(90 days)
The device is a digital monitor intended for use in measuring blood pressure and pulse rate in adult patient population with wrist circumference ranging from 5.3 inches (13.5cm to 21.5cm). The device detects the appearance of irregular heartbeats during measurement and gives a warning signal with readings.
The Wrist Blood Pressure Monitor Model BP4350 ("BP4350") is a battery-powered, automatic, noninvasive, wrist-worn blood pressure measuring system intended for over-the-counter (OTC) home use. BP4350 is designed for wrist circumference ranging from 5.3 inches to 8.5 inches (13.5cm to 21.5cm). The systolic and diastolic blood pressures are measured using the oscillometric method, where the cuff is inflated with an integral controllable Piezoelectric pump and deflates via an electric automatic rapid deflation 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 cuff can measure pressure range from 0 to 299mmHg, and the pulse rate range from 40 to 180 beats/min.
The device also detects the appearance of irregular heartbeats during the blood pressure measurement process, which is defined as the appearance of two (2) or more heartbeat intervals which differ by greater than 25% from the average heartbeat rhythm. Detection of such irregular rhythms would result in an "irregular heartbeat symbol" displayed along with the blood pressure and pulse rate readings. In addition, a "HIGH" indication appears if the blood pressure recorded is greater than 130/80 based on the AHA/ACC High Blood Pressure Clinical Practice Guideline criterion for Stage 1 Hypertension, published in 2017.
In addition, the device includes an Advanced Positioning Sensor (APS) feature known as the Heart Zone Indicator, which aids the user in determining if the Wrist Cuff is at the correct height in relation to the heart. It makes this determination based on the reading of an accelerometer (integral to the device) to measure the angle of the arm in relation to the table. The APS feature is similar to the predicate device.
The device displays the latest blood pressure reading, while up to 100 readings can be stored in memory. The operation of the device is intended for home use. Functions and other features that are controlled by the end user include applying the wrist cuff to the wrist, powering on/off the system, starting or stopping the blood pressure and pulse measurement cycle, and installing and changing the batteries as needed. As an optional feature, the user can also pair the BP4350 to a smartphone when employing the "Omron connect" app. This app is an optional feature and is only intended to display trend graphs of measured systolic and diastolic blood pressure, and pulse rate. This app does not provide any diagnostic or measurement functions and does not interpret or analyze the data for medical decision making. Unlimited readings can be stored in the app for archiving and review by the user. Aside from this optional app for smartphones, BP4350 does not connect with other collateral devices.
The provided text describes the 510(k) summary for the Omron Healthcare, Inc. Wrist Blood Pressure Monitor Model BP4350. This document primarily focuses on establishing substantial equivalence to a predicate device rather than detailing a study that proves the device meets specific acceptance criteria in the context of an AI/ML-driven device.
Therefore, much of the requested information regarding acceptance criteria for an AI/ML device, sample sizes for test sets, data provenance, expert ground truth establishment, adjudication methods, MRMC studies, standalone algorithm performance, and training set details cannot be extracted from this document as it is not an AI/ML device and the study described is a traditional clinical validation for a blood pressure monitor.
However, I can extract the information relevant to a traditional medical device clinical validation study as presented in the document:
1. A table of acceptance criteria and the reported device performance
The document refers to the acceptance criteria implicitly by stating adherence to the ANSI/AAMI/ISO 81060-2:2013 standard for non-invasive sphygmomanometers. This standard dictates the accuracy requirements for blood pressure monitors.
| Acceptance Criteria (from ANSI/AAMI/ISO 81060-2:2013, implied) | Reported Device Performance |
|---|---|
| Blood Pressure Accuracy: Mean difference (device - reference) ≤ ±5 mmHg. Standard deviation of difference ≤ 8 mmHg. (These are the primary statistical requirements of the standard) | "The results demonstrated that BP4350 performed equivalently to the auscultation method and is in conformance with ANSI/AAMI/ISO 81060-2:2013." (Specific numerical results are not provided in this summary, but conformance implies meeting the standard's criteria). |
| Pulse Rate Accuracy: Within ±5% of reading (stated as a specification in comparison table) | "Accuracy of pulse rate is ±5% in both devices." (Implies the proposed device meets this). |
| Irregular Heartbeat Detection: The device detects and gives a warning signal when two or more heartbeat intervals differ by greater than 25% from the average heartbeat rhythm. | "The device detects the appearance of irregular heartbeats during measurement and gives a warning signal with readings." (Functionality confirmed, but specific performance metrics for this feature like sensitivity/specificity are not provided in this summary). |
| AHA/ACC Hypertension Indicator Threshold: "HIGH" indication if BP > 130/80 mmHg. | "a 'HIGH' indication appears if the blood pressure recorded is greater than 130/80 based on the AHA/ACC High Blood Pressure Clinical Practice Guideline criterion for Stage 1 Hypertension, published in 2017." (Functionality confirmed). |
2. Sample sized used for the test set and the data provenance
- Sample Size: The document does not explicitly state the exact sample size (number of subjects) used for the clinical investigation. ANSI/AAMI/ISO 81060-2:2013 typically requires a minimum of 85 subjects for full validation.
- Data Provenance: Not specified in the provided text (e.g., country of origin). The study was a "clinical investigation" which implies it was prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- The ground truth was established by "trained medical staff" using an "auscultation method" with a "calibrated sphygmomanometer."
- The exact number of experts and their specific qualifications (e.g., medical doctors, nurses, with how much experience) are not detailed in this summary. The ANSI/AAMI/ISO 81060-2:2013 standard often requires multiple observers to mitigate bias.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- The document does not specify any adjudication method for the clinical investigation results. For blood pressure validation, direct comparison to reference measurements from trained observers is the primary method, and the standard outlines protocols for this.
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, an MRMC study was not done. This study is for a blood pressure monitor, not an AI/ML-driven diagnostic device that relies on human readers interpreting images with or without AI assistance. The device directly measures blood pressure.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- This is a standalone device that provides direct blood pressure readings. Its performance is measured independently against a reference standard (auscultation). So, in a sense, its "standalone" performance is what was evaluated. There is no "human-in-the-loop" interaction in the measurement process itself that would alter the device's reading.
7. The type of ground truth used
- The ground truth was established by expert auscultation (manual blood pressure measurement by trained medical staff) using a calibrated sphygmomanometer. This is the gold standard for clinical validation of automated blood pressure devices.
8. The sample size for the training set
- Not applicable. This device is a traditional blood pressure monitor, not an AI/ML device that requires a "training set" in the machine learning sense. Its design and algorithm are based on established oscillometric principles and engineering, not on learning from a large dataset.
9. How the ground truth for the training set was established
- Not applicable. See point 8.
§ 870.1130 Noninvasive blood pressure measurement system.
(a)
Identification. A noninvasive blood pressure measurement system is a device that provides a signal from which systolic, diastolic, mean, or any combination of the three pressures can be derived through the use of tranducers placed on the surface of the body.(b)
Classification. Class II (performance standards).