(15 days)
Measuring systolic and diastolic blood pressure and pulse rate in adult patients (18 years Mcasuring Systeme and Charlerse office. The arm circumference should be between 5.1" and 17.7" (13 cm to 45 cm).
Not Found
This FDA premarket notification (510(k)) filing for the LifeSource Models UA-787, UA-787PC, and UA-787T Digital Blood Pressure Monitors does not include detailed information about specific acceptance criteria, a comprehensive study report, or the methodology for establishing ground truth as typically requested for AI/ML device evaluations.
The document primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device under the 510(k) pathway, rather than providing a detailed technical performance study against pre-defined acceptance criteria with specific statistical measures.
Therefore, many of the requested details cannot be extracted directly from the provided text. However, based on the nature of a blood pressure monitor and standard validation practices, we can infer some general information or state that the specific details are not provided.
Here's an attempt to answer the questions based on the available information and general knowledge of medical device approvals:
1. A table of acceptance criteria and the reported device performance
- Acceptance Criteria: Not explicitly stated in the provided text. For a blood pressure monitor, typical performance acceptance criteria would relate to accuracy (e.g., standard deviation of difference, mean difference) and precision when compared to a reference measurement method (e.g., auscultatory method). Standards like ISO 81060-2 are commonly used for validating automated sphygmomanometers.
- Reported Device Performance: Not explicitly detailed in the provided text. The document states the device measures "systolic and diastolic blood pressure and pulse rate." Performance data, such as accuracy statistics (mean difference, standard deviation), are not provided.
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: Not specified in the provided text. Clinical validation studies for blood pressure monitors typically involve a specific number of subjects (e.g., AAMI/ISO standards recommend at least 85 subjects).
- Data Provenance: Not specified in the provided text. It's highly likely such studies would be prospective clinical trials.
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)
- Ground Truth Experts: Not specified. For blood pressure monitors, the "ground truth" is typically established by trained human observers using the auscultatory method with a mercury sphygmomanometer, often performed by at least two independent observers. Their qualifications would typically involve specific training in blood pressure measurement according to relevant clinical standards.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
- Adjudication Method: Not specified. If multiple human observers are used for ground truth, an adjudication method (e.g., averaging, or a third expert if discrepancies arise) would typically be employed.
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 is not applicable as this is a standalone blood pressure monitor, not an AI-assisted diagnostic tool for human readers. This device does not involve "human readers" in the context of interpretation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Yes, this is inherently a "standalone" device. Its performance is the algorithm's performance (i.e., the device's measurement) compared to a reference method. The document implicitly supports that a standalone performance evaluation was conducted as part of the substantial equivalence claim, but the details of that evaluation are not provided here.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Type of Ground Truth: Inferred to be a comparison to a reference measurement method, most commonly the auscultatory method performed by trained human observers using a mercury sphygmomanometer, which could be considered a form of "expert measurement" or "expert consensus" on the reference values.
8. The sample size for the training set
- Training Set Sample Size: Not applicable/not specified. This device likely uses traditional algorithms and calibration procedures rather than AI/ML requiring a distinct "training set" in the context of machine learning. If it used statistical models, the data used for developing those models would not typically be called a "training set" in the same way as for deep learning.
9. How the ground truth for the training set was established
- Training Set Ground Truth: Not applicable/not specified, for the same reasons as #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).