(248 days)
The Health Check Kiosk is indicated for use by the general public so that a user can measure his/her own health parameters using devices cleared for use by the public. It is not a diagnostic device, and only furnishes data so that users can consult their personal physicians.
The Health Check Kiosk is a kiosk that is erected in public spaces, and provides a location where the general public can measure various health parameters. The Health Check kiosks are intended only to provide information, and are not for diagnostic use. No charge is made for use of the kiosk, but advertising may be posted inside of it. It is planned to locate the kiosk in non-medical settings such as gyms, corporate offices and retail stores.
The Xperex Inc. Health Check Kiosk 510(k) submission does not provide the detailed information requested regarding acceptance criteria and a study to prove the device meets these criteria in the typical format expected for a comprehensive medical device evaluation. Instead, it relies on a declaration of substantial equivalence to predicate devices.
Here's an analysis of the provided text in relation to your questions, highlighting what is present and what is absent:
Analysis of Acceptance Criteria and Proving Study
The submission states:
- "Health Check Kiosk has been extensively validated by itself and in conjunction with the associated measurement devices."
- "Clinical tests are not necessary, since the Health Check Kiosk uses the same technology as the predicate devices."
- "The Health Check Kiosk is equivalent in safety and efficacy to the legally-marketed predicate devices."
This indicates that the primary "acceptance criterion" for this submission was substantial equivalence to predicate devices, rather than a specific set of performance metrics demonstrated through a novel study. The "study" proving this is implicitly the comparison to predicate devices and the assertion that the underlying technology is the same.
Therefore, many of your specific questions cannot be answered directly from the provided text, as the method of validation was comparison to existing devices, not a standalone performance study with established primary and secondary endpoints and corresponding acceptance criteria.
Response to Specific Questions:
-
A table of acceptance criteria and the reported device performance:
- Acceptance Criteria: The implicit acceptance criterion is "substantial equivalence in safety and efficacy to legally-marketed predicate devices," specifically those listed (Lifeclinic International, K040562; Advanced Monitoring Caregiving, K051544; Remote Nurse, K041308). There are no explicit quantitative performance acceptance criteria defined in this document for the new device itself (e.g., accuracy +/- X mmHg for blood pressure).
- Reported Device Performance: The document states that the "Health Check Kiosk has been extensively validated by itself and in conjunction with the associated measurement devices." However, it does not provide specific performance data (e.g., accuracy, precision, sensitivity, specificity) in a quantitative manner. The performance is inferred to be similar to the predicate devices due to shared technology.
-
Sample size used for the test set and the data provenance: Not applicable. No specific "test set" (in terms of a patient cohort for performance evaluation) is described, as the validation relied on substantial equivalence and "non-clinical tests" not detailed here rather than a de novo clinical performance study.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. No ground truth establishment by experts for a test set is described.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. No test set requiring expert adjudication is described.
-
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: Not applicable. This device is a kiosk for measuring health parameters, not an AI-assisted diagnostic tool that would involve human readers or MRMC studies.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The "non-clinical tests" and "extensive validation by itself" could be interpreted as standalone performance assessment, but no details of such a study (methods, results, metrics) are provided. The explicit statement that "Clinical tests are not necessary" further indicates that rigorous human-in-the-loop or standalone clinical performance studies were not performed or required for this 510(k).
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable. No ground truth is established for the device's performance, as its equivalence to predicate devices (which presumably had established ground truth in their own filings) is the basis of clearance.
-
The sample size for the training set: Not applicable. This is not an AI/ML device that requires a training set in the typical sense.
-
How the ground truth for the training set was established: Not applicable.
In summary, the 510(k) submission for the Xperex Health Check Kiosk indicates that its acceptance was based on its substantial equivalence to already cleared predicate devices, asserting that it uses the same technology and therefore does not require new clinical performance data to demonstrate safety and efficacy. Consequently, the detailed information about acceptance criteria, study design, sample sizes, and ground truth establishment (as typically applied to novel performance studies) is not present in this document.
§ 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).