(74 days)
This device is intended to measure alcohol in human breath. Measurements obtained by this device are used in the diagnosis of alcohol intoxication.
The BACTRACK® Select Breathalyzer is an alcohol screening device, used for the detection of alcohol in the breath. The BACTRACK® provides a digital result, indicating the approximate BAC (Blood Alcohol Content) of the test subject. The BACTRACK® is powered by two AA batteries and is very easy to use. The device employs a fuel cell sensor of the same type commonly used in evidentiary breathalyzers. This results in generally better accuracy and longer battery life than silicon sensor units. The units are factory calibrated but the product should be recalibrated at least every six to twelve months. If the product is used every day, it may need to be recalibrated as frequently as every month.
The provided text describes the 510(k) premarket notification for the Bactrack® Select Breathalyzer Model S80. It primarily focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study report with specific acceptance criteria and comprehensive performance data.
However, based on the available information, I can extract the following:
1. Table of Acceptance Criteria and Reported Device Performance
The device claims to meet the performance of the predicate device, the AlcoHAWK PT500. Therefore, the predicate's performance serves as an implicit acceptance criterion.
| Feature | Acceptance Criteria (from Predicate Device) | Reported Device Performance (Bactrack® Select Breathalyzer: S80) |
|---|---|---|
| Accuracy | ± 0.01% BAC at 0.10% BAC | +/- 0.01 %BAC @ 0.02 %BAC |
| Blowing time | 5 Seconds | SAME (5 Seconds) |
| Response time | 3 Seconds | SAME (3 Seconds) |
| Measurement Range | 0.000% to 0.400% BAC | SAME (0.000% to 0.400% BAC) |
| Battery Life | 200 tests | Up to 1500 tests |
| Warm Up Time | 10-20 seconds | SAME (10-20 seconds) |
| DOT | DOT Approved | Meets DOT requirements |
Note on Accuracy: The accuracy specification for the Bactrack® Select Breathalyzer is shown as "C +/- 0.01 %BAC @ 0.02 %BAC" while the predicate's is "± 0.01% BAC at 0.10% BAC". This implies the Bactrack® specifies its accuracy at a lower BAC level (0.02% BAC) compared to the predicate (0.10% BAC) while maintaining the same absolute tolerance of ±0.01% BAC. Without further context or test results, it's difficult to directly compare these as equivalent or superior/inferior at all BAC levels. However, in the context of a 510(k), meeting or exceeding predicate performance is generally expected. The text states "few technological differences" and "as safe and effective," suggesting this difference in accuracy specification is considered acceptable for substantial equivalence.
2. Sample Size Used for the Test Set and the Data Provenance
The document mentions "clinical testing data" and a "clinical trial performed." However, no specific sample size (number of subjects or tests) for this clinical trial is provided.
The data provenance is not explicitly stated (e.g., country of origin). The submission is to the US FDA, so it's likely US-based, but this is an assumption. The data is prospective, as it describes a clinical trial that was "performed."
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 text only states that the clinical trial showed "obtain results that were comparable to those provided by a professional unit administered by a trained observer." It does not specify the qualifications of this "trained observer" or if multiple experts were involved in establishing ground truth for the device accuracy itself.
4. Adjudication Method for the Test Set
The document does not describe any specific adjudication method for the test set.
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
An MRMC comparative effectiveness study was not done. This device is a breathalyzer, not an AI-assisted diagnostic tool for human readers. The clinical trial focused on the ability of an "over the counter purchaser" to use the device and obtain comparable results to a "professional unit administered by a trained observer."
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, the primary evaluation of this device is in a standalone capacity. The device itself (the "algorithm only," in this context, referring to its measurement mechanism) is being assessed for its ability to accurately measure alcohol in breath. The clinical trial additionally assessed the human factor of the "over the counter purchaser" correctly using the device, but the core performance is the device's standalone measurement.
7. The Type of Ground Truth Used
The ground truth for the clinical trial appears to be established by comparison to "a professional unit administered by a trained observer." This implies a reference standard or a "gold standard" breathalyzer, likely a more sophisticated evidentiary or clinical device, against which the performance of the BACTRACK® Select Breathalyzer was compared.
8. The Sample Size for the Training Set
The document does not refer to a "training set." This type of device (a breathalyzer) typically undergoes calibration during manufacturing and recalibration at specified intervals, but it is not a machine learning or AI-driven system that would have a conventional "training set" in the context of data-driven algorithm development.
9. How the Ground Truth for the Training Set Was Established
As there is no mention of a "training set" in the context of algorithm development, this information is not applicable. The device is factory calibrated, and recalibration is recommended, implying a process of adjusting the device against known alcohol concentrations, but this isn't a "training set" in the AI sense.
§ 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.