(535 days)
The Wrist Type Blood Pressure Monitor is intended to measure the systolic and diastolic blood pressure as well as the pulse rate of adult person via non-invasive oscillometric technique in which an inflatable cuff is wrapped around the Wrist. It can be used at medical facilities or at home. The cuff size is 310 mm x 75 mm, and the intended wrist circumference is 13.5 - 19.5 cm.
The proposed device, Wrist Type Blood Pressure Monitor, is a battery driven automatic non-invasive blood pressure monitor. The Wrist Type Blood Pressure Monitor can automatically complete the inflation, deflation and measurement of systolic and diastolic blood pressure as well as the pulse rate of adult person. User can set different user ID for data storage, which can be set as two independent groups of measured blood pressure data; User can set the time as year, month, day, hour and minute; User can enable or disable the function of voice broadcast about measurement result; User can select the unit of the measurement: mmHg or KPa; The device has the data storage function for data reviewing, including the data of systolic pressure. diastolic pressure, pulse rate and measurement time. The device has low power indicator to indicate the states of low batteries power.
The provided document is a 510(k) premarket notification for a Wrist Type Blood Pressure Monitor (K162616). This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving stand-alone safety and effectiveness through extensive, detailed clinical trials with the rigor typically seen for novel devices.
Therefore, the information available is primarily related to demonstrating equivalence to the predicate device, particularly regarding adherence to relevant performance standards for blood pressure monitors. It does not contain the granular detail about acceptance criteria, test set characteristics, expert qualifications, or multi-reader studies that would be present in a submission for a novel AI device with complex image analysis or diagnostic capabilities.
Here's an attempt to extract and interpret the information based on the provided document, addressing the requested points. Please note that many points cannot be fully answered due to the nature and scope of this 510(k) submission for a blood pressure monitor.
Acceptance Criteria and Device Performance (as demonstrated for a blood pressure monitor)
The primary acceptance criteria for a blood pressure monitor, as indicated by compliance with ISO 81060-2:2013, relate to the accuracy of blood pressure measurements.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (from ISO 81060-2:2013) | Reported Device Performance (YK-BPW1) |
|---|---|
| Blood Pressure Accuracy within ±5 mmHg (Mean difference and standard deviation requirements per ISO 81060-2:2013, though specific statistical values are not detailed in this summary beyond the general ±5mmHg statement). | "The results shown that the accuracy of proposed device meet the requirements of ISO 81060-2:2013 within the ±5mmHg." (Page 6) |
Note: Table 2 shows a general "BP Accuracy: ±3 mmHg" which typically refers to the device's inherent precision, not the clinical validation results against a gold standard as per ISO 81060-2. The clinical conclusion on page 6 is more relevant for the acceptance criteria. |
| Pulse Rate (PR) Accuracy (not explicitly detailed in acceptance criteria, but measured) | PR Range: 40-199 bpm (Table 2) |
| Non-Clinical Test Compliance | IEC 60601-1:2012 (General safety)
IEC 60601-1-2:2007 (EMC)
ISO 80601-2-30:2013 (Specific for automated non-invasive sphygmomanometers)
ISO 10993-5:2009 (Biocompatibility - cytotoxicity)
ISO 10993-10:2010 (Biocompatibility - irritation/sensitization) (Page 5-6) |
| Substantial Equivalence to Predicate Device | Demonstrated through comparative tables for product code, regulation, class, intended use, application site, patient population, measurement items, principle, main components, BP/PR ranges, operation/storage conditions, data storage, performance standard, cuff size, power supply, voltage, electrical safety, EMC, biocompatibility, labeling, and software level of concern. (Pages 6-8) |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: "There were 150 subjects been selected to participate in the trial." (Page 6)
- Data Provenance: The document does not explicitly state the country of origin for the clinical trial data. It can be inferred that it was likely conducted in China, given the manufacturer's and submission correspondent's locations.
- Retrospective or Prospective: Not explicitly stated, but clinical validation studies for device accuracy are typically prospective to ensure controlled measurement conditions per the standard.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- The ground truth was established by "Auscultation... with the qualified calibrated mercurial sphygmomanometer used as control group." (Page 6).
- The document does not specify the number or qualifications of the individuals (experts or clinicians) who performed the auscultation measurements. For ISO 81060-2:2013, typically two independent observers (clinicians trained in auscultation) are required to take measurements.
4. Adjudication Method for the Test Set
- Not explicitly described. For ISO 81060-2:2013, the standard dictates how the reference measurements are obtained and compared, often involving simultaneous auscultation by multiple observers. An explicit adjudication method beyond this standard protocol is not mentioned.
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 comparative effectiveness study was not done. This type of study is relevant for AI-assisted diagnostic tools (e.g., in radiology) where human-in-the-loop performance is being evaluated. This device is a standalone measurement device (blood pressure monitor), not an AI-assisted diagnostic tool.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, the primary clinical validation was a standalone performance test of the device's accuracy. The device (Wrist Type Blood Pressure Monitor, YK-BPW1) operated autonomously to measure blood pressure, and its readings were compared against the established gold standard (auscultation). This is inherent to the type of device.
7. The Type of Ground Truth Used
- Clinical Measurements via Auscultation: The ground truth was established by human auscultation using a qualified calibrated mercurial sphygmomanometer (a medical standard for manual BP measurement). This represents expert consensus/clinical gold standard.
8. The Sample Size for the Training Set
- This document describes a clinical validation study and non-clinical tests for a medical device (blood pressure monitor), not a machine learning or AI algorithm in the sense of needing a distinct "training set." The device's underlying algorithm is pre-programmed based on known oscillometric principles. Therefore, there is no explicit "training set" sample size mentioned or implied for this type of device submission.
9. How the Ground Truth for the Training Set Was Established
- As there is no "training set" in the context of an AI algorithm being trained, this question is not applicable to the information provided for this blood pressure monitor. The device's design and internal algorithms are based on established biometric measurement principles.
§ 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).