(242 days)
The AeviceMD is a non-invasive battery-operated device, including a wearable component, intended to longitudinally acquire, record and store lung sounds from adult patients in a clinical setting. The device stores the data for later playback, review, and analysis by a clinician and comparison with earlier data from the same patient.
The AeviceMD is designed as an electronic stethoscope to acquire and record lung sounds from users for healthcare professionals (HCP) to playback and interpret the sounds recorded. AeviceMD does not contain any alarm feature and it is not intended for emergency use. It is also not a sleep apnea device. The device is not intended for self-diagnosis.
The AeviceMD consists of hardware and embedded software. It is a five-part system that includes the following components:
-
AeviceMD Sensor – an embedded electronic wearable device that detects and records lung sounds and transmits data to an electronic gateway via Bluetooth.
-
AeviceMD Silicone Patch - silicone patch that houses and attaches the Sensor to the user's body (i.e., chest). This silicone patch undergoes biocompatibility testings which allow AeviceMD Sensor to be worn on the skin.
-
AeviceMD Docking Station - gateway device that serves as a computational hub and linkage from the Sensor to the Cloud Platform, and as a charqer for the Sensor.
-
AeviceMD App (for patients) / AeviceMD HCP Web App (for healthcare professionals in a clinical setting) - The AeviceMD App is a mobile app that downloads the post-processed information from the Cloud Platform and presents users with their recorded lung sounds at the auscultation locations which they can share with their HCP during their next consultation. A separate app, AeviceMD HCP Web App is tailored for HCP to review their patient's data in a clinical setting.
-
AeviceMD Cloud Platform – secure cloud server that receives data from gateway units and analyzes user's data using meaningful output information.
The AeviceMD is a non-invasive, battery-operated device intended to acquire, record, and store lung sounds from adult patients for later review and analysis by a clinician.
Here's an analysis of the acceptance criteria and the study that proves the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document details non-clinical performance tests but does not explicitly state specific quantitative acceptance criteria or corresponding reported device performance values in a table format for the device's primary function of acquiring and recording lung sounds.
However, based on the non-clinical performance data section, the device likely aims to perform "as well as" a legally marketed predicate device, implying equivalence in its core function. The "Stethoscope Performance Test against a 510(k) cleared reference stethoscope" suggests that the AeviceMD's acoustic performance was compared to an already cleared device.
Implicit Acceptance Criteria (inferred from the document):
| Acceptance Criteria Category | Description (Inferred) | Reported Device Performance (Inferred) |
|---|---|---|
| Acoustic Performance | Functional equivalence to a 510(k) cleared reference stethoscope in recording and acquiring lung sounds. Frequency range similar to predicate/reference devices. | "The subject device performs as well as the legally marketed predicate device and is substantially equivalent." "All three devices have the same frequency range and can connect to mobile applications for recording and sharing data with HCP." (This implies the AeviceMD's frequency response is acceptable and comparable to cleared devices). A "Non-clinical Frequency Response Test" and "Stethoscope Performance Test against a 510(k) cleared reference stethoscope" were performed. |
| Biocompatibility | Silicone patch does not cause adverse biological reactions. | Biocompatibility testing was performed on the AeviceMD Silicone Patch (ISO 10993-5:2009 for in vitro cytotoxity, ISO 10993-10:2010 for irritation and skin sensitization). Results are implied to be acceptable as part of the overall conclusion of substantial equivalence. |
| Electrical Safety (Basic & Essential Performance) | Compliance with general requirements for basic safety and essential performance of medical electrical equipment. | Compliance with IEC 60601-1:2005+A1:2012 (or 2012 reprint). Results are implied to be acceptable. |
| Electromagnetic Compatibility (EMC) | Compliance with electromagnetic disturbance requirements. | Compliance with EN 60601-1-2:2015. Results are implied to be acceptable. |
| Usability | Device is safe and effective for users in the intended environments. | Compliance with IEC 60601-1-6:2010 and ANSI AAMI IEC 62366-1:2015+AMD1:2020. Human Factors Usability testing was performed. Results are implied to be acceptable. |
| Software Life Cycle Processes | Software development and maintenance meet medical device standards. | Compliance with ANSI AAMI IEC 62304:2006/A1:2016. Results are implied to be acceptable. |
| Risk Management | Risks associated with the device are identified and managed. | Compliance with ISO 14971:2019. Results are implied to be acceptable. |
| Shipping Validation | Device maintains integrity and functionality during shipping. | Shipping Validation Test according to ASTM D4169-16 was performed. Results are implied to be acceptable. |
| Cleaning Validation | Device can be effectively cleaned without compromising safety or performance. | Cleaning Validation Testing was performed. Results are implied to be acceptable. |
2. Sample size used for the test set and the data provenance
The document does not specify the sample size for any "test set" in the context of clinical or performance data for lung sound acquisition accuracy. The studies mentioned are primarily non-clinical validation tests (e.g., biocompatibility, electrical safety, usability, software, shipping, cleaning, frequency response, stethoscope performance comparison). These typically involve specific test conditions and components rather than human subject data sets in the way an AI algorithm test set would.
For the "Stethoscope Performance Test against a 510(k) cleared reference stethoscope", the exact number of data points or recordings used for comparison is not provided.
The data provenance for these non-clinical tests is not explicitly stated in terms of country of origin but would generally originate from the manufacturer's testing facilities or accredited third-party labs carrying out these standardized tests. The studies are described as "non-clinical performance data," implying laboratory or engineering testing rather than retrospective or prospective clinical human studies to evaluate diagnostic performance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided in the document. The document describes a device for acquiring, recording, and storing lung sounds for later playback, review, and analysis by a clinician. It does not mention any automated interpretation or diagnostic capabilities that would necessitate a ground truth established by experts interpreting sounds. Therefore, there's no mention of experts establishing a ground truth for diagnostic accuracy for the device itself.
4. Adjudication method for the test set
Not applicable, as no expert-adjudicated test set for diagnostic performance is 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 MRMC study is mentioned. The device's indications for use emphasize acquisition, recording, storage, playback, and review by a clinician, not AI-assisted interpretation or diagnosis. There is no mention of AI features intended to improve human reader performance.
6. If a standalone (i.e. algorithm only, without human-in-the-loop performance) was done
No standalone algorithm performance study is mentioned. The device is a "Medical Magnetic Tape Recorder" and "Stethoscope, Electronic" intended for clinicians to interpret the recorded sounds, not for an algorithm to provide a standalone diagnosis. The device's cloud platform "analyzes user's data using meaningful output information," but the nature of this "meaningful output" is not specified to be diagnostic or requiring standalone performance evaluation in the context of this 510(k) summary.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not applicable, as the device doesn't have a stated diagnostic function that requires ground truth for clinical accuracy. The "Stethoscope Performance Test" would likely use a reference cleared stethoscope as its "ground truth" for acoustic fidelity, rather than clinical ground truth like pathology or expert consensus on a diagnosis.
8. The sample size for the training set
Not applicable. The document does not describe the development or evaluation of a machine learning algorithm for diagnostic purposes that would require a "training set." The "AeviceMD Cloud Platform" is mentioned to "analyze user's data using meaningful output information," but the details of this analysis, particularly if it involves machine learning and a corresponding training set, are not provided or assessed in this 510(k) summary for substantial equivalence.
9. How the ground truth for the training set was established
Not applicable, as no training set for a diagnostic algorithm is mentioned.
§ 870.2800 Medical magnetic tape recorder.
(a)
Identification. A medical magnetic tape recorder is a device used to record and play back signals from, for example, physiological amplifiers, signal conditioners, or computers.(b)
Classification. Class II (performance standards).