(140 days)
The APAS Independence is an in vitro diagnostic system comprised of an instrument and software analysis module(s) for specific indications that are used to automate imaging and interpretation of microbial colonies on plates of solid culture media.
The APAS Independence, when using its urine analysis module, automates urine culture plate imaging and interpretation to detect the presence or absence of microbial growth on sheep blood and MacConkey agar culture plates that are inoculated with a 1µL sample volume. The APAS Independence, when using its urine analysis module, provides a semi-quantitative assessment of colony counts that are used as an aid in the diagnosis of urinary tract infection. All urine culture plates that are identified as positive for growth by the APAS Independence, when using its urine analysis module, must be reviewed by a trained microbiologist.
APAS Independence with Urine Analysis Module is a device designed to be used in a microbiology laboratory to automate the initial screening for the presence of growth on urine culture plates. It is an in vitro diagnostic device and has no direct contact with patients.
APAS Independence consists of an automated plate handling mechanism to move the plates through the instrument, an imaging station to capture an image of the culture plate, combined with software for analysis of the image, determination of growth and presentation of reports.
The APAS Independence with Urine Analysis Module is intended to determine whether growth is present or not, and to provide a semi-quantitative assessment of the colony count (if present). This information will then be combined with other available clinical information to screen out biological samples without growth. All other plates will be presented to a microbiologist for examination, determination of status and further testing according to conventional laboratory practice. This enables the microbiologist to focus on plates with potentially significant growth, thereby reducing the time until results can be reported.
The APAS Independence is intended to have different software modules, each of which will provide an assessment of growth for specific clinical indications. This submission covers only the APAS Independence with Urine Analysis Module. The APAS Independence with Urine Analysis Module is indicated for screening of culture plates for assessment of urinary tract infections where the urine specimens are collected and 1μl is plated onto Blood and MacConkey Agars and incubated at 35±2°C for 18 to 22 hours.
The provided text describes the acceptance criteria and the study proving the device meets these criteria for the APAS Independence with Urine Analysis Module (K183648).
1. Table of Acceptance Criteria (Implicit) and Reported Device Performance:
The document establishes substantial equivalence to a predicate device, APAS Compact with Urine Analysis Module. Therefore, the acceptance criteria are implicitly tied to the performance of the predicate device. The performance data presented focuses on agreement with the predicate.
| Acceptance Criterion (Implicit) | Reported Device Performance |
|---|---|
| Device Designation Agreement with Predicate (Blood Agar) | Positive: 98.7% (96.3-99.6%) agreement. APAS Independence did not return any Negative results when APAS Compact reported Positive. |
| Review: 86.5% (72.0-94.1%) agreement. | |
| Negative: 79.5% (69.2-87.0%) agreement. For samples classified as Negative by APAS Compact, APAS Independence either agreed or assigned Review/Positive (requiring microbiologist investigation). | |
| Combined Positive and Review: 100% (98.6-100%) agreement. | |
| Device Designation Agreement with Predicate (MacConkey Agar) | Positive: 99.3% (95.9-99.9%) agreement. One instance where APAS Compact reported Positive, APAS Independence was Negative. |
| Review: 80.0% (37.6-96.4%) agreement. | |
| Negative: 89.1% (84.2-92.6%) agreement. For samples classified as Negative by APAS Compact, APAS Independence either agreed or assigned Review/Positive. | |
| Combined Positive and Review: 98.6% (94.9-99.6%) agreement. | |
| Colony Count Agreement with Predicate (Blood Agar) | High level of agreement between the two systems. APAS Independence was more likely to overestimate than underestimate enumeration. (Specific percentages vary by CFU/mL range in Table 5.5). |
| Example: 79.5% agreement for 0 CFU/mL, 90.4% for 10^3 CFU/mL, 90.5% for 10^4 CFU/mL, 99.2% for 10^5 CFU/mL. | |
| Colony Count Agreement with Predicate (MacConkey Agar) | High level of agreement between the two systems. APAS Independence was more likely to overestimate than underestimate enumeration. (Specific percentages vary by CFU/mL range in Table 5.6). |
| Example: 89.1% agreement for 0 CFU/mL, 89.7% for 10^3 CFU/mL, 87.5% for 10^4 CFU/mL, 100% for 10^5 CFU/mL. | |
| Colony Morphology Detection Rate (Blood Agar) | Probability of >95% detection across all colony types. (Specific percentages in Table 5.7, e.g., Alpha hemolysis: 0.971, Beta hemolysis: 0.963, Coliform: 0.989, Cream white: 0.951, Granular: 0.997, Small: 0.983, Swarming: 1.000). APAS Independence likely to overestimate some colony morphologies (AC-/Al+ > AC+/Al-). |
| Colony Morphology Detection Rate (MacConkey Agar) | Probability of >95% detection across all colony types. (Specific percentages in Table 5.8, e.g., Lactose fermenter: 0.991, Non-fermenter: 0.994, Non-pigmented: 1.000, Red Pink: 1.000). |
| Reproducibility and Precision (Colony Counts) | Similar to APAS Compact with Urine Analysis Module. Inversely proportional to colony count. |
| Exemplar %CV values (from Table 5.9): | |
| MacConkey (E. coli): Lowest Dilution 7.2%, Middle Dilution 5.6%, Highest Dilution 21.7%. | |
| TS-SBA (E. coli): Lowest Dilution 5.0%, Middle Dilution 6.7%, Highest Dilution 20.4%. | |
| Software Verification and Validation | Documentation provided as recommended by FDA guidance. Considered "moderate" level of concern. |
| Safety and EMC | Complies with IEC 61010-1: 2010, IEC 61010-2-101: 2017, UL 61010-1: 2012 for safety, and IEC 61326-1: 2013, IEC 61326-2-6: 2013, FCC Part 15B for EMC. |
2. Sample Size and Data Provenance for Test Set:
- Sample Size: 350 leftover clinical urine samples.
- Data Provenance: The document states "leftover clinical urine samples." The country of origin is not explicitly stated but is implicitly Australia, given the submitter's country for the predicate device's de novo application (DEN150059) was Australia. The data is retrospective as it uses "leftover clinical urine samples."
3. Number of Experts and Qualifications for Ground Truth for Test Set:
Not applicable for this section as the study's ground truth for the comparison was the predicate device's performance, not human expert consensus, for the new device's equivalence study.
4. Adjudication Method for the Test Set:
Not applicable. The study compares the new device (APAS Independence) to the predicate device (APAS Compact) itself, not to human expert reads requiring adjudication. Discrepancies between the two devices are analyzed, and the clinical implications (e.g., misclassification leading to microbiologist review) are discussed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- Was it done? No, an MRMC study comparing human readers with and without AI assistance was not conducted directly for the APAS Independence with Urine Analysis Module in this submission.
- The document states that the predicate device (APAS Compact with Urine Analysis Module) had three clinical studies (LBT001, LBT002, LBT003) submitted for its de novo applicationDEN150059, which "showed that APAS performed similarly to a microbiologist in reading and interpreting agar plates." This indicates that the predicate device's performance was evaluated against human microbiologists. The current submission established equivalence to this predicate.
- Effect Size: Not applicable since an MRMC study was not performed as part of this specific submission.
6. Standalone (Algorithm Only) Performance:
- Was it done? Yes, the entire study presented for the APAS Independence with Urine Analysis Module is a standalone (algorithm only) performance comparison between the new device and the predicate device. Both the APAS Independence and the APAS Compact are automated systems that read and interpret images without direct human intervention in the initial classification process.
7. Type of Ground Truth Used:
The ground truth for the APAS Independence performance evaluation was the performance of the predicate device (APAS Compact with Urine Analysis Module). The study aimed to demonstrate that the new device performs equivalently to the already-cleared predicate.
8. Sample Size for the Training Set:
The document does not explicitly state the sample size for the training set of the APAS Independence with Urine Analysis Module. It only details the test set used for the comparison with the predicate device (350 samples). However, it mentions that both devices "utilize the same core APAS technology and the same urine analysis module," implying shared underlying algorithmic development and training.
9. How the Ground Truth for the Training Set was Established:
The document does not provide details on how the ground truth for the training set (if any specific to APAS Independence's development rather than its use of the predicate's technology) was established. However, given that the "same core APAS technology and the same urine analysis module" are utilized as the predicate, it is highly likely that the training methodologies and ground truth establishment for the predicate device would apply. For the predicate device (APAS Compact), the clinical studies (LBT001, LBT002, LBT003) referenced for the de novo application would have established ground truth, likely through expert consensus of microbiologists, as it stated "APAS performed similarly to a microbiologist."
§ 866.2190 Automated image assessment system for microbial colonies on solid culture media.
(a)
Identification. An automated image assessment system for microbial colonies on solid culture media is a system that is intended to assess the presence or absence of microbial colonies on solid microbiological culture medium, and to interpret their number, and phenotypic and morphologic characteristics through analysis of two dimensional digital images as an aid in diagnosis of infectious disease.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Premarket notification submissions must include a detailed description of the device, including the technology employed, components and software modules, as well as a detailed explanation of the result algorithms and any expert rules that are used to assess colony characteristics and enumerate colonies from image capture through end result.
(2) Premarket notification submissions must include detailed documentation of the analytical studies performed to characterize device performance to support the intended use, as appropriate.
(3) Premarket notification submissions must include detailed documentation from clinical studies performed on a population that is consistent with the intended use population.
(i) The clinical studies must establish the device performance based on comparison to results obtained by an acceptable reference method, as appropriate.
(ii) The clinical study documentation must include the study protocol with a predefined statistical analysis plan and the final report documenting support for the Indications for Use and the results of the statistical analysis, as appropriate.
(4) Premarket notification submissions must include detailed documentation for device software, including but not limited to software applications and hardware based components that incorporate software, and any decision-making thresholds used to generate results for the device. If a part of a Total Laboratory Automation System, the premarket notification submission must include detailed documentation addressing the instrument and software system integration.
(5) Premarket notification submissions must include detailed documentation of appropriate instructions for use regarding the intended user's device quality control procedures for the instrument system and components, as appropriate.
(6) The 21 CFR 809.10 compliant device labeling must include:
(i) Detailed user instructions to mitigate the risk of failure to operate the instrument correctly.
(ii) A detailed explanation of the interpretation of results and limitations regarding the need for review of culture plates by a qualified microbiologist, as appropriate.
(iii) A summary of performance data obtained from the analytical studies used to support device performance, as appropriate.
(iv) A summary of performance data obtained from clinical studies performed on a population that is consistent with the intended use population, as appropriate.
(7) Under 21 CFR 820.30 compliant design control, device manufacturers must, as appropriate:
(i) Conduct human factors/usability validation testing with the final version of the labeling and related materials to adequately mitigate the risk of failure to operate the instrument correctly.
(ii) Document a device training program that will be offered to the end user to adequately mitigate the risk of failure to operate the instrument correctly.