FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

Atlas Multi-Drugs Screening Test Cup and Atlas Multi-Drugs Screening Test Panel are lateral flow chromatographic in vitro diagnostics immunoassays for the qualitative detection of following drugs in urine without the need of instruments: Amphetamine (AMP), Methylenedioxymethamphetamine (MDMA), Morphine (MOP), Oxycodone (OXY), Cocaine (COC), Nortriptyline, Methamphetamine (MET), Phencyclidine (PCP), Marijuana (THC), Secobarbital, Oxazepam, Methadone (MTD), Propoxyphene (PPX), Buprenorphine(BUP). The tests are intended for professional use only. The tests will yield preliminary positive results when the prescription drugs Secobarbital, oxazepam, Buprenorphine, Oxycodone, Propoxyphene, and Nortriptyline are ingested, even at or above therapeutic doses. There are no uniformly recognized drug levels for Secobarbital, oxazepam, Buprenorphine, Oxycodone, Propoxyphene, and Nortriptyline in urine. The multi-drugs screening tests (Cup and Panel formats) show the drug was or was not present at the cutoff level. The tests provide only preliminary test results, which must be confirmed by other methods such as gas chromatography/mass spectrometry (GC/MS). Clinical considerations and professional judgment should be applied to any drug of abuse test result, particularly when preliminary positive results are indicated. The tests are not intended to be used in monitoring the drug levels.

Device Description

Atlas Multi-Drugs Screening Test cup format is single use device. The user collects urine in the cup to the recommended volume. The reaction is initiated by movement the sample to the strip. The strips are incorporated into the sides of sample cup. Atlas Multi-Drugs Screening Test panel format is single use dip card device. The user inserts the absorbent end of the device in the urine sample to the maximum level indicated by the line on the device label. The test reaction is initiated by movement of the sample through the strip. Atlas Multi-Drugs Screening Tests (Cup and Panel Formats) detect up to 14 drugs.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the Atlas Multi-Drugs Screening Test Cup and Panel, extracted from the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implied by the precision and analytical sensitivity studies, which show the device consistently performs around its cut-off values. The clinical study indicates a high percentage of agreement with GC/MS or LC/MS.

Drug / Performance Metric	Acceptance Criteria (Implied)	Reported Device Performance
Precision (for each drug, across 3 lots and 3 users, at various concentrations relative to cut-off)	100% agreement between device result and expected result (negative for -100%, -75%, -50%, -25% cut-off; positive for cut-off, +25%, +50%, +75%, +100% cut-off)	100% agreement (45-/0+ or 45+/0-) across all lots and concentrations tested for all drugs listed (AMP, Secobarbital, Oxazepam, Buprenorphine, THC, MTD, MET, MDMA, Morphine 300 & 2000, Oxycodone, PCP, Propoxyphene, Nortriptyline, Cocaine) for both Panel and Cup formats.
Analytical Sensitivity (for each drug, n=25 samples per concentration)	Minimal misclassification at -25% and +25% cut-off; 100% agreement at -50% and +50% cut-off.	Panel: Minimal misclassifications at -25% cut-off (e.g., 1 out of 25 for BAR, THC, COC, MTD, MET, PPX) and +25% cut-off (e.g., 1 out of 25 for COC). 100% agreement at -50% and +50% cut-off for all drugs.
Cup: Similar results to Panel, with minimal misclassifications at -25% cut-off (e.g., 1 out of 25 for BAR, THC, COC, MTD, MET, PPX) and +25% cut-off (e.g., 1 out of 25 for COC). 100% agreement at -50% and +50% cut-off for all drugs.
Cross-Reactivity	Specific detection of the target drug; minimal to no cross-reactivity with structurally similar compounds at specified concentrations.	Detailed tables provided showing specific percentages of cross-reactivity for various compounds with each drug target. For substances showing no cross-reactivity, results are reported as ">100000 ng/ml" or ">0.3% / >0.01% / >1%" at very high concentrations.
Interference	No interference at 100 ug/ml (albumin at 20 mg/mL) for listed substances.	The study concluded that "no interference" was observed for a comprehensive list of common ingestible or physiological substances.
Effect of pH	No effect on test results across pH range 4.5-9.	The study demonstrated that "the PH does not affect the results."
Effect of Specific Gravity	No effect on test results across specific gravity range 1.005-1.030.	The study demonstrated that "the specific gravity do not affect the results."
Clinical Study (% Agreement with GC/MS or LC/MS)	High percentage agreement for both positive and negative results.	Panel & Cup (similar results for both):

% Agreement Among positive: 95%-100% (e.g., AMP 100%, THC 95%, PCP 100%).
% Agreement Among negative: 95%-100% (e.g., AMP 98%, THC 100%, PCP 95%). |
| Real-Time Stability | Stable for 24 months at 2-30°C. | The device was found stable for 24 months at 2-30°C. |
| Accelerated Stability | Stable for at least 24 months based on accelerated testing. | Based on accelerated testing, the device is expected to be stable for at least 24 months. |

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

Precision Study:
- Sample Size: For each drug, 9 different concentrations (ranging from -100% cut-off to +100% cut-off) were tested. Each concentration was tested with 15 tests (5 tests from each of 3 lots) for a total of 135 tests per drug. Across 14 drugs, this would be a total of 1890 tests per format (Cup and Panel).
- Data Provenance: Not explicitly stated, but the sample preparation involved spiking drugs into "prepared samples." This suggests laboratory-controlled samples rather than purely clinical, patient-derived samples for the precision study.
Analytical Sensitivity Study:
- Sample Size: For each drug, 5 different concentrations (Drug free, Cut-off-50%, Cut-off-25%, Cut-off+25%, Cut-off+50%) were tested. 25 samples were used for each concentration. Therefore, for each drug, 125 tests were performed. For 14 drugs, this amounts to 1750 tests per format (Cup and Panel).
- Data Provenance: "Drug-free urine pool was spiked with drugs." This indicates laboratory-prepared samples.
Analytical Specificity and Cross Reactivity Study:
- Sample Size: Not explicitly stated as a fixed number of samples, but implied to be a series of tests to determine the concentration at which cross-reacting substances are detected or not detected.
- Data Provenance: Laboratory-prepared samples with specific compounds and target drugs.
Interference Study:
- Sample Size: "Drug-free urine samples were collected." Each sample was spiked with drugs at cut-off-25%, cut-off, and cut-off+25%. These samples were then spiked with 100 ug/ml of various interfering substances (albumin at 20 mg/mL). The number of individual tests per interfering substance or per concentration is not specified, but the number of interfering substances is extensive (over 70 listed).
- Data Provenance: "Drug-free urine samples were collected," which could be clinical or laboratory-sourced. The spiking process makes them laboratory-controlled for interference testing.
Effect of pH Study:
- Sample Size: Samples spiked with drugs at cut-off-25%, cut-off, and cut-off+25% at 5 different pH values (4.5, 5, 6, 7, 8, 9).
- Data Provenance: "Drug-free urine samples were collected... spiked with drugs." Laboratory-controlled.
Effect of Specific Gravity Study:
- Sample Size: Samples spiked with drugs at cut-off-25%, cut-off, and cut-off+25% at 4 different specific gravity values (1.005, 1.015, 1.025, 1.030).
- Data Provenance: "Drug-free urine samples were collected... spiked with drugs." Laboratory-controlled.
Clinical Study (Method Comparison):
- Sample Size: 80 clinical specimens were tested for each drug.
- Data Provenance: Clinical specimens. "All samples used in this study belong to adults (males and females) with ages 18+." "PCP samples which were diluted as per the table mentioned below in the study due to difficulty in sourcing PCP real samples." The cohort also uses 27 other negative urine samples confirmed by GC/MS or LC/MS methods. This indicates a mix of prospectively collected general clinical samples and some retrospectively sourced/modified samples for specific drugs (PCP). The country of origin is not explicitly stated.

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

Clinical Study (Method Comparison): The ground truth for the clinical study was established by GC/MS (Gas Chromatography/Mass Spectrometry) or LC/MS (Liquid Chromatography/Mass Spectrometry). These are established analytical laboratory methods, not human expert consensus for this type of test. Therefore, human experts were not used to establish the ground truth in the traditional sense of medical image interpretation. The "experts" would be the laboratory personnel performing and interpreting the GC/MS or LC/MS results, who are usually highly qualified with specialized training and certifications in analytical chemistry and toxicology (e.g., clinical chemists, toxicologists). Their specific number or detailed qualifications are not provided in this document.

4. Adjudication Method for the Test Set

For the clinical study, the reference method (ground truth) was GC/MS or LC/MS. Discordant results between the device and the reference method were analyzed, but there is no mention of an independent adjudication process involving human readers. The GC/MS/LC/MS results are considered the definitive ground truth.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a "Multi-Reader Multi-Case (MRMC) comparative effectiveness study" comparing human readers with and without AI assistance was not mentioned, nor is it typically applicable to a rapid in-vitro diagnostic immunoassay like this, which is read visually by a single user. The device's performance is determined by its analytical accuracy against a gold standard (GC/MS/LC/MS) and its visual interpretability by a single user.

6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance)

Yes, the entire performance evaluation presented for the Atlas Multi-Drugs Screening Test Cup and Panel is a standalone performance study. The device itself (the immunoassay) is the 'algorithm' in this context, and its performance is evaluated directly against known concentrations and against reference laboratory methods (GC/MS/LC/MS). Human operators are involved in running the tests and reading the visual results, but the performance metrics (precision, sensitivity, specificity, agreement with GC/MS/LC/MS) are attributed to the device's inherent capability, not as an aid to human interpretation.

7. Type of Ground Truth Used

Precision, Analytical Sensitivity, Cross-Reactivity, Interference, pH, Specific Gravity Studies: Laboratory-prepared samples with known concentrations of drugs and interfering substances.
Clinical Study (Method Comparison): GC/MS or LC/MS (Gas Chromatography/Mass Spectrometry or Liquid Chromatography/Mass Spectrometry) results are used as the ground truth. These are considered the gold standard analytical methods for drug detection and quantification in urine.

8. Sample Size for the Training Set

This is a lateral flow immunoassay device, not an AI/Machine Learning algorithm that typically requires a distinct "training set." Therefore, there is no explicit training set sample size described in the context of an AI algorithm. The device's design and manufacturing process would be informed by prior research and development, but not in the sense of an algorithmic training data set.

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

As there is no explicit "training set" for an AI/ML algorithm in this context, this question is not applicable. The device's inherent performance is based on its biochemical design and manufacturing, which is validated through the studies described above.

Summary

Regulation Number and Section

§ 862.3100 Amphetamine test system.

(a)
Identification. An amphetamine test system is a device intended to measure amphetamine, a central nervous system stimulating drug, in plasma and urine. Measurements obtained by this device are used in the diagnosis and treatment of amphetamine use or overdose and in monitoring levels of amphetamine to ensure appropriate therapy.(b)
Classification. Class II (special controls). An amphetamine test system is not exempt if it is intended for any use other than employment or insurance testing or is intended for Federal drug testing programs. 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, provided the test system is intended for employment and insurance testing and includes a statement in the labeling that the device is intended solely for use in employment and insurance testing, and does not include devices intended for Federal drug testing programs (e.g., programs run by the Substance Abuse and Mental Health Services Administration (SAMHSA), the Department of Transportation (DOT), and the U.S. military).