(128 days)
HL158VA automatically measures human's Systolic, Diastolic blood pressure and heart rate by using the oscillometric method during inflation. All values can be read out in one LCD panel. Measurement position is at human being's wrist. The intended use of this over the counter device is for adults aged 18 years and older with wrist circumference ranging from 5.3 inches to 7.7 inches (approx. 135 mm to 195 mm) and for home use.
HLI S8VA detects the appearance of irregular heartbeats during measurement; an indicated symbol will appear with measuring reading. And the Risk Category Indicator will show the information with the readings on the screen for the user tracking their blood pressure level.
Besides, the device features a built-in "Bluetooth Data Transmission" function, which enables the device automatically transmit measuring results to paired Bluetooth-enabled device. Also, users could simply synchronize the current date and time, and check the battery status of blood pressure monitor by means of DailyChek® application software with the paired Bluetooth-enabled device.
HL158VA automatically measures human's Systolic, Diastolic blood pressure and heart rate by using the oscillometric method during inflation. All values can be read out in one LCD panel. Measurement position is at human being's wrist. The intended use of this over-the-counter device is for adults aged 18 years and older with arm circumference ranging from 5.3 inches to 7.7 inches (approx.13.5 cm to 19.5 cm) and for home use.
The device will display a symbol wor or to indicate the detection of irregular heartbeat rhythm as defined as a rhythm is more than or less than 25% from the average heartbeat intervals during the measurement. Additionally, after measurement, the Risk Category Indicator function will show the information with the readings on the screen for the user tracking their blood pressure level.
Besides, HL158VA has a built-in Wrist Position Guide. By holding START/STOP button, the display will illuminate with different icons that are designed to guide you move your wrist. Furthermore, the user can use the Bluetooth Data Transmission function, which provides users an optional choice to log, track and store their measurement data. Also synchronize the current date and time, and check the battery status of blood pressure monitor by means of DailyChek® application software with the paired Bluetooth-enabled device.
The document discusses the Food and Drug Administration's (FDA) review of the Full Automatic (NIBP) Blood Pressure Monitor, Model HL158VA. It determined the device to be substantially equivalent to previously marketed predicate devices.
Here's an analysis of the acceptance criteria and the study proving the device meets them:
1. A table of acceptance criteria and the reported device performance
The primary clinical performance acceptance criteria for the blood pressure monitor are related to its accuracy, as per ISO 81060-2.
| Acceptance Criteria (from ISO 81060-2:2013) | Reported Device Performance (HL158VA) |
|---|---|
| Mean difference limits for blood pressure measurements | Fulfilled (results of clinical investigation) |
| Standard deviation limits for blood pressure measurements | Fulfilled (results of clinical investigation) |
| Pressure Accuracy: ± 3mmHg | Achieved |
| Pulse Accuracy: ± 5% | Achieved |
Additional Technical Specifications:
| Feature | Predicate Device (HL158BT, K093824) | Subject Device (HL158VA) | Acceptance/Performance |
|---|---|---|---|
| Method of Measurement | Oscillometric | Oscillometric | Same as predicate, accepted |
| Measurement Type | During deflation | During inflation | Modified, but validated clinically |
| Range of measurement (Pressure) | 0~300 mmHg | Rated Range of Cuff Pressure: 0 | Accepted |
| Range of measurement (Pulse) | 40~199 Beats/minute | 40~199 Beats/minute | Same as predicate, accepted |
| Inflation | Automatic | Automatic | Same as predicate, accepted |
| Deflation | Automatic (Rapid Exhaust Valve) | Automatic (Passive Exhaust Valve) | Modified, but presumably validated |
| Pressure Changed Rate | 2-5 mmHg/sec. (from 150mmHg to 90mmHg) | 2-5 mmHg/sec. (from 90mmHg to 150mmHg) | Modified, but acceptable. |
| Display | Liquid Crystal Digital | Liquid Crystal Digital | Same as predicate, accepted |
| Memory | 2*60, total 120 | 2*120, total 240 | Improved, accepted |
| Number of Push Button | 7 keys | 6 keys | Modified, accepted |
| Cuff size (Wrist circumference) | 135 ~ 195 mm (5.3~7.7 inches) | 135 ~ 195 mm (5.3~7.7 inches) | Same as predicate, accepted |
| Risk Category Indicator | Yes | Yes | Same as predicate, accepted |
| Irregular Heartbeat Detector | Yes | Yes | Same as predicate, accepted |
| Data Link Function | Yes (Via USB cable) | Yes (Via Bluetooth) | Modified, validated non-clinically |
| Talking Function | Yes | No | Removed, accepted |
| Wrist Position Guide | No | Yes | Added, validated |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size: A "group of 100 subjects" was used for the clinical investigation.
- Data Provenance: The document does not specify the country of origin. The study was a prospective clinical investigation, designed to evaluate the device against a known standard.
3. 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)
The document does not provide details on the number or qualifications of experts used to establish the "ground truth" (reference blood pressure measurements). In ISO 81060-2 clinical validation, this typically involves trained observers taking auscultatory measurements using a mercury sphygmomanometer in a standardized manner.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not explicitly describe an adjudication method for the test set. For ISO 81060-2 clinical validation, measurements from multiple trained observers are often compared to minimize individual observer bias, but a formal "adjudication" in the sense of resolving discrepancies is not typically described in summary documents like 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
A multi-reader multi-case (MRMC) comparative effectiveness study was not performed, nor is it applicable to this device. This device is a standalone blood pressure monitor and does not involve human readers analyzing medical images with or without AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a standalone performance evaluation was conducted. The clinical investigation directly evaluated the accuracy of the device (HL158VA) against the ISO 81060-2 standard, which assesses the device's ability to measure blood pressure without human intervention influencing the measurement itself (though a human operates the device).
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth for the clinical validation was based on reference blood pressure measurements taken by trained observers, as specified by the requirements of the ISO 81060-2 standard for non-invasive sphygmomanometers. This is a form of "expert measurement" or "reference method."
8. The sample size for the training set
The document does not mention a training set sample size. For medical devices like this, which measure physiological parameters using established principles (oscillometric method), a "training set" in the machine learning sense is not typically used or reported for regulatory submissions; rather, the device's algorithms are developed and then validated through clinical studies.
9. How the ground truth for the training set was established
As no training set (in the machine learning sense) is mentioned, there's no information on how its ground truth was established. The device's underlying algorithm is based on the well-established oscillometric method, and its accuracy is validated directly on a test set (the 100 subjects) rather than through a separate training/validation split typical of AI systems.
§ 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).