (SpO2) and pulse rate (PR) value. The MD300C228 is adopted LCD screen to display to display SpO2, Pulse Rate value (PR), Perfusion Index (PI), pulse bar, brightness level, battery indicator, signal indicator and waveform, it has 7 display modes, the brightness level can be adjusted 1-5 level. The measured data can be transmitted to APP through Bluetooth. The device is normally applied to adult, adolescent child and infant patients in hospitals, hospital-type facilities and homecare.

The subject device is composed of following components to achieve the above detection process: power supply module, detector and emitter LED, signal collection and process module (MCU), LCD display screen, user interface and button control circuit.

Principle of the oximeter is as follows: The pulse oximeter works by applying a sensor to a fingertip. The sensor contains a dual light source and photo detector. The one wavelength of light source is 660mm, which is red light; the other is 905nm, which is infrared-red light. Skin, bone, tissue and venous vessels normally absorb a constant amount of light over time. The photo detector in finger sensor collects and converts the light into electronic signal which is proportional to the light intensity. The arteriolar bed normally pulsates and absorbs variable amounts of light during systole and diastole, as blood volume increases and decreases. The ratio of light absorbed at systole and diastole is translated into an oxygen saturation measurement. This measurement is referred to as SpO2.

The enclosure of the subject device is made of ABS and the fingertip cushion is made of Silicone Gel.

The subject device is not for life-supporting or life-sustaining, not for implant.

The device is not sterile, and the transducers are reusable and do not need sterilization and re-sterilization.

The device is for prescription.

The device does not contain drug or biological products.

The provided text describes the acceptance criteria and a clinical study conducted for the Pulse Oximeter MD300C228. This device is a pulse oximeter, not an AI/ML device, so certain requested details such as number of experts for ground truth, adjudication methods, MRMC studies, and training set information are not applicable in this context. However, I will extract and present the relevant information provided for this medical device.

Acceptance Criteria and Device Performance:

The primary performance metric mentioned is SpO2 accuracy.

Study Details:

1. Sample Size and Data Provenance:

   • Sample Size: 11 healthy adult volunteer subjects (ages 20-42yr, with light to dark pigmentation, including male and female).
   • Data Provenance: The document does not explicitly state the country of origin for the clinical study, but the manufacturer is based in Beijing, China. The study appears to be prospective, as it involved inducing hypoxia in volunteers to collect data.

2. Number of Experts and Qualifications for Ground Truth:

   • This criterion is not applicable as the "ground truth" for SpO2 accuracy was established through direct measurement using a reference co-oximeter, not through expert consensus or interpretation of images.

3. Adjudication Method:

   • Not applicable, as the ground truth was based on direct co-oximeter measurements, not subjective evaluations requiring adjudication.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • Not applicable. This is a study to validate the accuracy of a standalone pulse oximeter device, not an AI-assisted diagnostic tool for human readers.

5. Standalone Performance:

   • Yes, a standalone performance study was conducted. The clinical study aimed to evaluate the SpO2 accuracy performance of the pulse oximeter during stationary (non-motion) conditions over a wide range of arterial blood oxygen saturation levels as compared to arterial blood co-oximeter. The reported Arms of 1.8% is a measure of the device's standalone accuracy.

6. Type of Ground Truth Used:

   • Physiological Measurement/Reference Device: The ground truth for SpO2 accuracy was established by analyzing arterial blood samples with a reference co-oximeter, providing functional SaO2.

7. Sample Size for Training Set:

   • Not applicable. This is a hardware pulse oximeter device, not an AI/ML algorithm that requires a training set. The device's performance is based on its optical and signal processing design.

8. How Ground Truth for Training Set was Established:

   • Not applicable as there is no training set for this type of device.

Ask a specific question about this device