(15 days)
The BRAEBON Medical Corporation MEDIPalm-20™ is intended for use in collecting, recording and disclaying physiological data from FDA-cleared sensors during studies in both a cinical and home environment and for transmitting this data to an electrically isolated FDA-cleared polysomnographic analysis station for analysis.
The MEDIPalm-20™ is a portable data recorder used to collect physiological signals for transfer to an FDA-cleared polysomnographic analysis station capable of reading European Data Format (.edf) files.
The MEDIPalm-20™ is a hand-held recording device capable of acquiring and storing physiological signals from FDA-cleared sensors and transmitting the physiological data to a computer through the Universal Serial Bus (USB) port.
The MEDIPalm-20™ records up to 16 channels of physiological signals: any combination of eight differential analog channels of electroencephalogram (EEG), electronyogram (EOG), electrocardiogram (EMG), and electrocardiogram (EKG) signals; as well as chest effort; abdominal effort; airflow pressure; snoring; body position; arterial oxygen saturation (SaO2); pulse rate; and SaO2 probe status. The signals can be viewed in real time on a built-in LCD or on a remote computer. The data can be downloaded after collection for analysis on any FDA-deared polysomnographic analysis station capable of reading European Data Formatted files.
The provided text is a 510(k) summary for the BRAEBON Medical Corporation MEDIPalm-20™ device. This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving novel efficacy through extensive clinical trials. Therefore, the details requested about acceptance criteria for device performance, ground truth establishment, expert adjudication, and comparative effectiveness studies as typically found in AI/ML device submissions are largely not applicable in this context.
However, I can extract the information that is present concerning performance testing and equivalence.
1. Table of Acceptance Criteria and Reported Device Performance:
The document states that functional testing was performed to confirm the MEDIPalm-20™ meets its stated performance specifications. However, specific quantitative acceptance criteria (e.g., accuracy percentages, sensitivity/specificity thresholds) and their corresponding reported device performance values are not detailed in this 510(k) summary. The document only states:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Meet stated performance specifications | "MEDIPalm-20™ passed all tests." |
| Device output is readable | "MEDIPalm-20™ passed all tests." |
| Software testing in accordance with May 29, 1998 "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" | "The MEDIPalm-20™ passed all tests." |
| Software verification and validation in accordance with January 11, 2002 "General Principles of Software Validation; Final Guidance for Industry and FDA Staff" | "The MEDIPalm-20™ passed all tests." |
| Environmental and electrical safety testing in accordance with November [date omitted in text] "Guidance for 510(k) Content" | "The MEDIPalm-20™ passed all tests." |
| Comparative performance with predicate device (Sandman Digital Recording System) | "Performance of the BRAEBON Medical Corporation MEDIPalm-20™ (subject device) was identical to that of Sandman Digital Recording System (predicate device)." |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size:
- For the verification that signals were readable and appropriate: "a healthy person" (i.e., n=1).
- For simulation tests comparing with the predicate device: Not specified, but implied to be a simulation environment rather than patient data.
- Data Provenance: Not explicitly stated, but the tests were performed by the manufacturer, BRAEBON Medical Corporation (located in Canada, as per the address, though the submission is to the US FDA). The nature of the tests (connecting to "a healthy person" and "simulation tests") suggests internal validation rather than a clinical trial with sourced patient data. These appear to be prospective tests performed specifically for this submission.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
Not applicable. The document does not describe the establishment of "ground truth" in the context of diagnostic accuracy or expert consensus. The testing focused on functional performance, software compliance, electrical safety, and signal readability, not on diagnostic outcomes requiring expert interpretation against a gold standard.
4. Adjudication Method for the Test Set:
Not applicable. Since there was no "ground truth" establishment in the sense of diagnostic labels requiring expert consensus, no adjudication method was used.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, and Effect Size:
No. A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The submission explicitly states: "No clinical studies were required to support a substantial equivalence determination." This device is a data acquisition system, not an AI diagnostic tool, so such studies are generally not relevant for this type of 510(k).
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Study was Done:
Yes, in spirit. The performance tests described (functional, software, electrical safety, simulation tests) are essentially "standalone" evaluations of the device's ability to acquire and output data correctly, independent of a human interpreter's diagnostic capabilities. The comparison showing "identical" performance to the Sandman Digital Recording System in simulation tests is also a standalone evaluation of the device's technical output.
7. The Type of Ground Truth Used:
The "ground truth" for this device's performance was its own stated performance specifications and the output of a predicate device (Sandman Digital Recording System) for comparative testing, rather than a clinical ground truth like pathology or patient outcomes. For signal readability, the ground truth was simply whether the signals produced were "readable, appropriate signals."
8. The Sample Size for the Training Set:
Not applicable. This device is an electroencephalograph/polysomnograph data acquisition system, not a machine learning model that requires a training set.
9. How the Ground Truth for the Training Set Was Established:
Not applicable. As stated above, this device does not utilize a training set in the context of machine learning.
§ 882.1400 Electroencephalograph.
(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).