Search Results

Fully Automatic Electronic Blood Pressure Monitor is for use by medical professionals or at home and is a non-invasive blood pressure measurement system intended to measure the diastolic and systolic blood pressures and pulse rate of an adult individual by using a non-invasive technique in which an inflatable cuff is wrapped around the wrist. The cuff circumference is limited to 14cm-25cm.

Fully Automatic Electronic Blood Pressure Monitor (KD-743V, KD-743B, KD-752) is designed and manufactured according to IEC 80601-2-30.

The operational principle is based on oscillometric and silicon integrates pressure sensor technology. It can calculate the systolic and diastolic blood pressure, and display the result on the LCD. The measurements results can also be classified by the function of blood pressure classification indicator. If any irregular heartbeat is detected, it can be shown to the user.

This document is a 510(k) summary for a blood pressure monitor, not an AI/ML device. Therefore, the detailed information typically required for describing an AI/ML model's acceptance criteria and validation study (such as training/test set sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, and ground truth establishment for AI models) is not provided in this document.

The document discusses the substantial equivalence of the "Fully Automatic Electronic Blood Pressure Monitor" (models KD-743V, KD-743B, KD-752) to predicate devices (KD-753, K183535 and KD-721, K163276). The "acceptance criteria" here refer to meeting established performance standards for non-invasive blood pressure monitors, rather than the performance metrics of an AI algorithm.

Here's a breakdown of what can be extracted and what information is not available from the provided text, in the context of your specific questions:

Acceptance Criteria and Reported Device Performance

The acceptance criteria for blood pressure monitors are generally based on international standards like ISO 81060-2, which specifies requirements for the accuracy of automated non-invasive sphygmomanometers. The document states:

"Accuracy of the blood pressure monitors for the clinical test report was verified by meeting criteria 1 and criteria 2 of ISO 81060-2."

While the specific numeric criteria (e.g., mean difference and standard deviation of differences between device and reference measurements) are not explicitly listed in a table within this document, meeting ISO 81060-2 criteria 1 and 2 is the acceptance benchmark.

Detailed Information as Requested for AI/ML Studies:

1. A table of acceptance criteria and the reported device performance: See table above. This is based on NIBP standards, not AI performance metrics.

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

   • The document refers to "clinical test report of KD-7961" and "clinical test report of KD-972" being used as reference for the subject devices. These reports verified accuracy by meeting ISO 81060-2 criteria.
   • ISO 81060-2 typically recommends a minimum of 85 subjects for validation. While not explicitly stated here for the specific test, it's implied that the reference clinical tests adhered to this.
   • Data Provenance: Not specified (e.g., country of origin). The document states the company is based in Tianjin, China.
   • Retrospective or Prospective: Not specified. Clinical validation studies for medical devices are typically prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable in the context of this device study. Ground truth for blood pressure monitors is established by simultaneously measuring blood pressure using a calibrated reference method (e.g., auscultation by trained observers) and the device under test. It's not a consensus-based reading like for imaging. ISO 81060-2 requires a minimum of three trained observers for reference measurements. Their specific qualifications (e.g., years of experience) are not detailed in this summary, beyond "trained observers."

4. Adjudication method for the test set: Not applicable in the AI/ML sense. For NIBP validation, the "adjudication" is the comparison of device readings against the mean of the reference observers' readings, as per ISO 81060-2. There's no consensus or 2+1/3+1 adjudication of images.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not applicable. This is a blood pressure monitor, not an AI-assisted diagnostic imaging device.

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 performs the measurement. The "algorithm" here refers to the oscillometric method of blood pressure determination, not a separate AI algorithm that provides diagnostic interpretations.

7. The type of ground truth used: Reference blood pressure measurements obtained by trained observers using a reference method (e.g., auscultation), according to ISO 81060-2.

8. The sample size for the training set: Not applicable. This is a conventional medical device, not an AI/ML device that requires a distinct "training set" for model development. The "algorithm" for blood pressure measurement is based on established oscillometric principles and does not "learn" from a training set in the way an AI model does.

9. How the ground truth for the training set was established: Not applicable, as there's no training set for this type of device.

In summary: The provided document is a regulatory submission for a conventional medical device (blood pressure monitor), not an AI/ML product. Therefore, many of the detailed questions regarding AI/ML model validation are not addressed, as they are not relevant to this type of device. The "acceptance criteria" revolve around established performance standards for blood pressure measurement accuracy (ISO 81060-2).

Ask a specific question about this device