Search Results

Accutension Smartphone Auscultatory Blood Pressure Kit is intended for professionals or home users to nonautomatically measure systolic and diastolic blood pressure on adults by detecting Korotkoff sounds and measure pulse rate on adults by detecting oscillometry. This device is not indicated for children, heart failure patients and critical patients.

The Accutension Smartphone Auscultatory Blood Pressure Kit (Model XYZ-110) is a non-invasive blood pressure measurement system for professionals and home users to nonautomatically measure systolic and diastolic blood pressure and pulse rate. It utilizes advanced pressure sensing module to transfer cuff pressure value to an iOS App via established Bluetooth connection between the module and the iOS device during measurement, meanwhile a stethoscope detects Korotkoff sounds and transfers the sound signal to the smartphone via its earphone jack. Both the cuff pressure and auscultatory sounds are visualized in the app and a user can determine the systolic and diastolic blood pressure by finding the cuff pressures on the first and last Korotkoff sounds. It automatically calculates the pulse rate based on cuff pressure oscillometry. This device consists of 5 parts, arm cuff, pressure sensing module, hand pump (bulb) with airflow valve, stethoscope with earphone plug and charging cable.

This document describes the 510(k) premarket notification for the Accutension Smartphone Auscultatory Blood Pressure Kit (Model XYZ-110). It demonstrates the device's substantial equivalence to predicate devices for blood pressure and pulse rate measurement. The core of the evidence relies on clinical and non-clinical testing, particularly adherence to ISO 81060-2:2013 for blood pressure accuracy.

Here's a breakdown of the requested information based on the provided text:

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

The document states that the device's accuracy was assessed against the criteria specified in ISO 81060-2:2013. While specific numerical acceptance criteria (e.g., mean difference, standard deviation) for blood pressure are not explicitly tabulated in the provided text, the conclusion section confirms that the device "satisfies the criteria specified in ISO 81060-2:2013" and is "as safe and effective (accurate) in a clinical environment".

For pulse rate, the document states: "Testing to demonstrate pulse rate accuracy" was performed, and the Conclusion claims the device demonstrates "the same level of safety, effectiveness and performance" as predicate devices. However, explicit numerical acceptance criteria for pulse rate accuracy are not provided.

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

• Sample Size for Clinical Test (Blood Pressure Accuracy): "255 pairs of data from 85 valid subjects were achieved following the clinical study protocol defined in ISO 81060-2:2013."
• Data Provenance: The text does not explicitly state the country of origin of the data. Since the submitting company is Shanghai Hulu Devices Co., Ltd, it is highly probable the data originated from China. The study is described as a "clinical study," which implies a prospective collection of data.

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

The document mentions that a "manual Mercury Sphygmomanometer was used as a reference device in the clinical testing." For the primary blood pressure determination, the device relies on a human user "listening to the Korotkoff sounds with human ear." However, the text does not specify the number of expert readers, their qualifications (e.g., radiologists, physicians with X years of experience), or if they were involved in establishing the "ground truth" beyond performing the reference measurements with the mercury sphygmomanometer. The ISO 81060-2 standard usually details requirements for reference measurements and observers.

4. Adjudication method for the test set

The document describes a "Same arm simultaneous method" used during the clinical validation, with a manual Mercury Sphygmomanometer as a reference. This usually implies a direct comparison, rather than an adjudication process between multiple readers. No mention of an adjudication method (e.g., 2+1, 3+1) is made for determining the ground truth for 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

There is no mention of a multi-reader, multi-case (MRMC) comparative effectiveness study. The device is not an AI-assisted diagnostic tool in the typical sense where AI provides an interpretation and human readers improve with its assistance. Instead, it digitizes and visualizes blood pressure and Korotkoff sounds for a human user to interpret. The study focuses on the accuracy of the device itself compared to a reference standard (manual mercury sphygmomanometer).

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

No, the device is explicitly designed for human-in-the-loop performance. The core method for blood pressure determination is "By listening to the Korotkoff sounds with human ear". The device visualizes the sounds and cuff pressure, which "provides an extra feature to help capture the first and last Korotkoff sounds for blood pressure determination." Therefore, no standalone algorithm-only performance was conducted or is applicable given the device's function. The pulse rate is "automatically calculates based on cuff pressure oscillometry," which is a standalone algorithm component for that specific measurement.

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

The ground truth for blood pressure measurement was established using a "manual Mercury Sphygmomanometer" as a reference device in the clinical testing, following the protocol of ISO 81060-2:2013. This implies a direct, real-time comparison to a well-accepted clinical standard performed by human observers.

8. The sample size for the training set

The document does not mention a "training set" in the context of machine learning or AI models. Given that the device's primary method for blood pressure determination relies on human auscultation supplemented by visualization, and pulse rate is calculated via oscillometry (a known physiological method), there isn't an explicit "training set" for an AI algorithm for these core functions. The term "training set" is usually relevant for AI/ML devices that learn from data, which doesn't appear to be the case for the primary blood pressure determination function here.

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

As there is no explicit mention of a "training set" for a machine learning model for blood pressure determination, this question is not applicable to the provided information.

Ask a specific question about this device