(133 days)
Intended Use
The Soberlink Cellular Device is intended to quantitatively measure alcohol in human breath.
Indications for Use
Measurements obtained by this device are used in the diagnosis of alcohol intoxication.
For Prescription use and OTC use.
The Soberlink Cellular Device is a handheld breath alcohol measurement device with integrated GPS, digital imager, and cellular modem. It is designed to take a deep lung sample of the User's breath, calculate their Blood Alcohol Level (BAC), and send the BAC reading, physical location, and digital image of the User to the Sober Sky Web Portal and Device screen for review.
Here's an analysis of the acceptance criteria and study proving the device meets them, based on the provided text:
Device: Soberlink Cellular Device
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Accuracy: Measurement of Blood Alcohol Level (BAC) | An average difference of -0.0009 (SD = 0.0047) compared to a reference evidential breath alcohol tester (BACtrack S80 Pro). Regression analysis showed a non-significant difference of -0.001, with a level of agreement of ß = 0.987 and R2 = 0.974. |
| Precision/Reproducibility | Passed DOT Testing, which includes accuracy and repeatability. |
| Interfering Substances (e.g., cigarette smoke) | Passed all interference testing. |
| Environmental Performance (high/low ambient temperature) | Passed all temperature testing. |
| Air Blank Reading | Passed air blank reading testing. |
| Vibration Resistance | Passed all vibration testing. |
| Overall Design Requirements | Meets all requirements. |
| EMC Testing | Passed. |
| Electrical Safety | Passed. |
| Usability | Users can comprehend instructions for use and packaging without additional support to utilize the product correctly and safely, and produce a breath sample. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 43 participants
- Data Provenance: The document does not explicitly state the country of origin. The study was conducted by the sponsor (Soberlink Healthcare LLC, Huntington Beach, CA, USA), implying the study likely took place in the USA. The study appears to be prospective as it involved asking participants to consume alcohol and then use the device.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- The ground truth for the accuracy study was established using an "evidential breath alcohol tester (the BACtrack S80 Pro)." This is a reference device, not human experts.
- For the usability study, the ground truth was assessed by observing if "untrained study participants" could correctly use and interpret the device based on the supplied instructions. No specific number or qualifications of "experts" are mentioned for establishing ground truth in the usability study itself beyond the observed user behavior.
4. Adjudication Method for the Test Set
- For the accuracy study, the adjudication was by direct comparison to the reading of the BACtrack S80 Pro. No human adjudication method (like 2+1 or 3+1 by experts) was mentioned or implied for either the accuracy or usability studies.
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 or human-in-the-loop study was conducted or described in the provided text. This device is a standalone breath alcohol analyzer, not an AI-assisted diagnostic tool for human interpretation.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, the primary performance study (accuracy against the BACtrack S80 Pro) was implicitly a standalone performance assessment of the Soberlink Cellular Device. The device measures BAC and sends the reading, location, and image to a web portal for review, but the core measurement itself is standalone.
7. The Type of Ground Truth Used
- For the accuracy study, the ground truth was established by comparing the device's readings to those of a reference device/evidential breath alcohol tester (BACtrack S80 Pro).
- For precision/reproducibility and interference testing, the ground truth was established by conformance to DOT Testing standards (NHTSA Docket No. 2008-0030).
8. The Sample Size for the Training Set
- The document does not provide information about a "training set" as this device is a physical measurement device, not a machine learning/AI algorithm that typically undergoes a distinct training phase with a specific dataset.
9. How the Ground Truth for the Training Set Was Established
- Not applicable, as no training set for a machine learning model is mentioned. The device's calibration and design are based on established scientific principles of electrochemical fuel cell sensors for alcohol detection, calibrated against known standards.
§ 862.3050 Breath-alcohol test system.
(a)
Identification. A breath-alcohol test system is a device intened to measure alcohol in the human breath. Measurements obtained by this device are used in the diagnosis of alcohol intoxication.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9.