(121 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 AlcoHAWK® PT500 is designed to measure deep lung air to test for the presence of alcohol in the blood. The relationship between alcohol in the blood and alcohol in the deep lung breath is well established by Henry's law in ratio of 2100:1 The AlcoHAWK® PT500 has been tested and uses a blow time of 5 seconds to capture an accurate deep lung sample. The AlcoHAWK® PT500 sensor uses a fuel cell type of detector similar to one found on professional units. It is handheld and uses two AA alkaline batteries as a power source. The mouthpiece is replaceable Plexiglas plastic.
Here's a breakdown of the acceptance criteria and study information for the AlcoHAWK® PT500 Digital Alcohol Detector, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Measurement Range | .00-.40% |
| Accuracy | +/-0.01% |
| Blowing time | 5 seconds |
| Warm-Up Time | 10 Seconds |
| DOT Approval | DOT Approved |
Study Information
The provided document describes a "clinical trial" but does not detail it with the same rigor one might expect for a modern AI/device study. The focus is primarily on demonstrating substantial equivalence to a predicate device and user comprehension/usability.
-
Sample sized used for the test set and the data provenance:
- Sample Size: Not explicitly stated for the "clinical trial." The document mentions "user testing data" and "a clinical trial was performed," but does not provide a number of participants or samples.
- Data Provenance: Not explicitly stated. Given the context of a 510(k) summary for a US market device, it is implied to be relevant to a US population, but no specific country of origin is mentioned. It's described as a "clinical trial," suggesting prospective data collection, but details are absent.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated. The study aimed to show "results that were comparable to those provided by a professional unit administered by a trained observer." This implies one or more "trained observers" were involved, but their qualifications are not detailed beyond "trained observer."
- Qualifications of Experts: Only "trained observer" is mentioned for the professional unit's administration. No specific years of experience or professional titles (e.g., toxicologist, law enforcement officer) are given.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not explicitly stated. The comparison was against a "professional unit administered by a trained observer," implying a direct comparison rather than a multi-reader adjudication process for ground truth.
-
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, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed. This device is a standalone breath alcohol detector, not an AI-assisted diagnostic tool that would typically involve human "readers" or "interpreters" whose performance is analyzed.
-
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, the "clinical trial" assessed the standalone performance of the AlcoHAWK® PT500 in the hands of an "over the counter purchaser" (human-in-the-loop, but measuring the device's output) and compared it to a "professional unit administered by a trained observer." The primary goal was to show the device itself provides comparable results and that users can operate it correctly. The device's measurement function is algorithmic/automated once the breath sample is provided.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth was established by a "professional unit administered by a trained observer." This implies that the readings from a "professional unit" (likely an evidentiary-type breath alcohol tester) served as the reference standard against which the AlcoHAWK® PT500's readings were compared.
-
The sample size for the training set:
- Not applicable/Not mentioned. This device is a measurement device, not an AI or machine learning algorithm that typically requires a distinct training set. Its function is based on a fuel cell sensor and established physiological principles (Henry's law), not trained data.
-
How the ground truth for the training set was established:
- Not applicable. As noted above, there is no mention of a training set for an AI/ML algorithm.
§ 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.