Search Results

It is a device intended to measure the systolic, diastolic blood pressure and pulse rate of an adult individual by using a non-invasive oscillometric technique in which an inflatable cuff (available sizes: 22cm44cm (8.7in17.3in)) is wrapped around the single upper arm.

Arm automatic blood pressure monitor is based on pressure vibration method. Blood pressure cuff use the air pump to inflate, then the arteries are extruded by the cuff with pressure. Pressure sensor collects the pressure in the cuff, and then converts it to digital signal to the CPU. Then the software calculates the systolic and diastolic blood pressure and pulse rate.

This device is an Arm automatic blood pressure monitor, and the provided text describes its substantial equivalence to a predicate device, rather than presenting a standalone study with acceptance criteria and performance metrics in the typical sense of AI/ML device studies. This document is a 510(k) summary from the FDA.

However, I can extract the relevant "acceptance criteria" for blood pressure measurement accuracy based on the provided specifications, and then infer how it meets these based on the comparison to the predicate device and the referenced standard.

Inference from the text:

The device is an automatic blood pressure monitor that uses an oscillometric technique. The "acceptance criteria" are implied by the accuracy specification listed in the comparison table and the adherence to the IEC 80601-2-30 standard, which defines accuracy requirements for automated sphygmomanometers.

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

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

• Sample Size for Test Set: The document explicitly states: "Therefore repeated clinical test in accordance with the standard IEC 80601-2-30:2009 & A1:2013 is unnecessary." This indicates that no new clinical test set was used for the subject device to re-evaluate its accuracy for blood pressure measurement. Instead, substantial equivalence was established based on the technical similarity to the predicate device, which would have undergone clinical testing to meet the IEC 80601-2-30 standard. The IEC 80601-2-30 standard typically requires a clinical validation study with a specified number of subjects (e.g., at least 85 subjects for validation, including sufficient numbers in different blood pressure ranges). However, the specific sample size for the predicate is not provided in this document.
• Data Provenance: Not applicable for a new clinical test set for the subject device because it was deemed unnecessary. For the predicate device's validation (which the subject device is relying upon for clinical accuracy), the provenance is not detailed in this document.

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

• Not applicable as no new clinical test set was performed for the subject device. For the predicate device's validation, the IEC 80601-2-30 standard requires a specific methodology for reference measurements, typically involving trained observers using a mercury sphygmomanometer or auscultation, but the exact number and qualifications of experts for the predicate's original study are not specified here.

4. Adjudication method for the test set:

• Not applicable as no new clinical test set was performed for the subject device. For the predicate device's validation, the IEC 80601-2-30 standard details the requirements for obtaining reference blood pressure measurements (ground truth), which often involves multiple observers and a consensus or averaging approach.

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 standalone blood pressure monitor, not an AI-assisted diagnostic tool that would involve human readers.

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

• Yes, implicitly. The device is an "automatic blood pressure monitor" that uses an "oscillometric technique" and "software calculates the systolic and diastolic blood pressure and pulse rate." This is a standalone algorithm (device) performance measurement. The accuracy criteria (Pressure: ±3mmHg, Pulse: ±5%) are for this standalone performance. The document states that because the technical aspects influencing blood pressure measurement were identical to the predicate, a repeated clinical test was unnecessary, meaning the standalone performance of the subject device is considered to meet the same accuracy standards as the predicate, which would have been established through a standalone clinical validation.

7. The type of ground truth used:

• For the clinical validation implied by adherence to IEC 80601-2-30, the ground truth for blood pressure measurements is typically established through auscultation by trained observers using a reference standard like a mercury sphygmomanometer. This involves direct physiological measurement.

8. The sample size for the training set:

• Not applicable in the context of typical AI/ML training sets. This device uses a "pressure vibration method" and a "software algorithm" for calculation, but the document does not describe it as an AI/ML device that requires a distinct "training set" for model development in the machine learning sense. The algorithm would have been developed and fine-tuned based on engineering principles and potentially clinical data, but not referred to as a "training set."

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

• Not applicable, as no described training set in the AI/ML sense. The algorithm's development would follow standard medical device software engineering practices, with performance validated against reference physiological measurements based on established medical standards (e.g., auscultation).

Ask a specific question about this device

It is a device intended to measure the systolic, diastolic blood pressure and pulse rate of an adult individual by using a non-invasive oscillometric technique in which an inflatable cuff (available sizes: 22cm44cm (8.7in17.3in)) is wrapped around the single upper arm.

Arm automatic blood pressure monitor is based on pressure vibration method. Blood pressure cuff use the air pump to inflate, then the arteries are extruded by the cuff with pressure. Pressure sensor collects the pressure in the cuff, and then converts it to digital signal to the CPU. Then the software calculates the systolic and diastolic blood pressure and pulse rate.

This document is a 510(k) Summary for a medical device called an "Arm automatic blood pressure monitor" (various models). The purpose of this summary is to demonstrate that the new device is substantially equivalent to a legally marketed predicate device.

Here's an analysis of the acceptance criteria and study information provided, extracting the requested details:

Acceptance Criteria and Device Performance

The acceptance criteria for accuracy are based on the ANSI/AAMI/ISO 81060-2:2009 standard for non-invasive sphygmomanometers. While the document mentions that a repeated clinical test for the subject devices was "unnecessary" due to technical similarity with the predicate, the predicate device's performance, which the subject devices claim substantial equivalence to, is detailed in a comparison table.

Table of Acceptance Criteria and Reported Device Performance

Study Information:

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

   • The document states that a repeated clinical test for the subject devices was unnecessary because the subject devices are identical to the predicate device from a technical point of view, and the differences (Power Source, Weight, Size, Broadcast Function) do not relate to blood pressure measurement technology. Therefore, no new clinical test data for the subject devices is provided in this summary.
   • The provenance of the data for the predicate device's clinical validation (which established the acceptance criteria for these equivalence claims) is not detailed in this document. It is implied that the predicate device (K151258) met the ANSI/AAMI/ISO 81060-2:2009 standard, but the specific details of that study are not provided in this submission.

2. 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)

   • Since a new clinical test for the subject device was deemed "unnecessary," there would be no new ground truth established for the subject device in this submission. The ground truth for the predicate device's accuracy would have been established during its original clinical validation against the ANSI/AAMI/ISO 81060-2:2009 standard, which typically involves comparing automated measurements to those taken by trained observers using a reference sphygmomanometer. Details on the number or qualifications of these "experts" (trained observers) are not provided in this document.

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

   • No new clinical test was performed for the subject device, so no adjudication method is mentioned for its test set. The ANSI/AAMI/ISO 81060-2 standard outlines procedures for obtaining reference blood pressure measurements, often involving multiple observers to minimize bias, but the specific method used for the predicate device's validation is not detailed here.

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

   • This is not applicable. The device is an automatic blood pressure monitor, not an AI-assisted diagnostic tool that would involve human "readers" or an MRMC study.

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

   • The core functionality of an "Arm automatic blood pressure monitor" is inherently standalone. It uses an oscillometric technique to calculate blood pressure and pulse rate without human intervention during the measurement process. The comparison tables indicate the subject device and predicate device "use the same oscillometric method within the software algorithm to determine the systolic and diastolic blood pressure and pulse rate." This implies a standalone algorithm performance.

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

   • For blood pressure monitors, the "ground truth" during clinical validation (following standards like ANSI/AAMI/ISO 81060-2) is typically established by simultaneous auscultatory measurements performed by trained observers using a calibrated reference sphygmomanometer. This is considered an expert comparison or reference measurement.

7. The sample size for the training set

   • This document does not specify a training set as it focuses on demonstrating substantial equivalence rather than detailing the development and initial validation of the algorithm itself. The oscillometric method used is a well-established technique for blood pressure measurement, and any "training" (e.g., development of the algorithm's parameters) would have occurred during the initial design and validation of the predicate device's core technology, which is not described here.

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

   • As no training set is explicitly discussed in this document for the subject device, the method for establishing its ground truth is not provided. For oscillometric devices, the algorithm's parameters are typically derived and refined based on clinical data where the device's readings are compared against standard reference measurements.

Ask a specific question about this device

It is a device intended to measure the systolic, diastolic blood pressure, pulse rate of an adult individual by using a non-invasive oscillometric technique in which an inflatable cuff (available sizes: 22cm to 44cm (8.7in to 17.3in)) is wrapped around the single upper arm.

Arm automatic blood pressure monitor is based on pressure vibration method. Blood pressure cuff uses the air pump to inflate, and then the arteries are extruded by the cuff with pressure. Pressure sensor collects the pressure in the cuff, and then converts it to digital signal to the CPU. Then the software calculates the systolic, diastolic blood pressure and pulse rate.

The provided document is a 510(k) summary for the Shenzhen Pump Medical System Co., Ltd.'s Arm Automatic Blood Pressure Monitor, Models BE6034 and BE6134. It details the device's substantial equivalence to a predicate device but does not contain a standalone clinical study on the subject device (BE6034, BE6134) for blood pressure measurement accuracy with defined acceptance criteria and reported performance.

Instead, the document states: "The subject device, Model BE6034, BE6134 is from the technical point of view, identical to the predicate blood pressure monitor. Model BF1112, BF1113 and BF1115. The differences between them do not relate to blood pressure measurement technology, so the clinical accuracy in terms of blood pressure detection will not be affected. Therefore repeated clinical test in accordance with the standard IEC 80601-2-30:2009 & A1:2013... is unnecessary."

The acceptance criteria and reported device performance for blood pressure measurement accuracy are inferred from the predicate device's specifications, as no new clinical study was conducted for the subject devices on this aspect.

Here's a breakdown of the requested information based on the provided text, with the understanding that clinical accuracy data is based on the predicate and not a new study of the subject device in isolation:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not applicable for a new clinical test on the subject device's blood pressure accuracy, as none was performed. The determination of device accuracy for blood pressure measurement was based on the predicate device's performance.
• Data Provenance: Not applicable for a new clinical test on the subject device's blood pressure accuracy.

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

• Not applicable, as no new clinical study was performed for the subject device's blood pressure accuracy. The ground truth for the predicate device's original clinical validation would have been established according to the relevant standard (IEC 80601-2-30:2009 & A1:2013, which substituted ANSI/AAMI SP10). These standards typically involve simultaneous readings by trained observers (experts) using a reference sphygmomanometer.

4. Adjudication method for the test set

• Not applicable, as no new clinical study was performed for the subject device's blood pressure accuracy.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device is an automatic blood pressure monitor and does not involve human readers interpreting results in the context of AI assistance.

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

• A standalone performance assessment for the subject devices (BE6034, BE6134) explicitly demonstrating blood pressure accuracy was not done or required by the FDA. The justification provided is that the "subject device... is from the technical point of view, identical to the predicate blood pressure monitor... The differences between them do not relate to blood pressure measurement technology, so the clinical accuracy in terms of blood pressure detection will not be affected." Therefore, the clinical performance of the subject device is considered equivalent to the predicate device.

7. The type of ground truth used

• For blood pressure monitors, the ground truth for clinical validation (as would have been applied to the predicate device) is typically established by simultaneous measurements by trained observers using a reference method (e.g., auscultation with a mercury or aneroid sphygmomanometer). This is a common requirement for validating blood pressure measurement accuracy according to standards like IEC 80601-2-30 (which substituted ANSI/AAMI SP10).

8. The sample size for the training set

• Not applicable to this device, as it is a medical device for vital signs measurement, not an AI model that requires a training set in the conventional sense of machine learning for image analysis or diagnostics. The software calculates blood pressure based on a pressure vibration method and an algorithm, but it's not described as an adaptive learning system.

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

• Not applicable (see point 8).

Ask a specific question about this device

The Bpump Blood Pressure Cuff, Model: BC1000, BC8000, are intended to be wrapped on the upper arm and used with a non-invasive blood pressure monitor system to complete the measurement of blood parameters on adults.

The proposed device, Bpump Blood Pressure Cuff, is a rectangle soft inelastic sleeve reusable with a bladder. There is a single-tube connected to the bladder and the Non Invasive Blood Pressure Monitor for inflating and deflating. The device should be connected to a Non Invasive Blood Pressure Monitor to complete the function. There are two sizes for different arm range as follows:

Here's a breakdown of the acceptance criteria and study information for the Bpump Blood Pressure Cuff, based on the provided FDA 510(k) summary:

• Device Name: Bpump Blood Pressure Cuff, Model: BC1000, BC8000
• Submission K-Number: K151810

1. Table of Acceptance Criteria and Reported Device Performance

   The document states that the device "met all applicable requirements of the standard" during clinical testing. The primary standard for clinical validation of automated non-invasive sphygmomanometers is ANSI/AAMI/ISO 81060-2. This standard sets out accuracy requirements for blood pressure measurement devices. While the exact numerical acceptance criteria from the standard are not explicitly listed in the provided text, the conclusion affirms compliance.

   Acceptance Criteria (Based on ANSI/AAMI/ISO 81060-2)	Reported Device Performance
   Unspecified (Meets applicable requirements of standard for accuracy)	Met all applicable requirements of the standard

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

   • Sample Size: Not explicitly stated in the provided text.
   • Data Provenance: Not explicitly stated. The submitting company is from China (Shenzhen, PEOPLE'S REPUBLIC OF CHINA), but the location of the clinical test is not mentioned. The test is described as "Clinical test has been done," suggesting it was prospective but this is not explicitly stated.

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

   This information is not provided in the document. For blood pressure devices, "ground truth" (reference measurements) are typically established by trained observers using a validated reference sphygmomanometer, often with specific training and certification for such measurements.

4. Adjudication Method for the Test Set

   This information is not provided in the document.

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 versus without AI assistance

   This is not applicable. This device is a blood pressure cuff, not an AI-powered diagnostic imaging device. Therefore, an MRMC study and analysis of AI assistance effect size are not relevant to this submission.

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

   The device is a blood pressure cuff intended to be used with a "non-invasive blood pressure monitor system." The clinical validation was for the automated measurement type according to ANSI/AAMI/ISO 81060-2, which validates the device's ability to accurately measure blood pressure. This essentially represents the "standalone" performance of the cuff and the non-invasive blood pressure monitor as a system, separate from human interpretation of complex outputs.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

   For blood pressure devices, the ground truth is typically established by simultaneous or near-simultaneous measurements using a recognized reference standard sphygmomanometer (e.g., mercurial or validated aneroid device) performed by trained observers. While not explicitly detailed, compliance with ANSI/AAMI/ISO 81060-2 implies adherence to these ground truth methodologies.

8. The Sample Size for the Training Set

   This information is not applicable. Blood pressure cuffs do not typically involve "training sets" in the machine learning sense. The device's underlying algorithm (if it uses one for interpretation of oscillometric pulses) is developed and then validated.

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

   This information is not applicable as there is no "training set" in the context of this traditional medical device.

Ask a specific question about this device

It is intended for measuring adult blood pressure and pulse rate with circumference ranging from 135 mm to 215 mm.

Blood pressure monitor is based on pressure vibration method. Blood pressure cuff use the air pump to inflate, then the arteries are extruded by the cuff with pressure. Pressure sensor collects the pressure in the cuff, and then converts it to digital signal to the CPU. Then the software calculates the systolic and diastolic blood pressure and pulse rate.

The provided document describes a 510(k) premarket notification for a Blood Pressure Monitor (K141416). The acceptance criteria and the study proving the device meets these criteria are detailed, particularly in the section on "Testing data and clinical study" and the comparison table.

Here's a breakdown of the requested information:

1. Table of acceptance criteria and the reported device performance

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

The document states that "Clinical study has been evaluated according to ANSI/AAMI SP10 and ANSI/AAMI/ISO 81060-2."

• ANSI/AAMI SP10 (Manual, electronic, or automated sphygmomanometers) typically requires a minimum of 85 subjects for clinical validation.
• ANSI/AAMI/ISO 81060-2 (Non-invasive sphygmomanometers - Part 2: Clinical validation of automated measurement type) specifies a clinical investigation with a minimum of 85 participants meeting certain age, gender, and blood pressure distribution requirements.

Based on the reference to these standards, it is highly probable that the study included at least 85 subjects. However, the exact sample size is not explicitly stated in the provided text.

The data provenance (country of origin, retrospective/prospective) is not explicitly stated in the provided text. It is a clinical study, implying it was prospective, but this is not confirmed.

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

The document does not explicitly state the number of experts or their qualifications for establishing ground truth. Compliance with ANSI/AAMI SP10 and ANSI/AAMI/ISO 81060-2 for clinical validation typically involves reference measurements performed by trained observers (auscultatory method), but the specific details are not provided here.

4. Adjudication method for the test set

The document does not explicitly state any adjudication method for the test set. Compliance with ANSI/AAMI SP10 and ANSI/AAMI/ISO 81060-2 for clinical validation typically involves comparing device measurements against reference measurements taken by trained observers, where differences are analyzed. However, the specific method of handling discrepancies or consensus building is not detailed here.

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

This is not applicable. The device is a "Blood Pressure Monitor," which is an automated measurement device, not an AI-assisted diagnostic tool requiring human reader interpretation. Therefore, an MRMC study or evaluation of human reader improvement with AI assistance would not be relevant.

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

Yes, the device is standalone. It is a "Blood Pressure Monitor" that measures adult blood pressure and pulse rate automatically using an oscillometric method. Its performance is evaluated directly against reference measurements in clinical studies, without human intervention in the measurement process itself.

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

The ground truth for the clinical study would be established through reference blood pressure measurements obtained by trained observers using the auscultatory method, as per the requirements of ANSI/AAMI SP10 and ANSI/AAMI/ISO 81060-2. This is a form of expert reference measurement.

8. The sample size for the training set

The document does not provide any information regarding a specific "training set" or its size. For a medical device like a blood pressure monitor, manufacturers typically calibrate and develop their algorithms using internal data, but this is usually not referred to as a "training set" in the context of regulatory submissions the way it would be for an AI/ML device. The regulatory focus is on the clinical validation (test set) against established standards.

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

Since there is no explicit mention of a "training set" in the context of this regulatory submission, there is no information on how its ground truth might have been established. Any internal development and calibration would have used methods consistent with blood pressure measurement best practices.

Ask a specific question about this device

It is intended for use in measuring temperature in the human body (Armpit or Oral).

The body temperature is converted into electronic signal by the temperature sensor, and then the electronic signal is converted into LCD digital display. The Electronic Thermometers TF3100, TF3101 and TF3102 have the same basic principles, main function, performance and intended use, and they are consistent in product structure and material.

The provided PDF outlines the acceptance criteria and a study demonstrating that the Electronic Thermometer (Models TF3100, TF3101, TF3102) meets these criteria.

1. Table of Acceptance Criteria and Reported Device Performance:

The primary performance characteristics addressed in the submission are accuracy and response time. The acceptance criteria are based on recognized international and national standards for clinical electronic thermometers.

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

The document states that "Clinical evaluation of Electronic Thermometers has been conducted by SHENZHEN PUMP MEDICAL SYSTEM CO., LTD." However, the specific sample size used for the test set and the data provenance (e.g., country of origin, retrospective or prospective) for this clinical evaluation are not provided in the given text.

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

This information is not provided in the document. For a clinical thermometer, the ground truth would typically be established by highly accurate reference thermometers and not by "experts" in the sense of medical professionals adjudicating images or cases.

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

This information is not applicable and therefore not provided in the context of evaluating a clinical electronic thermometer. Adjudication methods like 2+1 or 3+1 are typically used in studies involving expert review of medical images or diagnoses, not for the direct measurement of physical parameters like temperature.

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 information is not applicable and therefore not provided. The device is an electronic thermometer, not an AI-assisted diagnostic tool that would involve human readers.

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

The device itself is a standalone electronic thermometer, designed to provide direct temperature readings. The "clinical evaluation" conducted would have assessed the device's accuracy in measuring human body temperature without human subjective interpretation. The document, however, does not explicitly describe the methodology or results of this standalone performance assessment beyond stating that "clinical evaluation... has been conducted."

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

For a clinical electronic thermometer, the ground truth would most likely be established by a highly accurate reference thermometer (e.g., a laboratory-grade mercury-in-glass thermometer or a highly calibrated electronic reference thermometer) under controlled conditions. The document does not explicitly state the type of ground truth used for the clinical evaluation, but it is inferable given the nature of the device.

8. The sample size for the training set:

This information is not applicable as the device is not an AI/ML product that would require a "training set." The submission describes a traditional electronic thermometer.

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

This information is not applicable as the device is not an AI/ML product that would require a "training set."

Ask a specific question about this device

It is intended for measuring adult blood pressure and pulse rate over-the-counter.

Arm automatic blood pressure monitor is based on pressure vibration method. Blood pressure cuff use the air pump to inflate, then the arteries are extruded by the cuff with pressure. Pressure sensor collects the pressure in the cuff, and then converts it to digital signal to the CPU. Then the software calculates the systolic and diastolic blood pressure and pulse rate.

The arm automatic blood pressure monitor BF1112, BF1112, BF1113 and BF1115 have the same basic principles, main function, performance and intended use, and they are consistent in product structure and material.

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

Acceptance Criteria and Reported Device Performance

Study Details

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

  • Sample Size: The document states that the clinical study was "evaluated according to ANSI/AAMI SP10." However, the exact sample size for the test set is not explicitly mentioned in the provided text. ANSI/AAMI SP10 is a standard for blood pressure measuring devices, and it outlines requirements for clinical validation, including sample sizes (typically a minimum of 85 subjects for accuracy assessment). Without further information, we cannot confirm the precise number of subjects used in this specific study.
  • Data Provenance: The document does not specify the country of origin of the data or whether the study was retrospective or prospective. It only mentions that the applicant is from Shenzhen, China, and the predicate device manufacturer is Omron Healthcare, Inc.

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

  • This information is not provided in the text. For blood pressure monitors, ground truth is typically established by trained observers taking manual auscultatory measurements using a mercury manometer or a validated oscillometric device, but the number and qualifications of such observers are not detailed here.

• 3. Adjudication method for the test set:

  • This information is not provided in the text.

• 4. 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 a blood pressure monitor, not an AI-assisted diagnostic device typically evaluated with MRMC studies comparing human readers. The device is standalone.

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

  • Yes. The device is an "Arm automatic blood pressure monitor" and operates as a standalone device, providing blood pressure and pulse rate measurements directly. The clinical study evaluated the device's performance against a standard, implying a standalone assessment of its accuracy.

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

  • The ground truth for blood pressure monitor validation, as per ANSI/AAMI SP10, typically involves manual auscultatory measurements performed by trained observers using a reference standard (like a mercury sphygmomanometer). While not explicitly stated as "expert consensus," this method relies on expert human measurement.

• 7. The sample size for the training set:

  • This information is not provided in the text. For traditional medical devices like this, there isn't typically a distinct "training set" in the sense of machine learning algorithms. The device's underlying algorithm is developed and calibrated, and then its performance is validated against a separate test set. The document only mentions "Laboratory testing" for specification validation.

• 8. How the ground truth for the training set was established:

  • As there isn't a "training set" described in the machine learning sense, the method for establishing ground truth for a training set is not applicable here. The device's design and calibration would have been based on established physiological principles and engineering practices, likely involving various test conditions and reference measurements during development, but this is distinct from a machine learning training set.

Ask a specific question about this device