(265 days)
This device is a digital monitor intended for use in measuring blood pressure(SYS and DIA) and pulse rate ,and the physician reference the result to diagnose. Environments of use: Hospital and other medical establishment. Patient population: Adult (exclude pregnant women ).
Clinical Automatic blood pressure monitor have two models that are DBP-01HP and DBP-01P,The Clinical Automatic blood pressure monitor is used to measure the blood pressure of adult in hospital or other medical establishment. It's contain of main body , power wire.it can show the time and measure result, print the measure result .There is a difference between DBP-01HP with DBP -01P. DBP-01HP show the measure result and time by the LCD screen,DBP-01P show the measure result and time by the LED screen.
This document is a 510(k) premarket notification for a Class II medical device, the "Clinical Automatic Blood Pressure Monitor (DBP-01P, DBP-01HP)," manufactured by Shenzhen Hingmed Medical Instrument Co., Ltd. The document primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device (UA-1200BLE Ultraconnect Digital Blood Pressure) to secure FDA clearance.
The information provided does not include detailed acceptance criteria and a study proving the device meets those criteria in the way typically expected for an AI/ML medical device, as the filing is for a traditional, non-AI medical device (a blood pressure monitor). Therefore, I will extract the closest equivalent information related to performance testing and "acceptance criteria" for this type of device, which is primarily based on established international standards for non-invasive sphygmomanometers.
Here's an interpretation of the request in the context of the provided document:
1. A table of acceptance criteria and the reported device performance
The relevant "acceptance criteria" for a blood pressure monitor are its accuracy specifications, as defined by international standards.
| Acceptance Criteria (from ISO 81060-2:2018) | Reported Device Performance (DBP-01P) | Metric |
|---|---|---|
| Criterion 1: Mean device-observer difference ≤ ±5 mmHg with SD ≤ 8 mmHg | 1.32 mmHg (for SBP), 0.78 mmHg (for DBP) | Mean Device-Observer Difference |
| Criterion 1: Standard Deviation (SD) of device-observer difference ≤ 8 mmHg | 3.18 mmHg (for SBP), 3.15 mmHg (for DBP) | SD of Device-Observer Difference |
| Criterion 2: SD of the 85 participants being below the maximum values required by the protocol | 6.80 mmHg (for SBP), 6.89 mmHg (for DBP) | SD Across Participants |
| Manufacturer's Stated Performance (General) | Pressure: Within ± 3 mmHg | Measurement Accuracy (Pressure) |
| Manufacturer's Stated Performance (General) | Pulse Rate: Whichever is greater (± 3 bpm or ± 3%) | Measurement Accuracy (Pulse Rate) |
Note: The document references ISO 81060-2:2018, which has two main criteria for accuracy. Criterion 1 (Mean and SD of device-observer difference) and Criterion 2 (SD of the differences for all subjects). The reported performance satisfies both.
2. Sample size used for the test set and the data provenance
- Sample Size for Test Set: 85 subjects.
- Data Provenance: The document states the study was a "clinical investigation" and does not specify a country of origin for the patients, but given the manufacturer's location (Shenzhen, China), it can be inferred the study likely took place in China. It was a prospective study conducted for the purpose of validating the device.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
For a blood pressure monitor, the "ground truth" is typically established by trained observers (human auscultatory method) using a reference sphygmomanometer. The document does not specify the exact number, training, or qualifications of the observers, but adherence to ISO 81060-2 standards implies that qualified personnel performed these measurements.
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" in the sense of expert consensus for classification. For blood pressure validation, the comparison is typically between the automated device readings and simultaneous auscultatory measurements by human observers. Discrepancies are handled according to the specific methodology described in ISO 81060-2, which involves multiple readings and specific statistical analysis, rather than an "adjudication" in the AI sense.
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
- MRMC Study: No, an MRMC study was not done.
- AI Assistance: This device is a traditional blood pressure monitor and does not incorporate AI. Therefore, there is no AI assistance to measure improvement in human readers. The clinical validation method directly assesses the device's accuracy against a known standard, not against human performance or human-AI collaboration.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, in a sense, the primary clinical validation described is a "standalone" performance assessment of the device's measurement accuracy. The device's measurement (algorithm's output) is compared directly to the gold standard (human auscultatory readings). The human "in the loop" here is the observer performing the reference measurement, not interacting with AI.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth used was simultaneous auscultatory measurements performed by trained human observers using a reference sphygmomanometer, in accordance with the ISO 81060-2 standard. This is considered the expert-derived reference standard for non-invasive blood pressure.
8. The sample size for the training set
This document describes the validation of a traditional medical device (blood pressure monitor), not an AI/ML algorithm. Therefore, there is no "training set" in the context of machine learning. The device's design is based on established oscillometric principles, not on learned data.
9. How the ground truth for the training set was established
As there is no "training set" for an AI/ML algorithm, this question is not applicable to the submitted device.
§ 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).