Search Results

The Fully Automatic Blood Pressure Monitors are intended to measure blood pressure (systolic and diastolic) and pulse rate of adults and adolescents age 12 through 21 years of age.

The arm-type series use an inflatable cuff which wraps around the patient's upper arm. The cuff is inflated automatically by an internal pump in the device. The systolic and diastolic blood pressures are determined by oscillometric method and silicon integrate pressure sensor technology. The deflation rate is controlled by a preset mechanical valve at a constant rate. The pressure of the cuff is completely released automatically at the end of the measurement. At the same time, the measurements are displayed on the LCD display for three minute. There is a maximum pressure safety setting at 300 mmHg. The device will not inflate the cuff higher than 300 mmHg.

The provided document describes the acceptance criteria and a clinical study conducted to demonstrate the substantial equivalence of the JOYTECH Fully Automatic Digital Blood Pressure Monitor (K173024) to its predicate devices. The study aimed to prove the accuracy of the blood pressure monitors.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are based on the ISO 81060-2 Standard.
There are two methods for evaluation:

Method 1: Mean difference and standard deviation of differences.

Method 2: Standard deviation of averaged paired determinations.

Note on Method 2 Acceptance Criteria: The specific maximum permissible standard deviation (Sm) values are derived from "Tab 1" in the document, which provides a lookup table based on the averaged mean difference ($\overline{x}_n$). The reported values for the device performance (e.g., 3.71 mmHg for arm-type systolic) are compared against the corresponding values from this table (e.g., < 6.91 mmHg if the mean difference is around -0.57 mmHg). The document states that "the averages difference... and the corresponding standard deviation fall are within the range of the standard."

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

• Sample Size: 85 subjects for the arm-type blood pressure monitor and 85 subjects for the wrist-type blood pressure monitor.
• Data Provenance: The studies were conducted "in the hospital." The country of origin is implied to be China, as JOYTECH Healthcare Co., Ltd. is based in Hangzhou, China. The studies are prospective in nature, as they involved actively recruiting and measuring subjects for the clinical validation.

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

• Number of Experts: Two doctors were used to perform the simultaneous and blinded blood pressure determinations.
• Qualifications of Experts: The document does not explicitly state the specific qualifications (e.g., years of experience, specialization like radiologist) of these "two doctors." However, by performing manual blood pressure measurements using a standard mercury sphygmomanometer in a clinical validation setting, it is implied they are medically trained professionals competent in such procedures.

4. Adjudication method for the test set

• The ground truth was established by "Simultaneous and blinded blood pressure determinations were performed by two doctors." This implies a form of dual-reader reading with a reference standard, where both doctors likely took independent measurements, and these were then compared against each other and the test device. The document does not specify a formal adjudication process if there were discrepancies between the two doctors' readings, such as a third reader or a specific consensus method. However, the ISO 81060-2 standard typically requires such a process or agreement between observers.

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 study is a clinical validation of the device's accuracy against a reference standard, not a study evaluating human reader performance with or without AI assistance. The device is a blood pressure monitor, not an AI-driven diagnostic tool that assists human readers.

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

• Yes, a standalone performance evaluation was done. The clinical study directly tested the accuracy of the automated blood pressure monitor (the algorithm/device itself) against manual measurements by human experts (using a standard mercury sphygmomanometer). The results provided in the tables above represent the standalone performance of the device without human intervention in the measurement process itself, other than applying the cuff and initiating the measurement.

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

• The ground truth used was expert measurements (made by two doctors) using a standard mercury sphygmomanometer, which serves as the reference method in accordance with clinical validation standards for blood pressure devices (ISO 81060-2). This is a form of expert consensus or highly accurate direct measurement.

8. The sample size for the training set

• The document does not provide information on a training set sample size. This is expected because the device in question is a traditional blood pressure monitor, not an AI/ML-based device that typically requires a distinct training set. The clinical study described is for validation/testing, not for training.

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

• As the document does not refer to a training set or an AI/ML component requiring training, this information is not applicable to the provided context.

Ask a specific question about this device