Search Filters

Search Results

Found 2 results

510(k) Data Aggregation

    K Number
    K071067
    Manufacturer
    Date Cleared
    2007-09-14

    (151 days)

    Product Code
    Regulation Number
    862.3050
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K041334

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    This device is intended to measure alcohol in the human breath. Measurements obtained by this device are used as an aid in the detection of alcohol intoxication.

    Device Description

    The BACTRACK™ Breathalyzer 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 BACTRACK™ Breathalyzer is has been tested and uses a blow time of 5 seconds to capture an accurate deep lung sample. The BACTRACK™ Breathalyzer sensor uses tin dioxide which has n-type conductivity when exposed to the atmosphere. This exposure causes a decrease in the number of electrons effecting absorbed oxygen molecules and thus increases resistance. If a specific gas (reducing gas) is presented, a reaction occurs with the absorbed oxygen which causes an increase in the electrons in the oxide molecules causing a decrease in resistance. This change in resistance can be measured and used to identify a specific gas (such as alcohol) and can be quantified into a % concentration.

    AI/ML Overview

    The K071067 submission describes the BACTRACK™ Breathalyzer Digital Alcohol Detector.

    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

    FeatureAcceptance Criteria (Predicate Device K041334)Reported Device Performance (BACTRACK™ Breathalyzer)
    Measurement Range.00-.40%.00-.40%
    Accuracy+/-0.01%+/-0.01%

    2. Sample Size Used for the Test Set and Data Provenance

    The submission mentions "user testing data" and a "clinical trial" but does not specify the sample size for these tests.

    The data provenance is not explicitly stated as retrospective or prospective, nor is the country of origin mentioned. However, the nature of a "clinical trial" and "user testing" generally implies a prospective data collection, likely in the country where the manufacturer operates or seeks approval.

    3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

    The submission states that the clinical trial aimed to: "perform comparably to an evidentiary type of breath alcohol tester." and "obtain results that were comparable to those provided by a professional unit administered by a trained observer."

    This implies that the ground truth for the clinical trial was established by an "evidentiary type of breath alcohol tester" operated by a "trained observer." The number of such "observers" or "professional units" is not specified. The qualifications of these observers are limited to "trained," without further detail (e.g., years of experience, specific certifications).

    4. Adjudication Method for the Test Set

    The submission does not explicitly describe an adjudication method for the test set. The comparison appears to be directly against the "evidentiary type of breath alcohol tester" or "professional unit."

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Its Effect Size

    No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The study described focuses on comparing the BACTRACK™ Breathalyzer's performance against a "professional unit" and user's ability to operate the device, not on assessing multiple human readers or the effect of AI assistance.

    6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Study Was Done

    Yes, a standalone performance evaluation was done in the sense that the device's accuracy was assessed independently against a reference standard. The "bench tests" and the comparison of the BACTRACK™ Breathalyzer's readings to an "evidentiary type of breath alcohol tester" represent a standalone evaluation of the device's core functionality.

    7. The Type of Ground Truth Used

    The ground truth used for performance validation was the measurement from an "evidentiary type of breath alcohol tester" or "professional unit." This implies a reference standard that is generally accepted as accurate for breath alcohol measurement.

    8. The Sample Size for the Training Set

    The submission does not mention a training set or its sample size. The BACTRACK™ Breathalyzer uses a semiconductor-oxide sensor, which suggests a physical-chemical principle of operation rather than a machine learning algorithm that typically requires a training set.

    9. How the Ground Truth for the Training Set Was Established

    Since there is no mention of a training set for machine learning, there is no information provided on how ground truth for a training set was established.

    Ask a Question

    Ask a specific question about this device

    K Number
    K062545
    Date Cleared
    2007-04-09

    (222 days)

    Product Code
    Regulation Number
    862.3050
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K052448, K041334

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Intended to measure alcohol in human breath. Measurements obtained by this device are used in the detection of alcohol intoxication.

    Device Description

    The RMI® LCD Alcohol Tester 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 RMI® LCD Alcohol Tester is an alcohol screening device and uses a blowing time of 3 seconds to capture an accurate deep lung sample. The RMI® LCD Alcohol Tester contains a semiconductor sensor designed to test for the presence of alcohol. The semiconductor material is heated to a specific temperature. The resistance of sensing material changes rapidly according to gas concentration changes, thereby enabling the reading of alcohol concentration by resistance measurement. The device employs a 3 digit LCD display which shows breath alcohol readings from 0.00 to 0.20 BAC (Breath Alcohol Concentration). Readings above 0.20 will display an LCD reading of "HI." The new device is a MODIFICATION of our old device, the Connectables® Alcohol Tester (K052448). We use the same sensor, but instead of three colored LEDs as indicators, the new device has a three digit LCD display of the measured BAC (breath alcohol concentration). Instead of analog comparators, we now employ an 8 bit microprocessor for control and measurement.

    AI/ML Overview

    The provided text is a 510(k) summary for the RMI® LCD Alcohol Tester. While it discusses the device's equivalence to a predicate device and mentions a "clinical trial" related to user understanding and device usage, it does not contain detailed acceptance criteria or a study proving the device directly meets specific performance metrics in terms of accuracy or precision against a gold standard for alcohol concentration measurement.

    The primary objective of the clinical trial mentioned was to establish that users could read and understand the instructions, properly use the device, and obtain comparable results to a predicate unit administered by a trained observer. This isn't a performance study in the sense of demonstrating accuracy against a laboratory reference.

    Here's an attempt to answer your request based on the limited information available in the provided document, highlighting what is not present:

    1. Table of Acceptance Criteria and Reported Device Performance

    Performance MetricAcceptance Criteria (Not explicitly stated for the new device's accuracy)Reported Device Performance (Implied equivalence)
    Accuracy of BAC measurementNot explicitly stated in terms of a specific range (e.g., +/- 0.01% BAC)The clinical trial showed that results were "comparable to those provided by a predicate unit administered by a trained observer." This indicates functional equivalence rather than specific accuracy data.
    User Understanding/Proper UseUser can read and understand instructions and properly use the device.The clinical trial showed that "the over the counter purchaser of this device could read and understand the instructions, could properly use the device."
    Comparability of resultsResults are comparable to a predicate unit administered by a trained observer.The clinical trial showed results were "comparable to those provided by a predicate unit administered by a trained observer."

    2. Sample Size for Test Set and Data Provenance

    • Sample Size for Test Set: Not specified. The document only mentions "a clinical trial was performed."
    • Data Provenance: Not specified (e.g., country of origin, retrospective or prospective). However, clinical trials are typically prospective.

    3. Number of Experts Used to Establish Ground Truth for Test Set and Qualifications

    • Number of Experts: Not specified.
    • Qualifications of Experts: The ground truth for direct alcohol concentration was likely the "predicate unit administered by a trained observer" but the qualifications of this observer are not specified.

    4. Adjudication Method for the Test Set

    • Not specified. Given the nature of the study (user-centric rather than expert interpretation of complex images/data), a formal adjudication method like "2+1" or "3+1" is unlikely to have been relevant or applied.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

    • No. An MRMC study was not described. The study focused on user interaction with the device and comparability to a single predicate unit's readings, not the improvement of human readers with AI assistance. This device is a standalone breathalyzer, not an AI-assisted diagnostic tool for interpretation by humans.

    6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

    • Yes, implicitly. The device itself is a standalone algorithm (microprocessor controlled) that measures and displays BAC. The "clinical trial" assessed whether users could operate it correctly and if its readings were comparable to a predicate device, but the device's core function itself is "standalone" in that it performs its measurement without human interpretation of its internal signals.

    7. Type of Ground Truth Used

    • Comparison to a predicate device: The implied ground truth for the BAC measurement aspect was the "predicate unit administered by a trained observer." For the usability aspect, direct observation of user interaction and instruction comprehension would form the "ground truth."

    8. Sample Size for the Training Set

    • Not Applicable / Not Specified. This device is a hardware-based alcohol tester, not an AI or machine learning model that requires a training set in the conventional sense. Its "training" would involve calibration and engineering design, not data-driven model training.

    9. How the Ground Truth for the Training Set Was Established

    • Not Applicable. See point 8.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1