Search Results

The Portable Oxygen Concentrator, model: Spirit-3, is intended to provide supplemental oxygen in a home, institutional, or travel environment. And the device is used with adult only, not used with pediatrics, infant, or neonate patients, etc.

Portable Oxygen Concentrator, model: Spirit-3, is a portable oxygen generator that is intended to release oxygen for respiratory therapy by means of physical means (a molecular sieve). It supplies a pulsed high concentration of oxygen and is used with a nasal cannula to deliver oxygen from the concentrator to the patient. The Portable Oxygen Concentrator is small, portable and may be used in home, institutional, or travel environment. Portable Oxygen Concentrator, model: Spirit-3, is capable of continuous use in a home, institutional, or travel environment. Power options include 100 – 240 V (50/ 60Hz) AC power supply, DC power supply and rechargeable lithium-ion battery. The portable oxygen concentrator consists of two parts: an oxygen concentrator and accessories.

The FDA 510(k) clearance letter and supporting documentation for the Portable Oxygen Concentrator (Spirit-3) do not describe a study involving an AI/ML component or human readers. Therefore, there is no information available regarding acceptance criteria related to AI/ML performance, sample sizes for test or training sets, expert qualifications, adjudication methods, multi-reader multi-case studies, or standalone algorithm performance.

The provided document focuses on demonstrating the substantial equivalence of the Spirit-3 Portable Oxygen Concentrator to predicate devices through technical specifications, non-clinical performance testing (bench testing), and compliance with various international standards. The "performance" being discussed in the document refers to the physical and functional performance of the oxygen concentrator itself (e.g., oxygen concentration, flow control, electrical safety, biocompatibility), not the performance of an AI/ML algorithm in an image or data interpretation task.

Therefore, many of the requested categories are "Not Applicable" (N/A) in the context of this specific regulatory submission.

However, I can extract the acceptance criteria and reported device performance for the Spirit-3 Portable Oxygen Concentrator based on the non-clinical tests described.

Here's the information derived from the provided text, adapted to the requested format where applicable:

1. Table of Acceptance Criteria and Reported Device Performance

Study Proving Device Meets Acceptance Criteria

The study conducted to prove the Spirit-3 Portable Oxygen Concentrator meets its acceptance criteria was a series of non-clinical bench tests and evaluations demonstrating compliance with recognized consensus standards and comparison to a legally marketed predicate device.

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

• Sample Size for Test Set: Not applicable in the context of an AI/ML algorithm being evaluated. For the performance testing of the physical device, it implicitly refers to the specific unit(s) of the Spirit-3 device undergoing testing. The document does not specify the number of devices tested but implies standard product testing.
• Data Provenance: The tests were conducted internally or by accredited labs as part of the manufacturing and submission process for Jiangsu Yuyue Medical Equipment & Supply Co., LTD. (China). This is prospective testing of the manufactured device.

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

• Not Applicable. This device is a physical oxygen concentrator, not an AI/ML diagnostic or interpretative device that requires expert ground truth for output validation.

4. Adjudication method for the test set:

• Not Applicable. As no expert interpretation was required. Device performance was objectively measured against predefined standard requirements.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

• No. This type of study is relevant for AI/ML systems that assist human readers in tasks like image interpretation. The Spirit-3 is a portable oxygen concentrator and does not involve human reading or AI assistance in that capacity.

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

• Not Applicable. The device does not involve a standalone algorithm for diagnostic or interpretative purposes. "Standalone" performance in this context refers to the device's inherent mechanical, electrical, and oxygen delivery performance.

7. The type of ground truth used:

• The "ground truth" for the performance of the portable oxygen concentrator is defined by the international consensus standards mentioned (e.g., ISO 80601-2-69, ISO 80601-2-67, IEC 60601-1, ISO 10993 series) and the specifications of the predicate devices. These standards provide benchmarks and methodologies for evaluating physical and electrical safety, essential performance, and biocompatibility.

8. The sample size for the training set:

• Not Applicable. This device does not use an AI/ML training set.

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

• Not Applicable. No AI/ML training set was employed for this device.

Ask a specific question about this device

The Infrared Ear Thermometer is indicated for intermittent measurement of human body temperature from the ear canal. The device can be used by people of all ages except preterm babies or babies who are small for gestational age. The thermometer is intended for use in professional settings and the home environment. It is not for emergency clinical conditions.

YUWELL® Infrared Ear Thermometer is designed to measure human body temperature. This hand-held, no-contact device is battery-powered and utilizes infrared energy emitted in the subject's tympanic membrane to determine human body temperature. The thermometer provides temperature readings in just 2 seconds. It is suitable for individuals of all ages except preterm babies or babies who are small for gestational age. The Infrared Ear Thermometer YHT107 can transmit the temperature readings via Bluetooth, whereas the YHT100 does not have data transmission capability.

Here's a detailed breakdown of the acceptance criteria and study information for the YUWELL® Infrared Ear Thermometer, extracted from the provided FDA 510(k) clearance letter:

YUWELL® Infrared Ear Thermometer (YHT100; YHT107) Acceptance Criteria and Study Details

The YUWELL® Infrared Ear Thermometer (YHT100; YHT107) is indicated for intermittent measurement of human body temperature from the ear canal in professional and home environments, for people of all ages except preterm babies or babies who are small for gestational age.

1. Table of Acceptance Criteria and Reported Device Performance

The core performance acceptance criteria are related to temperature accuracy, as specified by the standards ISO 80601-2-56 and ASTM E1965.

Ask a specific question about this device

This oxygen concentrator is intended for using as an oxygen supplement device in the professional healthcare facility and home healthcare environment. It provides high concentration of oxygen to persons requiring oxygen therapy. This device is to be used as an oxygen supplement and is NOT considered life-supporting or life-sustaining.

The Yuyue Oxygen Concentrator models 8F-3A/8F-5A is a portable concentrator which could utilize a molecular sieve and pressure swing adsorption to produce the oxygen. The device could separate nitrogen by absorbing through the molecular sieve when the room air enters the device, and allows the enriched oxygen to be collected. The subject device is intended use for adult population.

The subject device contains primary electrical components including main unit, compressor, fan, flowmeter and circuit breaker, the software is moderate level according to FDA software guideline.

This submission is for an Oxygen Concentrator, models 8F-3A and 8F-5A. The provided document does not contain information related to a study that proves the device meets acceptance criteria in the context of AI/ML performance, human-in-the-loop studies, or expert ground truth adjudication.

Instead, the document focuses on demonstrating substantial equivalence to a predicate device (L4 Oxygen Concentrator (EverFlo), K061261) through non-clinical performance data for regulatory clearance. This involves comparing technical specifications and performance against recognized standards, rather than evaluating AI performance with acceptance criteria typically found in machine learning contexts.

Therefore, many of the requested categories for acceptance criteria and study details cannot be filled from the provided text.

Here's an analysis based on the available information:

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

The document provides a comparison table for substantial equivalence, which includes various technical characteristics and a comparison to the predicate device. These characteristics serve as "acceptance criteria" for showing equivalence to the predicate, rather than explicit performance metrics against a defined threshold specific to a new AI/ML device.

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

Not applicable. The provided document details non-clinical laboratory testing and compliance with various standards, not performance results from a test set of patient data.

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

Not applicable. Ground truth establishment by experts is not relevant to this type of device and submission, which focuses on hardware performance and safety standards.

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

Not applicable. Adjudication methods are not relevant to this type of device and submission.

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 an oxygen concentrator, not an AI/ML-driven diagnostic or interpretative tool.

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

Not applicable. This is a medical device, not an algorithm.

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

Not applicable. Ground truth for AI/ML performance is not relevant here. The "ground truth" for this device's performance is its ability to meet the specified technical parameters (e.g., oxygen concentration, flow rate) and safety standards through physical testing and engineering measurements.

8. The sample size for the training set

Not applicable. This is not an AI/ML device; therefore, no training set is mentioned.

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

Not applicable. This is not an AI/ML device.

Ask a specific question about this device

This product is intended to measure the blood pressure and pulse rate of adult more than 12 years old and with wrist circumference ranging from 13.5 cm at household or medical center (not suitable for neonate, pregnancy or pre-eclampsia.)

The YUWELL® Blood Pressure Monitor (Model: YE8800AR, YE8800CR) is a rechargeable lithium battery-powered, automatic, noninvasive, wrist-worn blood pressure measuring system intended for over-the-counter (OTC) use. YE8800AR, YE8800CR is designed for wrist circumference ranging from 13.5 cm to 19.5 cm. The systolic and diastolic blood pressures are measured using the oscillometric method, where the cuff is inflated with an air pump and deflates via an exhaust valve. During inflation, the cuff pressure is monitored, and pulse waveform data is extracted. The extracted pulse waveform data is then further analyzed by software which determines pulse rate, as well as systolic and diastolic blood pressure.

The acceptance criteria for the YUWELL® Electronic Blood Pressure Monitor (Model: YE8800AR, YE8800CR) are primarily based on performance standards for blood pressure monitors. The study described is a clinical accuracy test.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The Study Proving Acceptance Criteria:

A clinical accuracy test was conducted on the Yuwell YE8800AR model.

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

• Sample Size: 85 participants.
• Data Provenance: The document does not explicitly state the country of origin. It describes participants as the "general population." The study is described as a "clinical accuracy test," suggesting a prospective collection of data for this validation.

3. Number of Experts and Qualifications for Ground Truth:

The document mentions "reference BP" and "two observers" in relation to the ANSI/AAMI/ISO 81060-2:2018 protocol. This standard typically requires measurements by trained observers or reference devices to establish ground truth.

• Number of Experts/Observers: Two observers are explicitly mentioned in the context of Criterion 2 of the ANSI/AAMI/ISO 81060-2:2018 protocol.
• Qualifications of Experts: Not explicitly stated in the provided text, but adherence to the ANSI/AAMI/ISO 81060-2:2018 protocol implies that the observers would be appropriately trained personnel, potentially medical professionals or technicians, who follow a standardized procedure for manual blood pressure measurement to establish the reference values.

4. Adjudication Method for the Test Set:

The document does not explicitly describe an adjudication method for the test set, such as 2+1 or 3+1. The ANSI/AAMI/ISO 81060-2 standard relies on comparisons between the automated device and simultaneous auscultatory measurements performed by trained observers. Discrepancies between observers might be handled by averaging or requiring re-measurements per the standard's guidelines, but a specific "adjudication" (like a third reader resolving disagreement) is not detailed here.

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

No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not done. This device is a standalone electronic blood pressure monitor, not an AI-assisted diagnostic tool that would typically involve human readers.

6. Standalone (Algorithm Only) Performance:

Yes, the described clinical accuracy test is a standalone performance test of the device (algorithm only), without a human-in-the-loop component for the measurement process itself. The "human-in-the-loop" aspect would primarily be the human observers establishing the reference blood pressure for comparison.

7. Type of Ground Truth Used:

The ground truth was established by reference blood pressure measurements, likely obtained through a standardized method such as auscultation (manual measurement with a stethoscope and sphygmomanometer) performed by trained observers, as dictated by the ANSI/AAMI/ISO 81060-2:2018 validation protocol.

8. Sample Size for the Training Set:

The document does not provide information on the sample size used for the training set. The clinical study described is for validation/testing, not for training the device's measurement algorithm. Blood pressure monitors typically rely on established oscillometric principles rather than machine learning models that require explicit "training sets" in the same way as AI diagnostic devices.

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

Not applicable, as a training set in the context of machine learning is not mentioned or implied for this type of device. The device operates based on physical principles of oscillometry. The inherent algorithm development would likely have been based on extensive physiological and engineering data, but not typically a labeled "training set" with ground truth in the AI sense.

Ask a specific question about this device

The YUWELL® Finger Pulse Oximeter is a non-invasive, non-sterile, spot checking device which can measure and display SpO2 and pulse rate through finger. It is intended for adults and children (weight >30 kg) and is expected for home and hospital inspection. The device is not for continuous monitoring,use during motion or for patients with low perfusion.

The YUWELL® Finger Pulse Oximeter is a non-invasive, non-sterile, spot checking device which can measure and display SpO2 and pulse rate through finger. It is intended for adults and children (weight >30 kg) and is expected for home and hospital inspection. The device is not for continuous monitoring, use during motion or for patients with low perfusion. The YUWELL® Finger Pulse Oximeter features in small volume, low power consumption, convenient operation and portable. It is only necessary for patient to put one of his fingers into a fingertip photoelectric sensor for measurement, and then the screen will display the measured value of Pulse Oxygen Saturation (SpO2) and pulse rate(PR) . The device consists of electronic circuits, plastic housing. OLED/LED display(differentiated by models) and button (YX301,YX306 equipped, YX102,YX103 not equipped) which powered by two alkaline AAA batteries. The device does not include alarms.

The provided text is a 510(k) summary for the YUWELL® Finger Pulse Oximeter. Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided document:

Acceptance Criteria and Reported Device Performance

The document primarily focuses on demonstrating substantial equivalence to a predicate device (Beijing Choice Electronic Technology Co., Ltd. Fingertip Pulse Oximeter, K101577). The key performance acceptance criteria can be inferred from the comparison table and the clinical study results.

Table of Acceptance Criteria and Reported Device Performance (Inferred from comparison and study results):

Ask a specific question about this device

The YUWELL® Infrared ear thermometer is a non-sterile, reusable clinical thermometer. The device is to display the body temperature in the ear cavity by thermal radiation for people of all ages except preterm babies and newborns (1-29 days old).

The YUWELL® Infrared ear thermometer is designed for measuring the body's temperature, is a hand-held non-contact infrared thermometer, battery powered, using the infrared energy emitted in the subject's tympanic membrane that converts a user's body temperature.

The provided document describes the safety and effectiveness of the YUWELL Infrared Ear Thermometer (Models YHT101, YHT200) based on comparisons to a predicate device (Braun Thermoscan® PRO 6000 Ear Thermometer) and compliance with various standards.

Here's an analysis of the acceptance criteria and study information, based on the provided text:

1. Table of Acceptance Criteria and the Reported Device Performance

The document does not present a formal table of "acceptance criteria" for the device, but rather compares the subject device's specifications and performance to a predicate device and states compliance with recognized standards. The "Performance" row in the "Substantial Equivalence" table (page 4) indicates the key performance standards met.

Here's a table based on the key performance and accuracy criteria mentioned:

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

The document mentions "Clinical accuracy test requirements established in the standard ASTM E1965 (Clinical part only) and ISO 80601-2-56 (Clinical accuracy validation only)". However, it does not provide details on the specific sample size used for these clinical accuracy tests, nor does it specify the country of origin of the data or whether the study was retrospective or prospective.

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

The document states that "Clinical accuracy test requirements established in the standard ASTM E1965 (Clinical part only) and ISO 80601-2-56 (Clinical accuracy validation only)" were met. For clinical thermometers, ground truth is typically established by comparing the device's readings against a highly accurate reference thermometer (e.g., rectal thermometry in controlled environments or other gold standard methods) in actual patients.

However, the document does not specify the number of experts used or their qualifications.

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

The document does not provide any information regarding an adjudication method for establishing ground truth or evaluating 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

The device under review is an infrared ear thermometer, which is a standalone measurement device, not an AI-assisted diagnostic tool that involves human "readers." Therefore, a multi-reader multi-case (MRMC) comparative effectiveness study focusing on human reader improvement with AI assistance is not applicable and was not performed or mentioned.

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

Yes, the primary performance evaluation described is for the standalone device (algorithm only, without human-in-the-loop performance beyond operating the device). The "Performance test according to ASTM E 1965 and ISO80601-2-56" and "Clinical accuracy test" directly assess the device's ability to accurately measure temperature on its own.

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

For the clinical accuracy validation of a thermometer, the ground truth is typically established by comparison to a highly accurate reference method (e.g., a calibrated reference thermometer measuring core body temperature, often rectal or arterial temperature, in a controlled setting) as defined by the standards like ASTM E1965 and ISO 80601-2-56. The document mentions meeting these standards for clinical accuracy.

8. The sample size for the training set

The document does not provide information regarding a separate "training set" for the device. Clinical thermometers are calibrated and validated against standards; they don't typically undergo machine learning training in the same way an AI diagnostic device would.

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

As there's no mention of a traditional machine learning "training set" in the context of this infrared ear thermometer, this question is not applicable. The device's internal algorithm is likely developed based on physics principles of infrared radiation and calibrated against known temperature sources, rather than being "trained" on a dataset with ground truth in the AI sense.

Ask a specific question about this device

The YUWELL® Infrared thermometer is a nonsterile, reusable clinical thermometer intended for measuring the human body temperature in non-contact mode on the center of the forehead as the measurement site on people of all ages except preterm babies.

The YUWELL® infrared thermometer is designed for measuring the body's frontal temperature, is a handheld non-contact infrared thermometer, battery powered, using the infrared energy emitted in the subject's forehead area within 0-5cm that converts a user's forehead temperature. The measurement reference sites is the center of the brow. The temperature measurement takes only 1 second, does not contact human skin. The infrared thermometer is intended for use on people of all ages except pre-term babies.

The YUWELL Infrared Thermometer (models YT-1, YT-1A, YT-1B, YT-1C, YT-2, YT-2A, YT-2B, YT-2C) underwent non-clinical (bench) testing to demonstrate substantial equivalence to its predicate device, the Braun No touch + Forehead NTF3000 Thermometer (K163516).

Here's a breakdown of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a "table of acceptance criteria and reported device performance" in the typical format of a clinical study report with specific statistical thresholds for metrics like sensitivity, specificity, or accuracy. Instead, the performance is demonstrated by conformity to recognized consensus standards for medical thermometers. The key acceptance criteria are the accuracy specifications described by ASTM E 1965 and ISO 80601-2-56.

The following table summarizes the device's accuracy specifications, which serve as the internal acceptance criteria regarding temperature measurement performance:

Beyond accuracy, other "criteria" for acceptance are successfully meeting the requirements of various international standards as listed in Section 5.9, including:

• Software verification and validation (FDA Guidance for software in medical devices)
• Biocompatibility (ISO 10993 and FDA Bluebook memo G95-1)
• Electrical safety (IEC 60601-1)
• Electromagnetic compatibility (IEC 60601-1-2)
• Home use (IEC 60601-1-11)

The document states, "all testing results have come back as positive results or pass for the subject device," indicating that these criteria were met.

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

The document describes non-clinical (bench) testing. Therefore, there is no "test set" of patient data in the context of a clinical study, nor data provenance (country of origin, retrospective/prospective). The performance testing was conducted according to ASTM E 1965 and ISO 80601-2-56, which are standards for infrared thermometers' performance. These standards involve laboratory testing with controlled temperature sources, not human subjects in a clinical setting. The specific sample sizes (e.g., number of measurements) for these bench tests are not provided in this summary.

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

Not applicable. This was a non-clinical (bench) study involving physical and electrical performance measurements against established standards, not interpretation by medical experts.

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

Not applicable. As this was non-clinical bench testing, no adjudication of expert opinions was required.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. This is not an AI-powered device, nor does it involve human "readers" or case interpretation. It is a standalone infrared thermometer.

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

Yes, the testing described is a standalone performance assessment of the device itself (the "algorithm" in a sense, refers to the device's internal measurement and processing capabilities) without human interpretation in the loop influencing the measurement output. The device functions as a direct measurement tool. The "Performance test according to ASTM E 1965 and ISO80601-2-56" is a standalone evaluation of the device's ability to accurately measure temperature under controlled conditions.

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

The ground truth for the "performance test" was established by calibrated reference temperature sources, as is standard for testing medical thermometers according to ASTM E 1965 and ISO 80601-2-56. These standards dictate precise methods for measuring the accuracy of temperature readings against known, stable temperatures.

8. The sample size for the training set

Not applicable. This is a traditional medical device (infrared thermometer), not an AI/Machine Learning device that requires a training set.

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

Not applicable. This is a traditional medical device, not an AI/Machine Learning device.

Ask a specific question about this device

Electronic blood pressure monitor is intended to measure the blood pressure and pulse rate of adult in household or medical facilities. (Not suitable for neonate, pregnancy or pre-eclampsia)

The measuring method for the Upper Arm Type Electronic Blood Pressure Monitor Series is oscillation mensuration. The subject devices will automatically start to take measurements after the inflation of the cuff is finished, the results will show the systolic pressure with pulse rate. The blood pressure monitor will store the measurements automatically; the time, date, blood pressure value and pulse value are included. The record maybe revisited.

Here's a breakdown of the acceptance criteria and study information for the Electronic Blood Pressure Monitor (models YE620B, YE620D, YE660E, YE660F, and YE680B), based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Clinical Validation (Test Set): 85 participants.
• Data Provenance: The document does not explicitly state the country of origin for the clinical study. It is a prospective study as participants were "involved in the study" and "three valid blood pressure values are taken for each participant."

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

• Number of Experts: The document states that "nurses" took the blood pressure values for the participants. The exact number of nurses is not specified, nor are their specific qualifications (e.g., years of experience in blood pressure measurement), beyond being "nurses."
• Ground Truth Establishment: The ground truth was established by these nurses using a reference device, a mercury sphygmomanometer.

4. Adjudication Method for the Test Set

• The document implies that the ground truth for each participant consisted of "three valid blood pressure values" taken by nurses. An explicit adjudication method (e.g., 2+1, 3+1 consensus) for these three values is not specified. It suggests these three values were directly used, perhaps averaged, or that "valid" implies some internal consistency checking.

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

• No, an MRMC comparative effectiveness study was not done. The study described is a clinical validation against a reference standard (mercury sphygmomanometer), not a comparison of human readers with and without AI assistance.

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

• Yes, a standalone performance study was done. The clinical validation detailed is focused on the device's (algorithm's) accuracy in measuring blood pressure compared to a reference standard (mercury sphygmomanometer), without human intervention in the device's measurement process itself.

7. The Type of Ground Truth Used

• Expert Consensus / Reference Standard: The ground truth was established by "nurses" using a "mercury sphygmomanometer" as the reference device. This falls under the category of a reference standard established by human experts.

8. The Sample Size for the Training Set

• The document does not specify a training set sample size. This is typical for a 510(k) submission for a non-AI medical device like a blood pressure monitor, where the focus is on clinical validation against a standard, not machine learning model training. The device's underlying oscillometric algorithm would have been developed and validated internally by the manufacturer, but details of that process (including training sets for the algorithm itself) are not usually part of a 510(k) summary focused on clinical performance for regulatory clearance.

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

• As no training set is explicitly mentioned or detailed in the document, how its ground truth was established is not provided.

Ask a specific question about this device

Electronic blood pressure monitor is intended to measure the blood pressure and pulse rate of adult at household or medical center. (Not suitable for neonate, pregnancy or pre-eclampsia).

The measuring method for the Upper Arm Type Electronic Blood Pressure Monitor Series is oscillation mensuration. The series will automatically starting to take measurements after the inflation of the cuff finished, the results will show the systolic pressure and diastolic pressure and pulse rate. The monitor will store the measurements automatically, which including the time, date, blood pressure and pulse. The record could be revisited. Total 74 sets of data could be stored for YE670A, 60 sets of data for YE670D, 60 sets of data for YE650A, 80 sets of data for YE650D and 74 sets of data for YE660B.

The provided text describes the 510(k) premarket notification for a series of Upper Arm Type Electronic Blood Pressure Monitors (YE650A, YE650D, YE660B, YE670A, and YE670D). The primary goal of a 510(k) submission is to demonstrate substantial equivalence to a legally marketed predicate device, rather than proving that a device meets specific acceptance criteria through novel clinical study data.

Therefore, the document does not contain information about a study proving the device meets acceptance criteria in the context of an AI/ML or diagnostic device that would typically involve a test set, ground truth, expert consensus, or MRMC studies. This is a blood pressure monitor, and its performance acceptance criteria are typically met through validation against recognized standards like ANSI/AAMI/ISO 81060-2 and IEC 80601-2-30.

Here's an analysis based on the provided text, focusing on what is stated or implied about performance validation for this type of device:

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

The acceptance criteria for blood pressure monitors are established by international standards. The document states that the Performance of the devices (YE650A, YE650D, YE670A, YE670D, and YE660B) meets:

• ANSI/AAMI/ISO 81060-2
• IEC 80601-2-30

These standards specify the accuracy requirements for non-invasive sphygmomanometers. While the document doesn't explicitly present a table of acceptance criteria and reported performance values from a clinical study for these specific devices, it does provide the following specifications and states they comply with the standards:

The core "proof" of meeting acceptance criteria for this device type, as documented here, is the declaration of compliance with these recognized international standards. These standards encompass the clinical validation of blood pressure measuring devices.

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

The document does not specify the sample size or data provenance (e.g., country of origin, retrospective/prospective) for the clinical validation studies that would have been conducted to demonstrate compliance with ANSI/AAMI/ISO 81060-2. These details are typically found in the full test reports, which are not part of this summary document. For ISO 81060-2, a specific number of subjects (e.g., typically at least 85 subjects with a certain distribution of blood pressures) are required for the clinical validation test.

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

This section is not applicable in the context of a blood pressure monitor's clinical validation. The "ground truth" for blood pressure measurements in validation studies (per ISO 81060-2) involves simultaneous auscultatory measurements performed by trained observers (often two observers for redundancy and comparison), against which the device's readings are compared. It's not about expert interpretation of an image or signal.

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

Not applicable in the sense of image interpretation adjudication. For blood pressure validation per ISO 81060-2, the method involves comparing the device's readings to those obtained by two trained auscultatory observers, often with a third observer or specific rules for resolving discrepancies if the initial two observers differ beyond a defined threshold. The standard specifies statistical analysis methods (e.g., Bland-Altman plots, mean difference, standard deviation) to assess agreement.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. This is a standalone diagnostic device for blood pressure measurement, not an AI-assisted diagnostic tool that aids human readers in interpreting complex medical images or signals.

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

Yes, in a sense. Blood pressure monitors operate largely as "standalone" automated devices. The performance evaluation (compliance with ISO 81060-2) assesses the device's accuracy in measuring blood pressure values independently, which are then displayed to the user. There isn't an "algorithm only" vs. "human-in-the-loop" distinction in the same way as for, say, an AI diagnostic aid. The device itself is the "algorithm" providing the measurement.

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

The ground truth for non-invasive blood pressure monitors, as defined by ISO 81060-2, is typically simultaneous auscultatory measurements performed by trained and certified observers using a calibrated sphygmomanometer and stethoscope. This is considered the clinical gold standard for non-invasive blood pressure.

8. The sample size for the training set

Not applicable in the traditional sense of AI/ML training sets. Blood pressure monitors use established algorithms based on oscillometric principles, not machine learning algorithms trained on large datasets. The device's underlying algorithm is developed and refined by the manufacturer, but there isn't a "training set" like there would be for an AI model.

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

Not applicable for the same reasons as point 8. The "ground truth" for the development of the oscillometric algorithm itself would be based on fundamental physiological principles and extensive engineering validation, likely drawing from datasets of pressure waveforms, but not a "training set" in the context of expert-labeled data for an AI model.

Ask a specific question about this device